{
  "data": {
    "a": {
      "slug": "langfuse",
      "name": "Langfuse API + MCP",
      "vendor": "Langfuse (ClickHouse)",
      "vendorUrl": "https://langfuse.com",
      "company": "langfuse.com",
      "kind": "http-api",
      "category": "agent-observability",
      "summary": "Open-source tracing, evaluation, prompt management and datasets for LLM apps and agents, built on OpenTelemetry.",
      "url": "https://www.anchorterminal.com/tools/langfuse",
      "markdownUrl": "https://www.anchorterminal.com/tools/langfuse.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/langfuse.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/langfuse.json",
      "dns": "langfuse.grade.anchorterminal.com",
      "repo": "https://github.com/langfuse/langfuse",
      "license": "MIT (core), commercial licence for the ee directories",
      "transports": [
        "http",
        "streamable-http"
      ],
      "remoteUrl": "https://cloud.langfuse.com/api/public",
      "packages": [
        {
          "registry": "pypi",
          "name": "langfuse"
        },
        {
          "registry": "npm",
          "name": "@langfuse/tracing"
        },
        {
          "registry": "npm",
          "name": "@langfuse/client"
        }
      ],
      "auth": "api-key",
      "authNotes": "Project-scoped key pair (public `pk-lf-...`, secret `sk-lf-...`) sent as HTTP Basic auth, for both the REST API and the MCP server at `/api/public/mcp`. Since 16 October 2026 a new key takes one permission set, Full access, Viewer (read-only), Ingestion or Scores ingestion, which can't be changed later. Organisation-level keys exist for SCIM and admin APIs on Enterprise.",
      "pricing": "freemium",
      "pricingNotes": "Cloud Hobby is free with 50,000 units a month, 30 days of data and 2 users, no card. Core $29 a month with 100,000 units and 90 days, Pro $199 a month with 3 years of data, Enterprise $2,499 a month. Extra units cost $8 per 100,000 on paid plans, lower with volume. A unit is one trace, observation or score. Teams add-on $300 a month for SSO and fine-grained RBAC. Self-hosted open source is free with unlimited usage, you pay for your own Postgres, ClickHouse, Redis and blob storage. Self-hosted Enterprise is custom and sold on top of a ClickHouse plan (https://langfuse.com/pricing).",
      "priceSummary": "$29 / mo",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402 support in docs or pricing (checked 2026-09-30).",
        "endpoints": []
      },
      "toolCount": 98,
      "popularity": {
        "githubStars": 35235,
        "npmWeekly": 3039593,
        "pypiWeekly": 5865664,
        "asOf": "2026-09-30"
      },
      "docsUrl": "https://langfuse.com/docs",
      "llmsTxt": "https://langfuse.com/llms.txt",
      "openapi": "https://cloud.langfuse.com/generated/api/openapi.yml",
      "capabilities": [
        "obs.traces",
        "obs.evals",
        "obs.prompts",
        "obs.datasets"
      ],
      "tags": [
        "hosted",
        "freemium",
        "no-card",
        "open-source",
        "self-hosted",
        "mcp",
        "llms-txt",
        "openapi",
        "python",
        "typescript",
        "webhooks"
      ],
      "lastRelease": "2026-10-29",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 74.3,
        "grade": "BB",
        "agentReady": true,
        "rank": 147,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 2,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 74,
          "maintenance": 88,
          "payments": 60,
          "reliability": 80,
          "schema": 93,
          "security": 77,
          "transparency": 86
        },
        "assessment": {
          "confidence": "high",
          "date": "2026-11-01"
        },
        "negative": -5,
        "negativeNotes": [
          "2025-11-09 to 2026-01-21. Three moderate advisories, cross-organisation enumeration of member and invitation lists (GHSA-94hf-6gqq-pj69), SSO account takeover through CSRF or phishing (GHSA-w9pw-c549-5m6w) and an unauthenticated Slack OAuth install that could link Slack to any project (GHSA-pvq7-vvfj-p98x). All fixed and published, eight to eleven months old, so -2 (https://github.com/langfuse/langfuse/security/advisories)",
          "2026-10-27, -3. v4.71.0, a minor release, stops self-hosted deployments with an Enterprise licence key and `LANGFUSE_REQUIRE_FIPS=true` from starting, and FIPS mode now needs a Government licence key (`lf_gov_`). The commit marks it BREAKING CHANGE. The 23 October changelog entry first said FIPS mode needed an Enterprise licence and was available from v4.57.0. It was changed to name the Government licence and v4.71.0 on 28 October, the day after the release, so no notice was given beforehand (https://github.com/langfuse/langfuse/commit/165b621fdf8fc7d34232df8d5a74a5ab36d3fc83, https://github.com/langfuse/langfuse-docs/commit/0e087c325947b3fded371150fc374b492cb7be93)"
        ],
        "verdict": "MIT core with no usage limits when self-hosted, and project API keys can be limited to read-only or ingestion-only access. 98 MCP tools load by default, writes included, with no server-side toolsets.",
        "bestFor": "Teams that want open source they can self-host or a predictable cloud bill, across tracing, evals, prompts and datasets.",
        "strengths": [
          "MIT core with no usage limits when self-hosted, and self-hosted telemetry documented with an off switch",
          "Project API keys can be created read-only (Viewer), ingestion-only or scores-only on every plan, since 16 October 2026",
          "Per-unit cloud pricing at $8 per 100,000 units, and a free Hobby plan with 50,000 units and no card",
          "Bug bounty, SOC 2 Type II, ISO 27001 and GitHub advisories handled in public",
          "Deprecated v1 read APIs have a dated sunset of 16 November 2026 and a migration guide"
        ],
        "weaknesses": [
          "98 MCP tools load by default, writes included, and the MCP docs still leave read-only to a client allowlist",
          "17 incidents on the status history in the 90 days to 1 November, mostly ingestion delays, one of them over six hours",
          "Python SDK v5 and JS/TS SDK v6 drop `api.scores_v3`, `api.legacy.*` and `api.ingestion`, and need Langfuse v4.59.0 or later",
          "No uptime SLA found, only support response targets",
          "Self-hosting means running ClickHouse, Postgres, Redis and S3-compatible storage"
        ],
        "agentNotes": [
          "Use a Viewer key for an agent that only reads traces. Keys created before 16 October keep full access and can't be narrowed",
          "Allowlist only the MCP tools the agent needs. All 98 load by default, writes included, and they share the General API bucket, so wait for `Retry-After` on 429",
          "Ask `listObservations` for specific `fields`. Requesting input, output or metadata caps the page at 50 rows and the range at 14 days",
          "Move off `GET /api/public/traces`, `/observations`, `/sessions` and the other v1 reads before 16 November 2026, and replace `api.scores_v3` when moving to Python SDK v5 or JS/TS SDK v6",
          "Pick the regional host (cloud, us.cloud, jp.cloud, hipaa.cloud) that matches the project's keys"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 4,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "high",
            "grade": "BB",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 74.3
          }
        ],
        "editorialScores": {
          "ergonomics": 74,
          "maintenance": 88,
          "payments": 60,
          "reliability": 80,
          "schema": 93,
          "security": 77,
          "transparency": 91
        },
        "provenanceScore": 81,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-01",
            "maintenance": "2026-11-01",
            "payments": "2026-11-01",
            "reliability": "2026-11-01",
            "schema": "2026-11-01",
            "security": "2026-11-01",
            "transparency": "2026-11-01"
          },
          "last": "2026-11-01",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-01",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl -u \"$LANGFUSE_PUBLIC_KEY:$LANGFUSE_SECRET_KEY\" https://cloud.langfuse.com/api/public/projects",
        "claudeCode": "claude mcp add --transport http langfuse https://cloud.langfuse.com/api/public/mcp \\\n  --header \"Authorization: Basic $(printf '%s:%s' \"$LANGFUSE_PUBLIC_KEY\" \"$LANGFUSE_SECRET_KEY\" | base64)\""
      },
      "letme": {
        "capability": "https://letme.dev/obs.traces",
        "tool": "https://letme.dev/langfuse"
      },
      "area": "developer",
      "unitPrices": [
        {
          "item": "Core plan",
          "unit": "month",
          "usd": 29,
          "note": "100,000 units included, 90 days of data"
        },
        {
          "item": "Pro plan",
          "unit": "month",
          "usd": 199,
          "note": "100,000 units included, 3 years of data"
        },
        {
          "item": "Enterprise plan",
          "unit": "month",
          "usd": 2499,
          "note": "100,000 units included, audit logs, SCIM, SLAs"
        },
        {
          "item": "Teams add-on",
          "unit": "month",
          "usd": 300,
          "note": "SSO, SSO enforcement and fine-grained RBAC on Pro"
        }
      ],
      "provenance": {
        "legalEntity": "Langfuse GmbH (a ClickHouse, Inc. company)",
        "domain": "langfuse.com",
        "domainRegistered": "2023-04-20",
        "endpointOnVendorDomain": true,
        "terms": "https://clickhouse.com/legal/clickhouse-general-terms-and-conditions",
        "privacy": "https://langfuse.com/privacy",
        "statusPage": "https://status.langfuse.com",
        "changelog": "https://langfuse.com/changelog",
        "securityTxt": "none",
        "checked": "2026-09-30",
        "notes": [
          "The imprint names Langfuse GmbH in Berlin. The privacy notice is issued by ClickHouse, Inc. and langfuse.com/terms redirects to the ClickHouse general terms"
        ],
        "score": 81
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/langfuse.json",
      "live": {
        "slug": "langfuse",
        "probe": {
          "target": "https://cloud.langfuse.com/api/public",
          "method": "get",
          "lastAt": "2026-11-18T22:43:37.524889642Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 169,
          "authRequired": false,
          "uptime24h": 99.59,
          "uptime30d": 99.99,
          "p50ms24h": 55,
          "p95ms24h": 212,
          "samples24h": 241,
          "samples30d": 7837,
          "days": [
            {
              "date": "2026-10-18",
              "probes": 256,
              "ok": 256
            },
            {
              "date": "2026-10-19",
              "probes": 255,
              "ok": 255
            },
            {
              "date": "2026-10-20",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-21",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-22",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-23",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-24",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-25",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-10-26",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-27",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-28",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-29",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-30",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-31",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-11-01",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-11-02",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-11-03",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-11-04",
              "probes": 246,
              "ok": 246
            },
            {
              "date": "2026-11-05",
              "probes": 185,
              "ok": 185
            },
            {
              "date": "2026-11-06",
              "probes": 241,
              "ok": 241
            },
            {
              "date": "2026-11-07",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-08",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-09",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-10",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-11",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-12",
              "probes": 245,
              "ok": 245
            },
            {
              "date": "2026-11-13",
              "probes": 238,
              "ok": 238
            },
            {
              "date": "2026-11-14",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-15",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-16",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-17",
              "probes": 242,
              "ok": 242
            },
            {
              "date": "2026-11-18",
              "probes": 228,
              "ok": 227
            }
          ],
          "since": "2026-10-08T00:00:00Z"
        },
        "vendorStatus": {
          "page": "https://status.langfuse.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-11-18T22:38:08.168931101Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "langfuse/langfuse",
            "version": "v4.82.0",
            "released": "2026-11-17",
            "seenAt": "2026-11-18T18:00:49.993497853Z"
          },
          {
            "registry": "npm",
            "name": "@langfuse/client",
            "version": "6.1.1",
            "seenAt": "2026-11-18T18:00:48.547742172Z"
          },
          {
            "registry": "npm",
            "name": "@langfuse/tracing",
            "version": "6.1.1",
            "seenAt": "2026-11-18T18:00:47.37529413Z"
          },
          {
            "registry": "pypi",
            "name": "langfuse",
            "version": "5.2.0",
            "released": "2026-11-05",
            "seenAt": "2026-11-18T18:00:47.206899628Z"
          }
        ],
        "githubStars": 37597,
        "npmWeekly": 4675731,
        "pypiWeekly": 7583013,
        "securityTxt": {
          "url": "https://langfuse.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-18T16:29:41.405453045Z"
        },
        "llmsTxt": {
          "url": "https://langfuse.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:14:48.496234911Z"
        },
        "domain": {
          "domain": "langfuse.com",
          "registered": "2023-04-20",
          "source": "https://rdap.verisign.com/com/v1/domain/langfuse.com",
          "checkedAt": "2026-11-15T15:25:50.951671127Z"
        },
        "pages": [
          {
            "url": "https://langfuse.com/changelog",
            "kind": "changelog",
            "status": 404,
            "checkedAt": "2026-11-18T21:46:20.33216157Z",
            "changedAt": "0001-01-01T00:00:00Z"
          },
          {
            "url": "https://langfuse.com/blog/joining-clickhouse",
            "kind": "deprecations",
            "status": 304,
            "checkedAt": "2026-11-18T21:46:17.635756337Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "4e8ff98bb557"
          },
          {
            "url": "https://langfuse.com/changelog/2026-10-14-python-sdk-v5-js-sdk-v6",
            "kind": "deprecations",
            "status": 304,
            "checkedAt": "2026-11-18T21:46:22.244443298Z",
            "changedAt": "2026-10-21T00:29:03.204686539Z",
            "fingerprint": "51a1acd1fb4a"
          },
          {
            "url": "https://langfuse.com/changelog/2026-10-23-fips-mode",
            "kind": "deprecations",
            "status": 304,
            "checkedAt": "2026-11-18T21:46:23.826781748Z",
            "changedAt": "2026-11-11T17:03:32.364280263Z",
            "fingerprint": "681e7f8436c9"
          },
          {
            "url": "https://langfuse.com/faq/all/deprecated-api-migration.md",
            "kind": "deprecations",
            "status": 304,
            "checkedAt": "2026-11-18T21:46:25.880965013Z",
            "changedAt": "2026-11-07T14:12:30.938766311Z",
            "fingerprint": "600b3ee6ae71"
          },
          {
            "url": "https://langfuse.com/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-11-18T21:46:27.803340763Z",
            "changedAt": "2026-11-18T21:46:27.803340763Z",
            "fingerprint": "5fd425ead51d"
          },
          {
            "url": "https://langfuse.com/privacy",
            "kind": "privacy",
            "status": 304,
            "checkedAt": "2026-11-18T21:46:29.994630665Z",
            "changedAt": "2026-11-12T17:42:28.389735522Z",
            "fingerprint": "9ad24cacf142"
          },
          {
            "url": "https://clickhouse.com/legal/clickhouse-general-terms-and-conditions",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-18T21:34:54.693817739Z",
            "changedAt": "2026-11-17T20:53:54.398051307Z",
            "fingerprint": "7ef123b83fcc"
          }
        ],
        "mcpTools": {
          "url": "https://cloud.langfuse.com/api/public/mcp",
          "checkedAt": "2026-11-18T04:25:07.003533789Z",
          "status": "auth",
          "note": "asks for credentials before listing its tools",
          "changedAt": "2026-11-07T01:45:40.974797389Z"
        },
        "github": {
          "repo": "langfuse/langfuse",
          "checkedAt": "2026-11-16T12:14:56.57000089Z",
          "stars": 37486,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-16T12:11:22Z",
          "openIssues": 337,
          "openPRs": 847,
          "issuesOpened90d": 433,
          "issuesClosed90d": 400,
          "prsMerged90d": 2459,
          "ci": {
            "branch": "main",
            "runs": 50,
            "success": 48,
            "failure": 0,
            "other": 2,
            "latest": "success",
            "latestAt": "2026-11-16T12:11:58Z"
          },
          "advisories": [
            {
              "ghsa": "GHSA-2524-j966-gfgh",
              "cve": "CVE-2026-41487",
              "severity": "low",
              "published": "2026-04-17T07:23:10Z"
            },
            {
              "ghsa": "GHSA-pvq7-vvfj-p98x",
              "cve": "CVE-2026-24055",
              "severity": "medium",
              "published": "2026-01-21T20:54:58Z"
            },
            {
              "ghsa": "GHSA-w9pw-c549-5m6w",
              "cve": "CVE-2025-65107",
              "severity": "medium",
              "published": "2025-11-19T23:28:36Z"
            },
            {
              "ghsa": "GHSA-94hf-6gqq-pj69",
              "cve": "CVE-2025-64504",
              "severity": "medium",
              "published": "2025-11-09T18:26:33Z"
            }
          ],
          "replies": {
            "sampled": 25,
            "unanswered": 12,
            "medianDays": 1.5
          }
        },
        "updatedAt": "2026-11-18T22:43:37.524889642Z"
      },
      "streak": {
        "days": 2,
        "from": "2026-11-16",
        "last": {
          "kind": "shutdown",
          "date": "2026-11-16",
          "what": "Deprecated v1 read endpoints (`GET /api/public/traces`, `GET /api/public/observations`, `GET /api/public/sessions` and their by-ID forms) are served on Langfuse Cloud until this date. Move to the v2 Observations and Metrics APIs",
          "source": "https://langfuse.com/faq/all/deprecated-api-migration.md"
        },
        "best": 20
      }
    },
    "answer": "Langfuse API + MCP scores 74.3 (BB) on agent readiness against Plurai Simulation's 52.6 (D), and leads in every scored category.",
    "b": {
      "slug": "plurai-simulation",
      "name": "Plurai Simulation",
      "vendor": "Plurai",
      "vendorUrl": "https://www.plurai.ai",
      "company": "plurai.ai",
      "kind": "platform",
      "category": "agent-observability",
      "summary": "Plurai Simulation is a plugin for Claude Code, Codex CLI and GitHub Copilot CLI that maps an agent's code, mocks its tools and data, plays generated scenarios against it and proposes fixes, using Plurai's hosted backend.",
      "url": "https://www.anchorterminal.com/tools/plurai-simulation",
      "markdownUrl": "https://www.anchorterminal.com/tools/plurai-simulation.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/plurai-simulation.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/plurai-simulation.json",
      "dns": "plurai-simulation.grade.anchorterminal.com",
      "repo": "https://github.com/plurai-ai/plurai-simulation",
      "transports": [
        "streamable-http",
        "stdio"
      ],
      "remoteUrl": "https://sandbox.plurai.ai/v1/mcp",
      "packages": [
        {
          "registry": "pypi",
          "name": "plurai-simulation-sdk"
        }
      ],
      "auth": "api-key",
      "authNotes": "First run opens a browser sign-in or sign-up, picks an organisation and mints a key the SDK saves in `~/.plurai/credentials.json` (mode 600), never shown. `plurai logout` revokes it. For CI, a key created in the dashboard goes in `PLURAI_TOKEN` with `PLURAI_URL`. Keys expire. No scopes found.",
      "pricing": "freemium",
      "pricingNotes": "The Free plan has 12,300 credits, 2 agent setups, 3 runs and 10 sandbox hours once, no overage. Base $60 a month and Business $210 a month with monthly credits, runs and sandbox hours, then $0.02 or $0.015 a credit up to an admin-set limit. A credit is one cent of model-provider usage at list price. Card requirement for Free not stated. Enterprise by agreement.",
      "priceSummary": "$0.02 / credit",
      "where": "both",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the pricing page, docs, terms, plugin repository or the hosted MCP tool list, read on 2026-11-18.",
        "endpoints": []
      },
      "toolCount": 52,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://docs.plurai.ai/",
      "llmsTxt": "https://docs.plurai.ai/llms.txt",
      "capabilities": [
        "obs.evals",
        "obs.datasets"
      ],
      "tags": [
        "hosted",
        "closed-source",
        "mcp",
        "remote-mcp",
        "agent-skills",
        "coding-agent",
        "python",
        "freemium",
        "free-tier",
        "usage-priced",
        "llms-txt",
        "no-status-page",
        "no-telemetry",
        "new"
      ],
      "lastRelease": "2026-11-15",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 52.6,
        "grade": "D",
        "agentReady": false,
        "rank": 1078,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 20,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 58,
          "maintenance": 72,
          "payments": 45,
          "reliability": 22,
          "schema": 81,
          "security": 52,
          "transparency": 52
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Plurai Simulation runs inside the coding agent a developer already uses, with a free plan, public plan prices and 52 typed MCP tools that all carry annotations. Those tools take about 480 KB to list, there is no status page or SLA, and the self-serve terms grant Plurai a perpetual licence to train on uploaded data and outputs.",
        "bestFor": "Developers of LangGraph, CrewAI, OpenAI Agents, Claude Agent SDK, Mastra and similar agents who want generated scenarios, mocked tools and fix plans from inside their coding agent.",
        "strengths": [
          "Installs from a public marketplace into Claude Code, Codex CLI and GitHub Copilot CLI, and signs in through the browser without the key entering the chat",
          "Free plan with 12,300 credits, three runs and 10 sandbox hours, and public plan prices ($60 and $210 a month) with per-credit overage",
          "All 52 hosted MCP tools have input and output schemas and annotations, with 14 read-only and 5 destructive, and long jobs take idempotent starts",
          "Every upload prints a disclosure first and is logged in `.plurai/uploads/audit.log`, with optional local anonymisation that fails closed",
          "SDK 1.0.0 to 1.0.3 and plugin 1.0.4 to 1.0.8 shipped between 9 and 15 November 2026 with changelogs"
        ],
        "weaknesses": [
          "The self-serve terms grant Plurai a perpetual, irrevocable licence to use customer content, outputs and traces to train its models, which survives account deletion",
          "The 52 MCP tool definitions total about 480 KB, the largest over 56 KB, with no toolsets or subsets",
          "No status page, SLA, published rate limits or security.txt, and the security policy promises only best-effort acknowledgement",
          "The plugin is proprietary and its terms forbid using outputs or results to build a competing evaluation product",
          "The terms refer to a privacy policy for self-serve products that wasn't found, and the linked policy (27 April 2026) says prompts aren't retained"
        ],
        "agentNotes": [
          "Ask the user before the first `/simulate`, since it opens a browser sign-in and uploads agent descriptions as written",
          "Set `anonymize: true` in `plurai.config.yaml` before the first upload if the data holds personal details, because an Environment can't change posture later",
          "Treat exit code 20 as credit, capacity or an outage and stop, rather than rerunning the simulation",
          "Use `PLURAI_SIM_NONINTERACTIVE=1` with `PLURAI_URL` and `PLURAI_TOKEN` in CI, and never paste the key into chat",
          "Prefer Claude models in Copilot CLI and Default mode in Codex, as the docs say the flows are tuned for them"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 52.6
          }
        ],
        "editorialScores": {
          "ergonomics": 58,
          "maintenance": 72,
          "payments": 45,
          "reliability": 22,
          "schema": 81,
          "security": 52,
          "transparency": 41
        },
        "provenanceScore": 63,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "lastMoved": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install plurai-simulation-sdk",
        "claudeCode": "/plugin marketplace add plurai-ai/plurai-plugins\n/plugin install plurai-simulation@plurai-plugins"
      },
      "letme": {
        "capability": "https://letme.dev/obs.evals",
        "tool": "https://letme.dev/plurai-simulation"
      },
      "area": "developer",
      "unitPrices": [
        {
          "item": "Sim credit, Base plan overage",
          "unit": "credit",
          "usd": 0.02,
          "note": "A credit is one cent of model-provider usage at list price"
        },
        {
          "item": "Sim credit, Business plan overage",
          "unit": "credit",
          "usd": 0.015,
          "note": "A credit is one cent of model-provider usage at list price"
        }
      ],
      "provenance": {
        "legalEntity": "Plurai Inc.",
        "domain": "plurai.ai",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://www.plurai.ai/terms-of-service",
        "privacy": "https://www.plurai.ai/privacy-policy",
        "statusPage": "",
        "changelog": "https://github.com/plurai-ai/plurai-simulation/blob/main/CHANGELOG.md",
        "securityTxt": "none",
        "checked": "2026-11-18",
        "notes": [
          "Plurai Inc., 488 Madison Avenue, Suite 1103, New York, NY, is named in the terms (last updated 10 November 2026, Delaware law). The plugin licence names Plurai Inc.",
          "plurai.ai and docs.plurai.ai publish robots.txt rules that allowed the pages read. sandbox.plurai.ai answers 404 for robots.txt.",
          "/.well-known/security.txt on www.plurai.ai answers an error page. SECURITY.md in the plugin repository asks for private GitHub reports.",
          "The self-serve terms forbid bots, crawlers and other automated access to the Product except through the APIs Plurai documents, and forbid using outputs to build a competing product. Recorded as a fact, no deduction.",
          "pypi.org answered the SDK's project page with a client challenge, so its licence is unread. No status page found. RDAP wasn't queried."
        ],
        "score": 63
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/plurai-simulation.json",
      "live": {
        "slug": "plurai-simulation",
        "probe": {
          "target": "https://sandbox.plurai.ai/v1/mcp",
          "method": "get",
          "lastAt": "2026-11-18T22:43:52.572607436Z",
          "lastOk": true,
          "lastStatus": 405,
          "lastMs": 317,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 254,
          "p95ms24h": 446,
          "samples24h": 11,
          "samples30d": 11,
          "days": [
            {
              "date": "2026-11-18",
              "probes": 11,
              "ok": 11
            }
          ],
          "since": "2026-11-18T21:38:22.28752903Z"
        },
        "updatedAt": "2026-11-18T22:43:52.572607436Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-18",
        "sinceWatching": true,
        "best": 0
      }
    },
    "edges": [
      {
        "by": 58,
        "category": "reliability",
        "leads": "langfuse",
        "name": "Reliability",
        "reasons": {
          "a": "incident.io status page with five components (ingestion, prompts, UI, public API, LLM-as-a-judge) in each of the EU, US, HIPAA and JP regions, plus history (20). The history page, re-read on 1 November, dates each component's impact. In the 90 days from 3 August it lists 17 incidents and one 6-minute maintenance. 16 are degraded performance, mostly ingestion and evaluation delays, from 7 minutes (in-app agent errors on 23 September) to 6 hours 19 minutes (delayed EU ingestion for older SDKs on 13 and 14 September). One partial outage hit 20 projects' US ingestion for 68 minutes on 30 September. Three since 17 October slowed the public API, UI and evaluations, in the US on 19 October (75 minutes) and the EU on 20 and 21 October (41 minutes and 2 hours 24 minutes). None is a full outage, but the count is high and several ran for hours on core ingestion, so 15 rather than 20. Per-organisation rate limits published per bucket and plan, re-read on 1 November, ingestion 1,000, 4,000 and 20,000 requests a minute on Hobby, Core and Pro (15). 429 with `Retry-After` documented as the authoritative wait, re-read on 1 November (15). Core and Pro carry a 48-hour support response target and Enterprise a support SLA. We found no uptime SLA (5). API and MCP are GA (10).",
          "b": "No status page found on plurai.ai, the docs or the plugin repository (0). With no history to read, 5. No rate limits with numbers found. The pricing page gives plan allowances, not request limits (0). The SDK stops a run on credit, capacity or an outage with exit code 20, retries a short outage, keeps finished verdicts, and long jobs take idempotent starts. No Retry-After or 429 guidance found (7). No SLA found (0). Launched as generally available on 11 November 2026 with SDK 1.0.0 (10). 0+5+0+7+0+10 = 22."
        },
        "scores": {
          "a": 80,
          "b": 22
        }
      },
      {
        "by": 34,
        "category": "transparency",
        "leads": "langfuse",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "MIT core with the ee directories under a commercial licence (27). Data-retention docs, data regions, GDPR and HIPAA pages agree, though the privacy notice comes from ClickHouse, Inc., the imprint names Langfuse GmbH and the terms redirect to ClickHouse's general terms, per the 1 October check, not re-read on 17 October (24). Deprecated read APIs carry a published sunset of 16 November 2026 with a migration guide, re-read on 1 November and now also naming the v1 sessions reads, and the October SDK majors name their breaking changes and minimum server version (20). Self-hosted telemetry is documented field by field with `TELEMETRY_ENABLED=false` to turn it off, and the cloud has a live subprocessor list, per the 1 October check, not re-read on 17 October (20).",
          "b": "The plugin is proprietary under a licence from Plurai Inc., and the terms (last updated 10 November 2026, Delaware law) are clear. The open-source IntellAgent framework is separate (15). Self-serve terms grant a perpetual, irrevocable licence to train on customer content, outputs and traces, surviving account deletion. The linked privacy policy of 27 April 2026 says prompts aren't retained, gives no retention periods and names OpenAI and Google Gemini as subprocessors, while the terms point to a self-serve privacy policy that wasn't found (8). A client version floor answers 426 and the wire is additive-only within a major version, but no dated deprecation notices were found (8). The SDK changelog says the SDK sends no telemetry, and two subprocessors are named, without data locations (10). 15+8+8+10 = 41."
        },
        "scores": {
          "a": 86,
          "b": 52
        }
      },
      {
        "by": 25,
        "category": "security",
        "leads": "langfuse",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Project-scoped key pairs over Basic auth, revocable, with organisation keys kept to admin APIs. Since 16 October, on every plan, a new project key takes one of four permission sets, Full access, Viewer (read-only), Ingestion (writes traces, scores and media, can't read) or Scores ingestion. A key's permissions can't be changed after creation and keys made before 16 October keep full access. Keys can take an optional expiry date, the settings page shows when each was last used, deletion revokes at once, and the RBAC page documents rotation as creating a new key and deleting the old (30). A Viewer key is read-only on the public API. The MCP server's source, re-read at v4.72.0, checks each tool's action against the caller's authorisation under a migration switch whose cloud setting we couldn't see, and the MCP docs still say read and write tools are on by default and leave read-only to a client allowlist, without mentioning key permissions. Annotations mark reads and destructive tools (14). Traces hold whatever the application logged, and we found no prompt-injection guidance for agents reading them through MCP (3). Audit logs on Enterprise only (10). Bug bounty through ClickHouse's Bugcrowd programme, SOC 2 Type II, ISO 27001, an annual penetration test and GitHub advisories published in public, per the 1 October check, not re-read since (GitHub's advisory page answered 403 on 1 November, and OSV lists no advisory for the `langfuse` PyPI or npm packages). langfuse.com/.well-known/security.txt returned 404 on 1 November (20).",
          "b": "The browser sign-in mints a key per machine, saved with mode 600 and never shown, which `plurai logout` revokes. Dashboard keys serve CI. Keys expire, and the plugin sends a key only to the backend that issued it. No scopes found (20). Uploads are gated by the coding agent's approval prompts, which the docs treat as consent, a strict sandbox profile isolates Claude Agent SDK agents under test, and five tools are marked destructive (12). No guidance on untrusted content in tool results found (5). Each upload prints a disclosure and is written to a local audit log (10). SECURITY.md asks for private GitHub reports with best-effort acknowledgement. No security.txt, bug bounty or certification found (5). The MCP server answered `initialize` and `tools/list` without a key. 20+12+5+10+5 = 52."
        },
        "scores": {
          "a": 77,
          "b": 52
        }
      },
      {
        "by": 16,
        "category": "ergonomics",
        "leads": "langfuse",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "98 MCP tool definitions in the source at v4.72.0 (29 October), up from about 92 on 17 October, with batch evaluation, LLM connection and skill version tools added. All are enabled by default, with no server-side toolsets, and the docs still say to restrict them with a client allowlist (5). Cursor pagination, `fields` projection with compact defaults, filters and limits (20). 429s carry `Retry-After`, and invalid MCP calls return named errors (16). 51 tools set `readOnlyHint: true` and 37 set `destructiveHint`. Dataset writes are upserts (18). Few required parameters. Python and TypeScript SDKs (15).",
          "b": "52 tools whose definitions total about 480 KB, a median of 5.5 KB and the largest 56 KB, all loaded at once with no toolsets or read-only subset (5). List tools take `limit` and `offset` (12). Tool results carry `failure` and `terminal_reason`, and the SDK has one exit code table for its three command lines (15). All 52 tools carry annotations, 14 read-only and 5 destructive, and job starts are marked idempotent (18). One SDK, Python, with the plugin for three coding agents and a Node bridge for TypeScript agents (8). 5+12+15+18+8 = 58."
        },
        "scores": {
          "a": 74,
          "b": 58
        }
      },
      {
        "by": 16,
        "category": "maintenance",
        "leads": "langfuse",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Server v4.72.0 tagged on 2026-10-29 (30). Nine v4 server tags from v4.64.0 on 19 October to v4.72.0 on 29 October, after 14 from 2 to 16 October, and v3.225.13 to v3.225.15 for the older line (20). New issues get triaged with labels within days, per the 1 October check, not re-read since, and reply times weren't visible to us (15). Python SDK v5.1.0 tagged on 2026-10-30 and JS SDK v6.1.0, current majors built for Langfuse v4 (15). CodeQL, Semgrep, Snyk and zizmor run in CI alongside the build pipeline. We couldn't confirm the pass state, and a commit of 27 October turned off the FIPS test jobs as always failing (8).",
          "b": "Plugin v1.0.8 tagged 15 November 2026 and `plurai-simulation-sdk` 1.0.3 on PyPI on 13 November (30). Five plugin tags and four SDK releases since 9 November (20). The plugin repository is a five-commit mirror, github.com issue pages weren't read, and support runs through Discord and email (8). One official SDK, Python, current with the plugin (10). A mirror CI workflow only, and its state couldn't be seen (4). 30+20+8+10+4 = 72."
        },
        "scores": {
          "a": 88,
          "b": 72
        }
      },
      {
        "by": 15,
        "category": "payments",
        "leads": "langfuse",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No x402 or other machine payment (0). Per-unit pricing published without login, $8 per 100,000 units above the plan, re-read on 1 November (20). Hobby is free with 50,000 units a month and \"No credit card required\" (20). A person signs up in a browser to create keys. Free self-hosting isn't an agent route (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.",
          "b": "No x402 or other machine payment (0). Plan prices and pay-as-you-go rates ($0.02 a credit on Base, $0.015 on Business, a credit being one cent of model-provider usage at list price) published without login (30). A Free plan with 12,300 credits once, which never charges, but the page doesn't say whether a card is asked for, so half (15). A person signs in or signs up in a browser on first run (0). 0+30+15+0 = 45."
        },
        "scores": {
          "a": 60,
          "b": 45
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "Platform",
        "name": "Kind"
      },
      {
        "a": "Langfuse (ClickHouse)",
        "b": "Plurai",
        "name": "Vendor"
      },
      {
        "a": "https://cloud.langfuse.com/api/public",
        "b": "https://sandbox.plurai.ai/v1/mcp",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP, Streamable HTTP",
        "b": "Streamable HTTP, stdio",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "MIT (core), commercial licence for the ee directories",
        "b": "none",
        "name": "Licence"
      },
      {
        "a": "98",
        "b": "52",
        "name": "Tools exposed"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-29",
        "b": "2026-11-15",
        "name": "Last release"
      },
      {
        "a": "2026-06-24",
        "b": "2026-11-10",
        "name": "Terms last updated"
      },
      {
        "a": "2026-08-21",
        "b": "2026-04-27",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Terms restrict automated access"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "35k stars, 3M npm/wk, 5.9M PyPI/wk",
        "b": "none",
        "name": "Popularity"
      },
      {
        "a": "4/5 (2)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Langfuse API + MCP scores 74.3 (BB) on agent readiness against Plurai Simulation's 52.6 (D), and leads in every scored category.",
        "question": "Which is better for AI agents, Langfuse API + MCP or Plurai Simulation?"
      },
      {
        "answer": "Yes. Langfuse API + MCP has a hosted endpoint at https://cloud.langfuse.com/api/public and Plurai Simulation at https://sandbox.plurai.ai/v1/mcp.",
        "question": "Can an agent call Langfuse API + MCP and Plurai Simulation without installing anything?"
      },
      {
        "answer": "Langfuse API + MCP is open source (MIT (core), commercial licence for the ee directories). No open-source release is listed for Plurai Simulation.",
        "question": "Are Langfuse API + MCP and Plurai Simulation open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 80 against 22",
          "Schema \u0026 documentation, 93 against 81",
          "Agent ergonomics, 74 against 58",
          "Security \u0026 auth, 77 against 52",
          "Payments \u0026 pricing, 60 against 45",
          "Maintenance \u0026 community, 88 against 72",
          "Transparency \u0026 trust, 86 against 52"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "Free to start without a card",
          "Open source"
        ],
        "goodFor": "Teams that want open source they can self-host or a predictable cloud bill, across tracing, evals, prompts and datasets.",
        "slug": "langfuse",
        "watchFor": "98 MCP tools load by default, writes included, and the MCP docs still leave read-only to a client allowlist"
      },
      {
        "aheadOn": null,
        "also": [
          "Runs on your own machine",
          "No incidents deducted, where Langfuse API + MCP loses 5 points for them"
        ],
        "goodFor": "Developers of LangGraph, CrewAI, OpenAI Agents, Claude Agent SDK, Mastra and similar agents who want generated scenarios, mocked tools and fix plans from inside their coding agent.",
        "slug": "plurai-simulation",
        "watchFor": "The self-serve terms grant Plurai a perpetual, irrevocable licence to use customer content, outputs and traces to train its models, which survives account deletion"
      }
    ],
    "history": {
      "langfuse": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 2.5,
          "from": 71.8,
          "fromGrade": "BB",
          "to": 74.3,
          "toGrade": "BB"
        },
        {
          "causes": [
            "event"
          ],
          "date": "2026-11-01",
          "delta": -3,
          "from": 74.8,
          "fromGrade": "BB",
          "to": 71.8,
          "toGrade": "BB"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-27",
          "delta": 0,
          "from": 74.8,
          "fromGrade": "BB",
          "to": 74.8,
          "toGrade": "BB"
        }
      ],
      "plurai-simulation": [
        {
          "causes": [
            "terms"
          ],
          "date": "2026-11-18",
          "delta": -0.1,
          "from": 52.7,
          "fromGrade": "D",
          "to": 52.6,
          "toGrade": "D"
        }
      ]
    },
    "job": {
      "capability": "obs.evals",
      "name": "Evaluations"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent-tree-vs-langfuse.json",
        "title": "Agent Tree vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/agent-tree-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agents-tree-vs-langfuse.json",
        "title": "agents-tree vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/agents-tree-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/arize-phoenix-vs-langfuse.json",
        "title": "Arize Phoenix vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/arize-phoenix-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/baserun-vs-langfuse.json",
        "title": "Baserun vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/baserun-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/botgauge-vs-langfuse.json",
        "title": "BotGauge vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/botgauge-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/braintrust-vs-langfuse.json",
        "title": "Braintrust API + MCP vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/braintrust-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/galileo-vs-langfuse.json",
        "title": "Galileo API + MCP vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/galileo-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/helicone-vs-langfuse.json",
        "title": "Helicone AI Gateway + MCP vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/helicone-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/honeyhive-vs-langfuse.json",
        "title": "HoneyHive vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/honeyhive-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hue-vs-langfuse.json",
        "title": "Hue vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/hue-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/laminar-vs-langfuse.json",
        "title": "Laminar API + MCP vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/laminar-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-langsmith.json",
        "title": "Langfuse API + MCP vs LangSmith API + MCP",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-langsmith"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-langwatch.json",
        "title": "Langfuse API + MCP vs LangWatch",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-langwatch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-mlflow-tracing.json",
        "title": "Langfuse API + MCP vs MLflow Tracing",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-mlflow-tracing"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-navige.json",
        "title": "Langfuse API + MCP vs Navige",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-navige"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-opik.json",
        "title": "Langfuse API + MCP vs Opik API + MCP",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-opik"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-overmind.json",
        "title": "Langfuse API + MCP vs Overmind",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-overmind"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-prefactor.json",
        "title": "Langfuse API + MCP vs Prefactor",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-prefactor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-pydantic-logfire.json",
        "title": "Langfuse API + MCP vs Pydantic Logfire",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-pydantic-logfire"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-respan.json",
        "title": "Langfuse API + MCP vs Respan API + MCP",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-respan"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langfuse-vs-wandb-weave.json",
        "title": "Langfuse API + MCP vs W\u0026B Weave",
        "url": "https://www.anchorterminal.com/compare/langfuse-vs-wandb-weave"
      },
      {
        "json": "https://www.anchorterminal.com/compare/arize-phoenix-vs-plurai-simulation.json",
        "title": "Arize Phoenix vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/arize-phoenix-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/baserun-vs-plurai-simulation.json",
        "title": "Baserun vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/baserun-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/botgauge-vs-plurai-simulation.json",
        "title": "BotGauge vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/botgauge-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/braintrust-vs-plurai-simulation.json",
        "title": "Braintrust API + MCP vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/braintrust-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepeval-vs-langfuse.json",
        "title": "DeepEval vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/deepeval-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepeval-vs-plurai-simulation.json",
        "title": "DeepEval vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/deepeval-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/galileo-vs-plurai-simulation.json",
        "title": "Galileo API + MCP vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/galileo-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-langfuse.json",
        "title": "Gauge CLI vs Langfuse API + MCP",
        "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-langfuse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-plurai-simulation.json",
        "title": "Gauge CLI vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/helicone-vs-plurai-simulation.json",
        "title": "Helicone AI Gateway + MCP vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/helicone-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/honeyhive-vs-plurai-simulation.json",
        "title": "HoneyHive vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/honeyhive-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hue-vs-plurai-simulation.json",
        "title": "Hue vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/hue-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/laminar-vs-plurai-simulation.json",
        "title": "Laminar API + MCP vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/laminar-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langsmith-vs-plurai-simulation.json",
        "title": "LangSmith API + MCP vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/langsmith-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/langwatch-vs-plurai-simulation.json",
        "title": "LangWatch vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/langwatch-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-plurai-simulation.json",
        "title": "MLflow Tracing vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/opik-vs-plurai-simulation.json",
        "title": "Opik API + MCP vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/opik-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/overmind-vs-plurai-simulation.json",
        "title": "Overmind vs Plurai Simulation",
        "url": "https://www.anchorterminal.com/compare/overmind-vs-plurai-simulation"
      },
      {
        "json": "https://www.anchorterminal.com/compare/plurai-simulation-vs-prefactor.json",
        "title": "Plurai Simulation vs Prefactor",
        "url": "https://www.anchorterminal.com/compare/plurai-simulation-vs-prefactor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/plurai-simulation-vs-pydantic-logfire.json",
        "title": "Plurai Simulation vs Pydantic Logfire",
        "url": "https://www.anchorterminal.com/compare/plurai-simulation-vs-pydantic-logfire"
      },
      {
        "json": "https://www.anchorterminal.com/compare/plurai-simulation-vs-respan.json",
        "title": "Plurai Simulation vs Respan API + MCP",
        "url": "https://www.anchorterminal.com/compare/plurai-simulation-vs-respan"
      },
      {
        "json": "https://www.anchorterminal.com/compare/plurai-simulation-vs-wandb-weave.json",
        "title": "Plurai Simulation vs W\u0026B Weave",
        "url": "https://www.anchorterminal.com/compare/plurai-simulation-vs-wandb-weave"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 58,
        "edge": "langfuse",
        "key": "reliability",
        "langfuse": 80,
        "name": "Reliability",
        "plurai-simulation": 22,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 12,
        "edge": "langfuse",
        "key": "schema",
        "langfuse": 93,
        "name": "Schema \u0026 documentation",
        "plurai-simulation": 81,
        "weight": 13
      },
      {
        "by": 16,
        "edge": "langfuse",
        "key": "ergonomics",
        "langfuse": 74,
        "name": "Agent ergonomics",
        "plurai-simulation": 58,
        "weight": 13
      },
      {
        "by": 25,
        "edge": "langfuse",
        "key": "security",
        "langfuse": 77,
        "name": "Security \u0026 auth",
        "plurai-simulation": 52,
        "weight": 14
      },
      {
        "by": 15,
        "edge": "langfuse",
        "key": "payments",
        "langfuse": 60,
        "name": "Payments \u0026 pricing",
        "plurai-simulation": 45,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 16,
        "edge": "langfuse",
        "key": "maintenance",
        "langfuse": 88,
        "name": "Maintenance \u0026 community",
        "plurai-simulation": 72,
        "weight": 7
      },
      {
        "by": 34,
        "edge": "langfuse",
        "key": "transparency",
        "langfuse": 86,
        "name": "Transparency \u0026 trust",
        "plurai-simulation": 52,
        "weight": 7
      }
    ],
    "summary": "Langfuse API + MCP scores 74.3 (BB) on agent readiness against Plurai Simulation's 52.6 (D), and leads in every scored category. Both do evaluations.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "langfuse": "MIT core with no usage limits when self-hosted, and project API keys can be limited to read-only or ingestion-only access. 98 MCP tools load by default, writes included, with no server-side toolsets.",
      "plurai-simulation": "Plurai Simulation runs inside the coding agent a developer already uses, with a free plan, public plan prices and 52 typed MCP tools that all carry annotations. Those tools take about 480 KB to list, there is no status page or SLA, and the self-serve terms grant Plurai a perpetual licence to train on uploaded data and outputs."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/langfuse-vs-plurai-simulation",
    "json": "https://www.anchorterminal.com/compare/langfuse-vs-plurai-simulation.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/langfuse-vs-plurai-simulation.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/langfuse-vs-plurai-simulation.min.md"
  },
  "markdown": "Langfuse API + MCP scores 74.3 (BB) on agent readiness against Plurai Simulation's 52.6 (D), and leads in every scored category. Both do evaluations.\n\n- Langfuse API + MCP: grade BB, 74.3/100, rank #147 of 1557. Markdown https://www.anchorterminal.com/tools/langfuse.md · JSON https://www.anchorterminal.com/api/v1/tools/langfuse.json\n- Plurai Simulation: grade D, 52.6/100, rank #1078 of 1557. Markdown https://www.anchorterminal.com/tools/plurai-simulation.md · JSON https://www.anchorterminal.com/api/v1/tools/plurai-simulation.json\n- Best agent tracing, monitoring and evaluation tools: https://www.anchorterminal.com/best/agent-observability/index.md\n- All 294 evals comparisons: https://www.anchorterminal.com/compare/agent-observability/index.md\n\n## Which one, for what\n\n### Langfuse API + MCP (BB)\n\nGood for: Teams that want open source they can self-host or a predictable cloud bill, across tracing, evals, prompts and datasets.\n\nAhead on:\n- Reliability, 80 against 22\n- Schema \u0026 documentation, 93 against 81\n- Agent ergonomics, 74 against 58\n- Security \u0026 auth, 77 against 52\n- Payments \u0026 pricing, 60 against 45\n- Maintenance \u0026 community, 88 against 72\n- Transparency \u0026 trust, 86 against 52\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Free to start without a card\n- Open source\n\nWatch for: 98 MCP tools load by default, writes included, and the MCP docs still leave read-only to a client allowlist\n\n### Plurai Simulation (D)\n\nGood for: Developers of LangGraph, CrewAI, OpenAI Agents, Claude Agent SDK, Mastra and similar agents who want generated scenarios, mocked tools and fix plans from inside their coding agent.\n\nAlso in its favour:\n- Runs on your own machine\n- No incidents deducted, where Langfuse API + MCP loses 5 points for them\n\nWatch for: The self-serve terms grant Plurai a perpetual, irrevocable licence to use customer content, outputs and traces to train its models, which survives account deletion\n\n\n## Why the edge\n\n### Reliability: Langfuse API + MCP +58\n\n- Langfuse API + MCP (80): incident.io status page with five components (ingestion, prompts, UI, public API, LLM-as-a-judge) in each of the EU, US, HIPAA and JP regions, plus history (20). The history page, re-read on 1 November, dates each component's impact. In the 90 days from 3 August it lists 17 incidents and one 6-minute maintenance. 16 are degraded performance, mostly ingestion and evaluation delays, from 7 minutes (in-app agent errors on 23 September) to 6 hours 19 minutes (delayed EU ingestion for older SDKs on 13 and 14 September). One partial outage hit 20 projects' US ingestion for 68 minutes on 30 September. Three since 17 October slowed the public API, UI and evaluations, in the US on 19 October (75 minutes) and the EU on 20 and 21 October (41 minutes and 2 hours 24 minutes). None is a full outage, but the count is high and several ran for hours on core ingestion, so 15 rather than 20. Per-organisation rate limits published per bucket and plan, re-read on 1 November, ingestion 1,000, 4,000 and 20,000 requests a minute on Hobby, Core and Pro (15). 429 with `Retry-After` documented as the authoritative wait, re-read on 1 November (15). Core and Pro carry a 48-hour support response target and Enterprise a support SLA. We found no uptime SLA (5). API and MCP are GA (10).\n- Plurai Simulation (22): No status page found on plurai.ai, the docs or the plugin repository (0). With no history to read, 5. No rate limits with numbers found. The pricing page gives plan allowances, not request limits (0). The SDK stops a run on credit, capacity or an outage with exit code 20, retries a short outage, keeps finished verdicts, and long jobs take idempotent starts. No Retry-After or 429 guidance found (7). No SLA found (0). Launched as generally available on 11 November 2026 with SDK 1.0.0 (10). 0+5+0+7+0+10 = 22.\n\n### Transparency \u0026 trust: Langfuse API + MCP +34\n\n- Langfuse API + MCP (86): MIT core with the ee directories under a commercial licence (27). Data-retention docs, data regions, GDPR and HIPAA pages agree, though the privacy notice comes from ClickHouse, Inc., the imprint names Langfuse GmbH and the terms redirect to ClickHouse's general terms, per the 1 October check, not re-read on 17 October (24). Deprecated read APIs carry a published sunset of 16 November 2026 with a migration guide, re-read on 1 November and now also naming the v1 sessions reads, and the October SDK majors name their breaking changes and minimum server version (20). Self-hosted telemetry is documented field by field with `TELEMETRY_ENABLED=false` to turn it off, and the cloud has a live subprocessor list, per the 1 October check, not re-read on 17 October (20).\n- Plurai Simulation (52): The plugin is proprietary under a licence from Plurai Inc., and the terms (last updated 10 November 2026, Delaware law) are clear. The open-source IntellAgent framework is separate (15). Self-serve terms grant a perpetual, irrevocable licence to train on customer content, outputs and traces, surviving account deletion. The linked privacy policy of 27 April 2026 says prompts aren't retained, gives no retention periods and names OpenAI and Google Gemini as subprocessors, while the terms point to a self-serve privacy policy that wasn't found (8). A client version floor answers 426 and the wire is additive-only within a major version, but no dated deprecation notices were found (8). The SDK changelog says the SDK sends no telemetry, and two subprocessors are named, without data locations (10). 15+8+8+10 = 41.\n\n### Security \u0026 auth: Langfuse API + MCP +25\n\n- Langfuse API + MCP (77): Project-scoped key pairs over Basic auth, revocable, with organisation keys kept to admin APIs. Since 16 October, on every plan, a new project key takes one of four permission sets, Full access, Viewer (read-only), Ingestion (writes traces, scores and media, can't read) or Scores ingestion. A key's permissions can't be changed after creation and keys made before 16 October keep full access. Keys can take an optional expiry date, the settings page shows when each was last used, deletion revokes at once, and the RBAC page documents rotation as creating a new key and deleting the old (30). A Viewer key is read-only on the public API. The MCP server's source, re-read at v4.72.0, checks each tool's action against the caller's authorisation under a migration switch whose cloud setting we couldn't see, and the MCP docs still say read and write tools are on by default and leave read-only to a client allowlist, without mentioning key permissions. Annotations mark reads and destructive tools (14). Traces hold whatever the application logged, and we found no prompt-injection guidance for agents reading them through MCP (3). Audit logs on Enterprise only (10). Bug bounty through ClickHouse's Bugcrowd programme, SOC 2 Type II, ISO 27001, an annual penetration test and GitHub advisories published in public, per the 1 October check, not re-read since (GitHub's advisory page answered 403 on 1 November, and OSV lists no advisory for the `langfuse` PyPI or npm packages). langfuse.com/.well-known/security.txt returned 404 on 1 November (20).\n- Plurai Simulation (52): The browser sign-in mints a key per machine, saved with mode 600 and never shown, which `plurai logout` revokes. Dashboard keys serve CI. Keys expire, and the plugin sends a key only to the backend that issued it. No scopes found (20). Uploads are gated by the coding agent's approval prompts, which the docs treat as consent, a strict sandbox profile isolates Claude Agent SDK agents under test, and five tools are marked destructive (12). No guidance on untrusted content in tool results found (5). Each upload prints a disclosure and is written to a local audit log (10). SECURITY.md asks for private GitHub reports with best-effort acknowledgement. No security.txt, bug bounty or certification found (5). The MCP server answered `initialize` and `tools/list` without a key. 20+12+5+10+5 = 52.\n\n### Agent ergonomics: Langfuse API + MCP +16\n\n- Langfuse API + MCP (74): 98 MCP tool definitions in the source at v4.72.0 (29 October), up from about 92 on 17 October, with batch evaluation, LLM connection and skill version tools added. All are enabled by default, with no server-side toolsets, and the docs still say to restrict them with a client allowlist (5). Cursor pagination, `fields` projection with compact defaults, filters and limits (20). 429s carry `Retry-After`, and invalid MCP calls return named errors (16). 51 tools set `readOnlyHint: true` and 37 set `destructiveHint`. Dataset writes are upserts (18). Few required parameters. Python and TypeScript SDKs (15).\n- Plurai Simulation (58): 52 tools whose definitions total about 480 KB, a median of 5.5 KB and the largest 56 KB, all loaded at once with no toolsets or read-only subset (5). List tools take `limit` and `offset` (12). Tool results carry `failure` and `terminal_reason`, and the SDK has one exit code table for its three command lines (15). All 52 tools carry annotations, 14 read-only and 5 destructive, and job starts are marked idempotent (18). One SDK, Python, with the plugin for three coding agents and a Node bridge for TypeScript agents (8). 5+12+15+18+8 = 58.\n\n### Maintenance \u0026 community: Langfuse API + MCP +16\n\n- Langfuse API + MCP (88): Server v4.72.0 tagged on 2026-10-29 (30). Nine v4 server tags from v4.64.0 on 19 October to v4.72.0 on 29 October, after 14 from 2 to 16 October, and v3.225.13 to v3.225.15 for the older line (20). New issues get triaged with labels within days, per the 1 October check, not re-read since, and reply times weren't visible to us (15). Python SDK v5.1.0 tagged on 2026-10-30 and JS SDK v6.1.0, current majors built for Langfuse v4 (15). CodeQL, Semgrep, Snyk and zizmor run in CI alongside the build pipeline. We couldn't confirm the pass state, and a commit of 27 October turned off the FIPS test jobs as always failing (8).\n- Plurai Simulation (72): Plugin v1.0.8 tagged 15 November 2026 and `plurai-simulation-sdk` 1.0.3 on PyPI on 13 November (30). Five plugin tags and four SDK releases since 9 November (20). The plugin repository is a five-commit mirror, github.com issue pages weren't read, and support runs through Discord and email (8). One official SDK, Python, current with the plugin (10). A mirror CI workflow only, and its state couldn't be seen (4). 30+20+8+10+4 = 72.\n\n### Payments \u0026 pricing: Langfuse API + MCP +15\n\n- Langfuse API + MCP (60): No x402 or other machine payment (0). Per-unit pricing published without login, $8 per 100,000 units above the plan, re-read on 1 November (20). Hobby is free with 50,000 units a month and \"No credit card required\" (20). A person signs up in a browser to create keys. Free self-hosting isn't an agent route (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.\n- Plurai Simulation (45): No x402 or other machine payment (0). Plan prices and pay-as-you-go rates ($0.02 a credit on Base, $0.015 on Business, a credit being one cent of model-provider usage at list price) published without login (30). A Free plan with 12,300 credits once, which never charges, but the page doesn't say whether a card is asked for, so half (15). A person signs in or signs up in a browser on first run (0). 0+30+15+0 = 45.\n\n## Score by category\n\n| Category | Weight | Langfuse API + MCP | Plurai Simulation | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 80 | 22 | Langfuse API + MCP +58 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 93 | 81 | Langfuse API + MCP +12 |\n| Agent ergonomics | 13% | 74 | 58 | Langfuse API + MCP +16 |\n| Security \u0026 auth | 14% | 77 | 52 | Langfuse API + MCP +25 |\n| Payments \u0026 pricing | 10% | 60 | 45 | Langfuse API + MCP +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 88 | 72 | Langfuse API + MCP +16 |\n| Transparency \u0026 trust | 7% | 86 | 52 | Langfuse API + MCP +34 |\n| Negative events | ≤15 | -5 | 0 | |\n| **Total** | | **74.3 · BB** | **52.6 · D** | |\n\n## Facts side by side\n\n| Fact | Langfuse API + MCP | Plurai Simulation |\n| --- | --- | --- |\n| Kind | HTTP API | Platform |\n| Vendor | Langfuse (ClickHouse) | Plurai |\n| Hosted endpoint | `https://cloud.langfuse.com/api/public` | `https://sandbox.plurai.ai/v1/mcp` |\n| Transports | HTTP, Streamable HTTP | Streamable HTTP, stdio |\n| Auth | API key | API key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | MIT (core), commercial licence for the ee directories | none |\n| Tools exposed | 98 | 52 |\n| Read-only variant documented | yes | yes |\n| llms.txt | yes | yes |\n| Last release | 2026-10-29 | 2026-11-15 |\n| Terms last updated | 2026-06-24 | 2026-11-10 |\n| Privacy policy last updated | 2026-08-21 | 2026-04-27 |\n| Customer content may train models | not found in the text | yes |\n| Terms restrict automated access | not found in the text | yes |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 35k stars, 3M npm/wk, 5.9M PyPI/wk | none |\n| Agent reviews | 4/5 (2) | none |\n\n## How the scores have moved\n\n### Langfuse API + MCP\n\n- +2.5 on 13 November 2026: checklist\n- -3.0 on 1 November 2026: negative event\n- no change on 27 October 2026: checklist\n\n### Plurai Simulation\n\n- -0.1 on 18 November 2026: terms\n\n## Verdicts\n\n**Langfuse API + MCP.** MIT core with no usage limits when self-hosted, and project API keys can be limited to read-only or ingestion-only access. 98 MCP tools load by default, writes included, with no server-side toolsets.\n\n**Plurai Simulation.** Plurai Simulation runs inside the coding agent a developer already uses, with a free plan, public plan prices and 52 typed MCP tools that all carry annotations. Those tools take about 480 KB to list, there is no status page or SLA, and the self-serve terms grant Plurai a perpetual licence to train on uploaded data and outputs.\n\n## Before you call either\n\n### Langfuse API + MCP\n\n1. Use a Viewer key for an agent that only reads traces. Keys created before 16 October keep full access and can't be narrowed\n2. Allowlist only the MCP tools the agent needs. All 98 load by default, writes included, and they share the General API bucket, so wait for `Retry-After` on 429\n3. Ask `listObservations` for specific `fields`. Requesting input, output or metadata caps the page at 50 rows and the range at 14 days\n4. Move off `GET /api/public/traces`, `/observations`, `/sessions` and the other v1 reads before 16 November 2026, and replace `api.scores_v3` when moving to Python SDK v5 or JS/TS SDK v6\n5. Pick the regional host (cloud, us.cloud, jp.cloud, hipaa.cloud) that matches the project's keys\n\n### Plurai Simulation\n\n1. Ask the user before the first `/simulate`, since it opens a browser sign-in and uploads agent descriptions as written\n2. Set `anonymize: true` in `plurai.config.yaml` before the first upload if the data holds personal details, because an Environment can't change posture later\n3. Treat exit code 20 as credit, capacity or an outage and stop, rather than rerunning the simulation\n4. Use `PLURAI_SIM_NONINTERACTIVE=1` with `PLURAI_URL` and `PLURAI_TOKEN` in CI, and never paste the key into chat\n5. Prefer Claude models in Copilot CLI and Default mode in Codex, as the docs say the flows are tuned for them\n\n## Questions\n\n### Which is better for AI agents, Langfuse API + MCP or Plurai Simulation?\n\nLangfuse API + MCP scores 74.3 (BB) on agent readiness against Plurai Simulation's 52.6 (D), and leads in every scored category.\n\n### Can an agent call Langfuse API + MCP and Plurai Simulation without installing anything?\n\nYes. Langfuse API + MCP has a hosted endpoint at https://cloud.langfuse.com/api/public and Plurai Simulation at https://sandbox.plurai.ai/v1/mcp.\n\n### Are Langfuse API + MCP and Plurai Simulation open source?\n\nLangfuse API + MCP is open source (MIT (core), commercial licence for the ee directories). No open-source release is listed for Plurai Simulation.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/langfuse-vs-plurai-simulation.json, and with the fewest tokens: https://www.anchorterminal.com/compare/langfuse-vs-plurai-simulation.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"langfuse\", \"b\": \"plurai-simulation\"}`. From a terminal: `anchor compare langfuse plurai-simulation`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/langfuse.json and https://www.anchorterminal.com/api/v1/tools/plurai-simulation.json\n\n## Other comparisons with Langfuse API + MCP or Plurai Simulation\n\n- [Agent Tree vs Langfuse API + MCP](https://www.anchorterminal.com/compare/agent-tree-vs-langfuse.md)\n- [agents-tree vs Langfuse API + MCP](https://www.anchorterminal.com/compare/agents-tree-vs-langfuse.md)\n- [Arize Phoenix vs Langfuse API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-langfuse.md)\n- [Baserun vs Langfuse API + MCP](https://www.anchorterminal.com/compare/baserun-vs-langfuse.md)\n- [BotGauge vs Langfuse API + MCP](https://www.anchorterminal.com/compare/botgauge-vs-langfuse.md)\n- [Braintrust API + MCP vs Langfuse API + MCP](https://www.anchorterminal.com/compare/braintrust-vs-langfuse.md)\n- [Galileo API + MCP vs Langfuse API + MCP](https://www.anchorterminal.com/compare/galileo-vs-langfuse.md)\n- [Helicone AI Gateway + MCP vs Langfuse API + MCP](https://www.anchorterminal.com/compare/helicone-vs-langfuse.md)\n- [HoneyHive vs Langfuse API + MCP](https://www.anchorterminal.com/compare/honeyhive-vs-langfuse.md)\n- [Hue vs Langfuse API + MCP](https://www.anchorterminal.com/compare/hue-vs-langfuse.md)\n- [Laminar API + MCP vs Langfuse API + MCP](https://www.anchorterminal.com/compare/laminar-vs-langfuse.md)\n- [Langfuse API + MCP vs LangSmith API + MCP](https://www.anchorterminal.com/compare/langfuse-vs-langsmith.md)\n- [Langfuse API + MCP vs LangWatch](https://www.anchorterminal.com/compare/langfuse-vs-langwatch.md)\n- [Langfuse API + MCP vs MLflow Tracing](https://www.anchorterminal.com/compare/langfuse-vs-mlflow-tracing.md)\n- [Langfuse API + MCP vs Navige](https://www.anchorterminal.com/compare/langfuse-vs-navige.md)\n- [Langfuse API + MCP vs Opik API + MCP](https://www.anchorterminal.com/compare/langfuse-vs-opik.md)\n- [Langfuse API + MCP vs Overmind](https://www.anchorterminal.com/compare/langfuse-vs-overmind.md)\n- [Langfuse API + MCP vs Prefactor](https://www.anchorterminal.com/compare/langfuse-vs-prefactor.md)\n- [Langfuse API + MCP vs Pydantic Logfire](https://www.anchorterminal.com/compare/langfuse-vs-pydantic-logfire.md)\n- [Langfuse API + MCP vs Respan API + MCP](https://www.anchorterminal.com/compare/langfuse-vs-respan.md)\n- [Langfuse API + MCP vs W\u0026B Weave](https://www.anchorterminal.com/compare/langfuse-vs-wandb-weave.md)\n- [Arize Phoenix vs Plurai Simulation](https://www.anchorterminal.com/compare/arize-phoenix-vs-plurai-simulation.md)\n- [Baserun vs Plurai Simulation](https://www.anchorterminal.com/compare/baserun-vs-plurai-simulation.md)\n- [BotGauge vs Plurai Simulation](https://www.anchorterminal.com/compare/botgauge-vs-plurai-simulation.md)\n- [Braintrust API + MCP vs Plurai Simulation](https://www.anchorterminal.com/compare/braintrust-vs-plurai-simulation.md)\n- [DeepEval vs Langfuse API + MCP](https://www.anchorterminal.com/compare/deepeval-vs-langfuse.md)\n- [DeepEval vs Plurai Simulation](https://www.anchorterminal.com/compare/deepeval-vs-plurai-simulation.md)\n- [Galileo API + MCP vs Plurai Simulation](https://www.anchorterminal.com/compare/galileo-vs-plurai-simulation.md)\n- [Gauge CLI vs Langfuse API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-langfuse.md)\n- [Gauge CLI vs Plurai Simulation](https://www.anchorterminal.com/compare/gauge-cli-vs-plurai-simulation.md)\n- [Helicone AI Gateway + MCP vs Plurai Simulation](https://www.anchorterminal.com/compare/helicone-vs-plurai-simulation.md)\n- [HoneyHive vs Plurai Simulation](https://www.anchorterminal.com/compare/honeyhive-vs-plurai-simulation.md)\n- [Hue vs Plurai Simulation](https://www.anchorterminal.com/compare/hue-vs-plurai-simulation.md)\n- [Laminar API + MCP vs Plurai Simulation](https://www.anchorterminal.com/compare/laminar-vs-plurai-simulation.md)\n- [LangSmith API + MCP vs Plurai Simulation](https://www.anchorterminal.com/compare/langsmith-vs-plurai-simulation.md)\n- [LangWatch vs Plurai Simulation](https://www.anchorterminal.com/compare/langwatch-vs-plurai-simulation.md)\n- [MLflow Tracing vs Plurai Simulation](https://www.anchorterminal.com/compare/mlflow-tracing-vs-plurai-simulation.md)\n- [Opik API + MCP vs Plurai Simulation](https://www.anchorterminal.com/compare/opik-vs-plurai-simulation.md)\n- [Overmind vs Plurai Simulation](https://www.anchorterminal.com/compare/overmind-vs-plurai-simulation.md)\n- [Plurai Simulation vs Prefactor](https://www.anchorterminal.com/compare/plurai-simulation-vs-prefactor.md)\n- [Plurai Simulation vs Pydantic Logfire](https://www.anchorterminal.com/compare/plurai-simulation-vs-pydantic-logfire.md)\n- [Plurai Simulation vs Respan API + MCP](https://www.anchorterminal.com/compare/plurai-simulation-vs-respan.md)\n- [Plurai Simulation vs W\u0026B Weave](https://www.anchorterminal.com/compare/plurai-simulation-vs-wandb-weave.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Langfuse API + MCP vs Plurai Simulation",
        "url": ""
      }
    ],
    "description": "Langfuse scores 74.3 (BB) to Plurai Simulation's 52.6 (D) for evaluations. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Langfuse API + MCP BB 74.3",
      "Plurai Simulation D 52.6",
      "scores"
    ],
    "h1": "Langfuse API + MCP vs Plurai Simulation",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/langfuse-vs-plurai-simulation",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Langfuse vs Plurai Simulation for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/langfuse-vs-plurai-simulation"
  },
  "tokens": {
    "markdown": 5550,
    "slim": 1130
  },
  "version": 1
}
