{ "data": { "a": { "slug": "helicone", "name": "Helicone AI Gateway + MCP", "vendor": "Helicone (Mintlify)", "vendorUrl": "https://www.helicone.ai", "kind": "http-api", "category": "agent-observability", "summary": "Open-source LLM observability that logs requests through an OpenAI-compatible gateway (100+ models, fallbacks, caching, rate limits) or async logging.", "url": "https://www.anchorterminal.com/tools/helicone", "markdownUrl": "https://www.anchorterminal.com/tools/helicone.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/helicone.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/helicone.json", "repo": "https://github.com/Helicone/helicone", "license": "Apache-2.0", "transports": [ "http", "stdio" ], "remoteUrl": "https://ai-gateway.helicone.ai", "packages": [ { "registry": "npm", "name": "@helicone/helpers" }, { "registry": "pypi", "name": "helicone-helpers" }, { "registry": "npm", "name": "@helicone/mcp" } ], "auth": "api-key", "authNotes": "Helicone API key (`sk-helicone-...`) as a Bearer token on the gateway and REST API. Bring your own provider keys, or bill model usage to Helicone credits, which since 25 August 2026 only works for organisations Helicone has switched on (others get a 403 asking them to contact support). The MCP server reads `HELICONE_API_KEY` from the environment.", "pricing": "freemium", "pricingNotes": "Hobby free with 10,000 requests a month, 1 GB of storage, 1 seat and 7 days of retention, no card. Pro $79 a month and Team $799 a month, each with 10,000 requests and 1 GB free then usage-based charges the pricing page doesn't itemise. The pricing page still shows 7-day trials, but a commit on 30 August 2026 removed the in-app self-serve upgrade paths and sends upgrades to a contact page. Enterprise custom. Gateway credits pass model prices through at 0% markup, but since 25 August 2026 need Helicone to enable them per organisation. Self-hosted is free under Apache-2.0 with Docker Compose or Helm, you run ClickHouse, Postgres and object storage (https://www.helicone.ai/pricing).", "priceSummary": "$79 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402 support in docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": 3, "popularity": { "githubStars": 6190, "npmWeekly": 4328, "pypiWeekly": 4210, "asOf": "2026-09-30" }, "docsUrl": "https://docs.helicone.ai", "llmsTxt": "https://docs.helicone.ai/llms.txt", "openapi": "https://docs.helicone.ai/ai-gateway.openapi.json", "capabilities": [ "obs.traces", "obs.gateway", "obs.prompts", "obs.datasets", "obs.evals" ], "tags": [ "hosted", "freemium", "no-card", "open-source", "self-hosted", "mcp", "llms-txt", "openapi", "typescript", "python", "webhooks" ], "lastRelease": "2026-09-16", "graded": true, "anchor": { "graded": true, "score": 46.9, "grade": "D", "agentReady": false, "rank": 840, "ranked": true, "rankOf": 950, "categoryRank": 15, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 66, "payments": 30, "reliability": 50, "schema": 69, "security": 50, "transparency": 69 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -10, "negativeNotes": [ "2026-08-30. Helicone's own security commit (INC-657) fixed an authenticated cross-tenant read of other organisations' decrypted provider keys, a route that let any account mint proxy keys spending another organisation's provider key, a shared client that reused one organisation's OpenRouter key for others, an unauthenticated SSRF path and unauthenticated Stripe routes. Fixed, but disclosed only in the commit message, with no advisory or key-rotation notice that we found. -7 after decay for the fix (https://github.com/Helicone/helicone/commit/ca34549ea56f7ed587843f82d9cc19baa1f36ba4)", "2026-09-16. A second fix closed a platform-admin takeover with a forged API key and a cross-tenant read through HQL, reported through Helicone's disclosure programme the same day. Fixed within hours and again disclosed only in the commit. -3 (https://github.com/Helicone/helicone/commit/067d9290acb4f1fc9320e902fc67b4b399b50363)" ], "verdict": "One base-URL change gives logging, caching, fallbacks and rate limits for 100+ models. Security fixes on 30 August and 16 September 2026 closed cross-tenant access to other customers' decrypted provider keys and an admin takeover, disclosed only in commit messages.", "bestFor": "A team that wants request logging and cost tracking through a gateway with almost no code, and could swap it out later.", "strengths": [ "One base-URL change gives logging, caching, fallbacks and rate limits for 100+ models", "Apache-2.0 with Docker Compose and Helm self-hosting", "Per-plan ingestion and API rate limits published on the pricing page", "OpenAPI for the gateway, a Swagger file for the REST API and an llms.txt", "Free Hobby plan with 10,000 requests a month and no card" ], "weaknesses": [ "Security fixes on 30 August and 16 September 2026 closed cross-tenant access to other customers' decrypted provider keys and an admin takeover, disclosed only in commit messages", "Maintenance mode since March 2026, changelog silent since 26 November 2025, and Experiments, Realtime and self-serve upgrades removed on 30 August 2026", "The status page has no incident history, leaves out the AI Gateway and doesn't mention the four-day outage of 14 to 18 May 2026", "Helicone credits need a per-organisation switch since 25 August 2026, so new accounts must bring their own provider keys", "Privacy policy last updated in February 2023, with no retention period or DPA" ], "agentNotes": [ "Bring your own provider keys. Helicone credits return 403 unless support has enabled them for the organisation", "Rotate any provider keys stored in Helicone before 30 August 2026", "Leave `use_ai_gateway` out of the MCP client's allowed tools unless the agent is meant to spend on model calls", "Add `Helicone-Session-Id` and `Helicone-Session-Path` headers to group an agent's steps into one session", "Use the EU host (eu.helicone.ai) if the account was created there" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 2, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 46.9 } ], "editorialScores": { "ergonomics": 70, "maintenance": 66, "payments": 30, "reliability": 50, "schema": 69, "security": 50, "transparency": 60 }, "provenanceScore": 77 }, "connect": { "http": "curl https://ai-gateway.helicone.ai/chat/completions -H \"Authorization: Bearer $HELICONE_API_KEY\" \\\n -H \"content-type: application/json\" -d '{\"model\":\"gpt-4o-mini\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'", "claudeCode": "claude mcp add helicone -e HELICONE_API_KEY=$HELICONE_API_KEY -- npx -y @helicone/mcp@latest", "config": { "mcpServers": { "helicone": { "args": [ "-y", "@helicone/mcp@latest" ], "command": "npx", "env": { "HELICONE_API_KEY": "${HELICONE_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/obs.traces", "tool": "https://letme.dev/helicone" }, "area": "developer", "unitPrices": [ { "item": "Pro plan", "unit": "month", "usd": 79, "note": "10,000 requests and 1 GB free, then usage-based" }, { "item": "Team plan", "unit": "month", "usd": 799, "note": "5 organisations, SOC 2 and HIPAA, 10,000 requests and 1 GB free, then usage-based" } ], "provenance": { "legalEntity": "Helicone, Inc.", "domain": "helicone.ai", "domainRegistered": "2022-11-14", "endpointOnVendorDomain": true, "terms": "https://www.helicone.ai/terms", "privacy": "https://www.helicone.ai/privacy", "statusPage": "https://status.helicone.ai", "changelog": "https://www.helicone.ai/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms still name Helicone, Inc. and were last updated 2024-09-17, before the Mintlify acquisition" ], "score": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/helicone.json", "live": { "slug": "helicone", "probe": { "target": "https://ai-gateway.helicone.ai", "method": "get", "lastAt": "2026-10-10T02:54:57.472616221Z", "lastOk": true, "lastStatus": 405, "lastMs": 43, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 56, "p95ms24h": 151, "samples24h": 249, "samples30d": 2466, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 30, "ok": 30 } ] }, "vendorStatus": { "page": "https://status.helicone.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-10T00:50:40.216393148Z" }, "versions": [ { "registry": "github", "name": "Helicone/helicone", "version": "v2025.08.21-1", "released": "2025-08-21", "seenAt": "2026-10-09T16:57:37.795245737Z" }, { "registry": "npm", "name": "@helicone/helpers", "version": "1.8.3", "seenAt": "2026-10-09T16:57:34.366946009Z" }, { "registry": "npm", "name": "@helicone/mcp", "version": "0.1.6", "seenAt": "2026-10-09T16:57:36.669422247Z" }, { "registry": "pypi", "name": "helicone-helpers", "version": "1.2.1", "released": "2025-11-08", "seenAt": "2026-10-09T16:57:36.467136335Z" } ], "githubStars": 6210, "npmWeekly": 2989, "pypiWeekly": 5469, "securityTxt": { "url": "https://helicone.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-09T15:40:31.302356219Z" }, "llmsTxt": { "url": "https://docs.helicone.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:02:07.179582683Z" }, "domain": { "domain": "helicone.ai", "registered": "2022-11-14", "source": "https://rdap.identitydigital.services/rdap/domain/helicone.ai", "checkedAt": "2026-10-04T13:08:06.915944951Z" }, "pages": [ { "url": "https://www.helicone.ai/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:50:50.419310263Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1af05c56483a" }, { "url": "https://www.helicone.ai/blog/joining-mintlify", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-09T18:50:48.179958129Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a82c441b1103" }, { "url": "https://www.helicone.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-09T18:50:52.488347863Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4b1e79419d28" }, { "url": "https://www.helicone.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:50:54.51228366Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "47e9ad5d395a" }, { "url": "https://www.helicone.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:50:56.556023308Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "adbbffec4ecd" } ], "updatedAt": "2026-10-10T02:54:57.472616221Z" } }, "answer": "MLflow Tracing scores 61.2 (C) on agent readiness against Helicone AI Gateway + MCP's 46.9 (D), and leads in 5 of 7 scored categories. Helicone AI Gateway + MCP leads on security \u0026 auth and transparency \u0026 trust.", "b": { "slug": "mlflow-tracing", "name": "MLflow Tracing", "vendor": "MLflow Project (LF Projects, LLC)", "vendorUrl": "https://mlflow.org", "kind": "http-api", "category": "agent-observability", "summary": "Open-source tracing, evaluation and prompt management for LLM applications and agents, part of MLflow, a Linux Foundation project. Owners run the server themselves, and agents read and annotate traces through an experimental MCP server or the `mlflow traces` CLI.", "url": "https://www.anchorterminal.com/tools/mlflow-tracing", "markdownUrl": "https://www.anchorterminal.com/tools/mlflow-tracing.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/mlflow-tracing.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/mlflow-tracing.json", "repo": "https://github.com/mlflow/mlflow", "license": "Apache-2.0", "transports": [ "stdio", "http" ], "packages": [ { "registry": "pypi", "name": "mlflow" }, { "registry": "pypi", "name": "mlflow-tracing" }, { "registry": "npm", "name": "@mlflow/core" } ], "auth": "mixed", "authNotes": "No authentication on a default server. Starting it with `mlflow server --app-name basic-auth` requires a username and password on every request, with role-based access control and no default admin password. The MCP server is a local stdio process that reads `MLFLOW_TRACKING_URI` and the MLflow credential environment variables, such as `MLFLOW_TRACKING_USERNAME` and `MLFLOW_TRACKING_PASSWORD`. Single sign-on needs a community plugin or a reverse proxy.", "pricing": "free", "pricingNotes": "Free to self-host under Apache-2.0, with no account or contract. The owner pays for compute, a database and artifact storage. The MLflow project sells nothing. Its README links managed MLflow from Databricks, Amazon SageMaker, Azure ML and Nebius, whose prices were not read (checked 2026-10-09).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository docs or the MCP server source (checked 2026-10-09).", "endpoints": [] }, "toolCount": 26, "popularity": { "githubStars": 28320, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://mlflow.org/docs/latest/genai/", "llmsTxt": "https://mlflow.org/docs/latest/llms.txt", "capabilities": [ "obs.traces", "obs.evals", "obs.prompts", "obs.datasets", "obs.gateway" ], "tags": [ "open-source", "self-hosted", "local", "apache-2.0", "mcp", "cli", "opentelemetry", "llms-txt", "python", "typescript", "linux-foundation" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 61.2, "grade": "C", "agentReady": false, "rank": 476, "ranked": true, "rankOf": 950, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 88, "payments": 60, "reliability": 76, "schema": 78, "security": 40, "transparency": 62 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": -6, "negativeNotes": [ "2026-10-09: GHSA-26p8-2jq9-3vq9, critical, remote code execution on MLflow servers without authentication through third-party scorer deserialisation, affecting 3.12.0rc0 up to 3.17.0 and patched in 3.17.0 of 6 October. Four more advisories were published between 27 July and 4 August 2026, among them GHSA-7gwp-5pfp-969j, a high-severity unauthenticated SSRF in webhook delivery patched in 3.15.0. All are published with fixes, so the deduction is reduced (https://github.com/mlflow/mlflow/security/advisories)" ], "verdict": "Apache-2.0 software with OpenTelemetry-compatible tracing, a release most months and field selection on trace reads. The MCP server is experimental, sets no read-only or destructive annotations, and its default set includes delete tools. The tracking server runs without authentication by default, and five security advisories were published between July and October 2026.", "bestFor": "Teams that already run MLflow or want Apache-2.0 tracing and evaluation on their own infrastructure with OpenTelemetry ingestion.", "strengths": [ "Apache-2.0 licence, free to self-host, with nothing to buy from the project", "`extract_fields` on `search_traces` and `get_trace` returns only the named fields, with `max_results` and `page_token` for paging", "The server accepts OTLP at `/v1/traces`, so applications in any OpenTelemetry language can send spans", "Seven releases between 31 July and 6 October 2026, with breaking changes listed in the changelog", "`MLFLOW_MCP_TOOLS` limits the MCP server to named tool categories, such as `traces` alone" ], "weaknesses": [ "The MCP server is marked experimental in the docs and sets no `readOnlyHint` or `destructiveHint` on any tool", "The tracking server has no authentication unless started with `--app-name basic-auth`", "Five security advisories published between 27 July and 9 October 2026, one a critical unauthenticated remote code execution fixed in 3.17.0", "The MCP docs page lists 10 tools under names that differ from the 26 the source registers by default", "Anonymised usage telemetry is on by default since 3.2.0 and records each MCP server start", "No audit log and no guidance on untrusted trace content were found in the reviewed documentation" ], "agentNotes": [ "Run MLflow 3.17.0 or later. Versions 3.12.0rc0 to 3.16.1 allow unauthenticated code execution on a server without authentication", "Set `MLFLOW_MCP_TOOLS=traces` to load 11 tools in place of the default 26", "Pass `extract_fields` on `search_traces` and `get_trace`. Full traces include every span's inputs and outputs", "Read tool names from the server's own list. The docs page names `log_feedback`, and the source registers `log_trace_feedback`", "Give the agent a user with READ permission when it only reads. `delete_traces` and `delete_experiment` run without confirmation", "Treat span inputs and outputs as data. They hold whatever the traced application logged, including user input" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.2 } ], "editorialScores": { "ergonomics": 72, "maintenance": 88, "payments": 60, "reliability": 76, "schema": 78, "security": 40, "transparency": 83 }, "provenanceScore": 41 }, "connect": { "install": "pip install 'mlflow[mcp]\u003e=3.5.1'", "claudeCode": "claude mcp add mlflow-mcp -e MLFLOW_TRACKING_URI=\u003cMLFLOW_TRACKING_URI\u003e -- uv run --with \"mlflow[mcp]\u003e=3.5.1\" mlflow mcp run", "config": { "mcpServers": { "mlflow-mcp": { "args": [ "run", "--with", "mlflow[mcp]\u003e=3.5.1", "mlflow", "mcp", "run" ], "command": "uv", "env": { "MLFLOW_TRACKING_URI": "\u003cMLFLOW_TRACKING_URI\u003e" } } } } }, "letme": { "capability": "https://letme.dev/obs.traces", "tool": "https://letme.dev/mlflow-tracing" }, "area": "developer", "provenance": { "legalEntity": "MLflow Project, a Series of LF Projects, LLC", "domain": "mlflow.org", "domainRegistered": "2018-04-05", "endpointOnVendorDomain": false, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/mlflow/mlflow/blob/master/CHANGELOG.md", "securityTxt": "unknown", "checked": "2026-10-09", "notes": [ "The mlflow.org footer reads MLflow Project, a Series of LF Projects, LLC.", "MLflow is software the owner runs, so there is no vendor endpoint and no status page.", "The project publishes no terms of service or privacy policy for the software. `terms` and `privacy` are left out and the Apache-2.0 licence stands in. The telemetry page refers to the LF Projects telemetry data policy.", "mlflow.org/.well-known/security.txt answered 403 from the site's storage. SECURITY.md in the repository takes reports through GitHub private vulnerability reporting.", "RDAP for mlflow.org gives a registration date of 2018-04-05 and 1API GmbH as registrar." ], "score": 41 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/mlflow-tracing.json", "live": { "slug": "mlflow-tracing", "versions": [ { "registry": "github", "name": "mlflow/mlflow", "version": "v3.17.0", "released": "2026-10-07", "seenAt": "2026-10-09T17:06:56.716473096Z" }, { "registry": "npm", "name": "@mlflow/core", "version": "0.4.0", "seenAt": "2026-10-09T17:06:55.82052791Z" }, { "registry": "pypi", "name": "mlflow", "version": "3.17.0", "released": "2026-10-07", "seenAt": "2026-10-09T17:06:53.813494162Z" }, { "registry": "pypi", "name": "mlflow-tracing", "version": "3.17.0", "released": "2026-10-07", "seenAt": "2026-10-09T17:06:53.928988136Z" } ], "githubStars": 28331, "npmWeekly": 15392, "pypiWeekly": 4590348, "pages": [ { "url": "https://raw.githubusercontent.com/mlflow/mlflow/master/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:45:35.157905643Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "81678c02de88" } ], "updatedAt": "2026-10-09T18:45:35.157905643Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Helicone (Mintlify)", "b": "MLflow Project (LF Projects, LLC)", "name": "Vendor" }, { "a": "https://ai-gateway.helicone.ai", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "stdio, HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache-2.0", "name": "Licence" }, { "a": "3", "b": "26", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-16", "b": "2026-10-06", "name": "Last release" }, { "a": "2024-09-17", "b": "no document linked", "name": "Terms last updated" }, { "a": "2023-02-28", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "", "name": "Customer content may train models" }, { "a": "yes", "b": "", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "6.2k stars, 4.3k npm/wk, 4.2k PyPI/wk", "b": "28k stars", "name": "Popularity" }, { "a": "2/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "MLflow Tracing scores 61.2 (C) on agent readiness against Helicone AI Gateway + MCP's 46.9 (D), and leads in 5 of 7 scored categories. Helicone AI Gateway + MCP leads on security \u0026 auth and transparency \u0026 trust.", "question": "Which is better for AI agents, Helicone AI Gateway + MCP or MLflow Tracing?" }, { "answer": "Helicone AI Gateway + MCP needs an API key. MLflow Tracing takes an API key or an OAuth sign-in.", "question": "Do Helicone AI Gateway + MCP and MLflow Tracing need an API key?" }, { "answer": "Helicone AI Gateway + MCP has a hosted endpoint at https://ai-gateway.helicone.ai. MLflow Tracing runs on your own machine, with no hosted endpoint listed.", "question": "Can an agent call Helicone AI Gateway + MCP and MLflow Tracing without installing anything?" }, { "answer": "Yes. Helicone AI Gateway + MCP is open source (Apache-2.0). MLflow Tracing is open source (Apache-2.0).", "question": "Are Helicone AI Gateway + MCP and MLflow Tracing open source?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 50 against 40", "Transparency \u0026 trust, 69 against 62" ], "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "A team that wants request logging and cost tracking through a gateway with almost no code, and could swap it out later.", "slug": "helicone", "watchFor": "Security fixes on 30 August and 16 September 2026 closed cross-tenant access to other customers' decrypted provider keys and an admin takeover, disclosed only in commit messages" }, { "aheadOn": [ "Reliability, 76 against 50", "Schema \u0026 documentation, 78 against 69", "Payments \u0026 pricing, 60 against 30", "Maintenance \u0026 community, 88 against 66" ], "also": null, "goodFor": "Teams that already run MLflow or want Apache-2.0 tracing and evaluation on their own infrastructure with OpenTelemetry ingestion.", "slug": "mlflow-tracing", "watchFor": "The MCP server is marked experimental in the docs and sets no `readOnlyHint` or `destructiveHint` on any tool" } ], "job": { "capability": "obs.traces", "name": "Agent tracing" }, "others": [ { "json": "https://www.anchorterminal.com/compare/arize-phoenix-vs-helicone.json", "title": "Arize Phoenix vs Helicone AI Gateway + MCP", "url": "https://www.anchorterminal.com/compare/arize-phoenix-vs-helicone" }, { "json": "https://www.anchorterminal.com/compare/arize-phoenix-vs-mlflow-tracing.json", "title": "Arize Phoenix vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/arize-phoenix-vs-mlflow-tracing" }, { "json": "https://www.anchorterminal.com/compare/baserun-vs-helicone.json", "title": "Baserun vs Helicone AI Gateway + MCP", "url": "https://www.anchorterminal.com/compare/baserun-vs-helicone" }, { "json": "https://www.anchorterminal.com/compare/baserun-vs-mlflow-tracing.json", "title": "Baserun vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/baserun-vs-mlflow-tracing" }, { "json": "https://www.anchorterminal.com/compare/braintrust-vs-helicone.json", "title": "Braintrust API + MCP vs Helicone AI Gateway + MCP", "url": "https://www.anchorterminal.com/compare/braintrust-vs-helicone" }, { "json": "https://www.anchorterminal.com/compare/braintrust-vs-mlflow-tracing.json", "title": "Braintrust API + MCP vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/braintrust-vs-mlflow-tracing" }, { "json": "https://www.anchorterminal.com/compare/galileo-vs-helicone.json", "title": "Galileo API + MCP vs Helicone AI Gateway + MCP", "url": "https://www.anchorterminal.com/compare/galileo-vs-helicone" }, { "json": "https://www.anchorterminal.com/compare/galileo-vs-mlflow-tracing.json", "title": "Galileo API + MCP vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/galileo-vs-mlflow-tracing" }, { "json": "https://www.anchorterminal.com/compare/helicone-vs-honeyhive.json", "title": "Helicone AI Gateway + MCP vs HoneyHive", "url": "https://www.anchorterminal.com/compare/helicone-vs-honeyhive" }, { "json": "https://www.anchorterminal.com/compare/helicone-vs-laminar.json", "title": "Helicone AI Gateway + MCP vs Laminar API + MCP", "url": "https://www.anchorterminal.com/compare/helicone-vs-laminar" }, { "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/helicone-vs-langsmith.json", "title": "Helicone AI Gateway + MCP vs LangSmith API + MCP", "url": "https://www.anchorterminal.com/compare/helicone-vs-langsmith" }, { "json": "https://www.anchorterminal.com/compare/helicone-vs-langwatch.json", "title": "Helicone AI Gateway + MCP vs LangWatch", "url": "https://www.anchorterminal.com/compare/helicone-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/helicone-vs-prefactor.json", "title": "Helicone AI Gateway + MCP vs Prefactor", "url": "https://www.anchorterminal.com/compare/helicone-vs-prefactor" }, { "json": "https://www.anchorterminal.com/compare/helicone-vs-pydantic-logfire.json", "title": "Helicone AI Gateway + MCP vs Pydantic Logfire", "url": "https://www.anchorterminal.com/compare/helicone-vs-pydantic-logfire" }, { "json": "https://www.anchorterminal.com/compare/helicone-vs-respan.json", "title": "Helicone AI Gateway + MCP vs Respan API + MCP", "url": "https://www.anchorterminal.com/compare/helicone-vs-respan" }, { "json": "https://www.anchorterminal.com/compare/helicone-vs-wandb-weave.json", "title": "Helicone AI Gateway + MCP vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/helicone-vs-wandb-weave" }, { "json": "https://www.anchorterminal.com/compare/honeyhive-vs-mlflow-tracing.json", "title": "HoneyHive vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/honeyhive-vs-mlflow-tracing" }, { "json": "https://www.anchorterminal.com/compare/laminar-vs-mlflow-tracing.json", "title": "Laminar API + MCP vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/laminar-vs-mlflow-tracing" }, { "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/langsmith-vs-mlflow-tracing.json", "title": "LangSmith API + MCP vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/langsmith-vs-mlflow-tracing" }, { "json": "https://www.anchorterminal.com/compare/langwatch-vs-mlflow-tracing.json", "title": "LangWatch vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/langwatch-vs-mlflow-tracing" }, { "json": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-prefactor.json", "title": "MLflow Tracing vs Prefactor", "url": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-prefactor" }, { "json": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-pydantic-logfire.json", "title": "MLflow Tracing vs Pydantic Logfire", "url": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-pydantic-logfire" }, { "json": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-respan.json", "title": "MLflow Tracing vs Respan API + MCP", "url": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-respan" }, { "json": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-wandb-weave.json", "title": "MLflow Tracing vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/mlflow-tracing-vs-wandb-weave" }, { "json": "https://www.anchorterminal.com/compare/deepeval-vs-helicone.json", "title": "DeepEval vs Helicone AI Gateway + MCP", "url": "https://www.anchorterminal.com/compare/deepeval-vs-helicone" }, { "json": "https://www.anchorterminal.com/compare/deepeval-vs-mlflow-tracing.json", "title": "DeepEval vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/deepeval-vs-mlflow-tracing" } ], "scores": [ { "by": 26, "edge": "mlflow-tracing", "helicone": 50, "key": "reliability", "mlflow-tracing": 76, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 9, "edge": "mlflow-tracing", "helicone": 69, "key": "schema", "mlflow-tracing": 78, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 2, "edge": "mlflow-tracing", "helicone": 70, "key": "ergonomics", "mlflow-tracing": 72, "name": "Agent ergonomics", "weight": 13 }, { "by": 10, "edge": "helicone", "helicone": 50, "key": "security", "mlflow-tracing": 40, "name": "Security \u0026 auth", "weight": 14 }, { "by": 30, "edge": "mlflow-tracing", "helicone": 30, "key": "payments", "mlflow-tracing": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 22, "edge": "mlflow-tracing", "helicone": 66, "key": "maintenance", "mlflow-tracing": 88, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 7, "edge": "helicone", "helicone": 69, "key": "transparency", "mlflow-tracing": 62, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "MLflow Tracing scores 61.2 (C) on agent readiness against Helicone AI Gateway + MCP's 46.9 (D), and leads in 5 of 7 scored categories. Helicone AI Gateway + MCP leads on security \u0026 auth and transparency \u0026 trust. Both do agent tracing.", "verdicts": { "helicone": "One base-URL change gives logging, caching, fallbacks and rate limits for 100+ models. Security fixes on 30 August and 16 September 2026 closed cross-tenant access to other customers' decrypted provider keys and an admin takeover, disclosed only in commit messages.", "mlflow-tracing": "Apache-2.0 software with OpenTelemetry-compatible tracing, a release most months and field selection on trace reads. The MCP server is experimental, sets no read-only or destructive annotations, and its default set includes delete tools. The tracking server runs without authentication by default, and five security advisories were published between July and October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/helicone-vs-mlflow-tracing", "json": "https://www.anchorterminal.com/compare/helicone-vs-mlflow-tracing.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/helicone-vs-mlflow-tracing.md", "slim": "https://www.anchorterminal.com/compare/helicone-vs-mlflow-tracing.min.md" }, "markdown": "MLflow Tracing scores 61.2 (C) on agent readiness against Helicone AI Gateway + MCP's 46.9 (D), and leads in 5 of 7 scored categories. Helicone AI Gateway + MCP leads on security \u0026 auth and transparency \u0026 trust. Both do agent tracing.\n\n- Helicone AI Gateway + MCP: grade D, 46.9/100, rank #840 of 950. Markdown https://www.anchorterminal.com/tools/helicone.md · JSON https://www.anchorterminal.com/api/v1/tools/helicone.json\n- MLflow Tracing: grade C, 61.2/100, rank #476 of 950. Markdown https://www.anchorterminal.com/tools/mlflow-tracing.md · JSON https://www.anchorterminal.com/api/v1/tools/mlflow-tracing.json\n- Best agent tracing, monitoring and evaluation tools: https://www.anchorterminal.com/best/agent-observability/index.md\n- All 120 evals comparisons: https://www.anchorterminal.com/compare/agent-observability/index.md\n\n## Which one, for what\n\n### Helicone AI Gateway + MCP (D)\n\nGood for: A team that wants request logging and cost tracking through a gateway with almost no code, and could swap it out later.\n\nAhead on:\n- Security \u0026 auth, 50 against 40\n- Transparency \u0026 trust, 69 against 62\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: Security fixes on 30 August and 16 September 2026 closed cross-tenant access to other customers' decrypted provider keys and an admin takeover, disclosed only in commit messages\n\n### MLflow Tracing (C)\n\nGood for: Teams that already run MLflow or want Apache-2.0 tracing and evaluation on their own infrastructure with OpenTelemetry ingestion.\n\nAhead on:\n- Reliability, 76 against 50\n- Schema \u0026 documentation, 78 against 69\n- Payments \u0026 pricing, 60 against 30\n- Maintenance \u0026 community, 88 against 66\n\nWatch for: The MCP server is marked experimental in the docs and sets no `readOnlyHint` or `destructiveHint` on any tool\n\n\n## Score by category\n\n| Category | Weight | Helicone AI Gateway + MCP | MLflow Tracing | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 50 | 76 | MLflow Tracing +26 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 69 | 78 | MLflow Tracing +9 |\n| Agent ergonomics | 13% (16.2 this run) | 70 | 72 | MLflow Tracing +2 |\n| Security \u0026 auth | 14% (17.5 this run) | 50 | 40 | Helicone AI Gateway + MCP +10 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 60 | MLflow Tracing +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 66 | 88 | MLflow Tracing +22 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 69 | 62 | Helicone AI Gateway + MCP +7 |\n| Negative events | ≤15 | -10 | -6 | |\n| **Total** | | **46.9 · D** | **61.2 · C** | |\n\n## Facts side by side\n\n| Fact | Helicone AI Gateway + MCP | MLflow Tracing |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Helicone (Mintlify) | MLflow Project (LF Projects, LLC) |\n| Hosted endpoint | `https://ai-gateway.helicone.ai` | no (local only) |\n| Transports | HTTP, stdio | stdio, HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 |\n| Tools exposed | 3 | 26 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-16 | 2026-10-06 |\n| Terms last updated | 2024-09-17 | no document linked |\n| Privacy policy last updated | 2023-02-28 | no document linked |\n| Customer content may train models | not found in the text | |\n| Terms restrict automated access | yes | |\n| Terms restrict benchmarking | not found in the text | |\n| Terms or service can change without notice | yes | |\n| Arbitration or class-action waiver | not found in the text | |\n| Popularity | 6.2k stars, 4.3k npm/wk, 4.2k PyPI/wk | 28k stars |\n| Agent reviews | 2/5 (2) | none |\n\n## Verdicts\n\n**Helicone AI Gateway + MCP.** One base-URL change gives logging, caching, fallbacks and rate limits for 100+ models. Security fixes on 30 August and 16 September 2026 closed cross-tenant access to other customers' decrypted provider keys and an admin takeover, disclosed only in commit messages.\n\n**MLflow Tracing.** Apache-2.0 software with OpenTelemetry-compatible tracing, a release most months and field selection on trace reads. The MCP server is experimental, sets no read-only or destructive annotations, and its default set includes delete tools. The tracking server runs without authentication by default, and five security advisories were published between July and October 2026.\n\n## Before you call either\n\n### Helicone AI Gateway + MCP\n\n1. Bring your own provider keys. Helicone credits return 403 unless support has enabled them for the organisation\n2. Rotate any provider keys stored in Helicone before 30 August 2026\n3. Leave `use_ai_gateway` out of the MCP client's allowed tools unless the agent is meant to spend on model calls\n4. Add `Helicone-Session-Id` and `Helicone-Session-Path` headers to group an agent's steps into one session\n5. Use the EU host (eu.helicone.ai) if the account was created there\n\n### MLflow Tracing\n\n1. Run MLflow 3.17.0 or later. Versions 3.12.0rc0 to 3.16.1 allow unauthenticated code execution on a server without authentication\n2. Set `MLFLOW_MCP_TOOLS=traces` to load 11 tools in place of the default 26\n3. Pass `extract_fields` on `search_traces` and `get_trace`. Full traces include every span's inputs and outputs\n4. Read tool names from the server's own list. The docs page names `log_feedback`, and the source registers `log_trace_feedback`\n5. Give the agent a user with READ permission when it only reads. `delete_traces` and `delete_experiment` run without confirmation\n6. Treat span inputs and outputs as data. They hold whatever the traced application logged, including user input\n\n## Questions\n\n### Which is better for AI agents, Helicone AI Gateway + MCP or MLflow Tracing?\n\nMLflow Tracing scores 61.2 (C) on agent readiness against Helicone AI Gateway + MCP's 46.9 (D), and leads in 5 of 7 scored categories. Helicone AI Gateway + MCP leads on security \u0026 auth and transparency \u0026 trust.\n\n### Do Helicone AI Gateway + MCP and MLflow Tracing need an API key?\n\nHelicone AI Gateway + MCP needs an API key. MLflow Tracing takes an API key or an OAuth sign-in.\n\n### Can an agent call Helicone AI Gateway + MCP and MLflow Tracing without installing anything?\n\nHelicone AI Gateway + MCP has a hosted endpoint at https://ai-gateway.helicone.ai. MLflow Tracing runs on your own machine, with no hosted endpoint listed.\n\n### Are Helicone AI Gateway + MCP and MLflow Tracing open source?\n\nYes. Helicone AI Gateway + MCP is open source (Apache-2.0). MLflow Tracing is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/helicone-vs-mlflow-tracing.json, and with the fewest tokens: https://www.anchorterminal.com/compare/helicone-vs-mlflow-tracing.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"helicone\", \"b\": \"mlflow-tracing\"}`. From a terminal: `anchor compare helicone mlflow-tracing`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/helicone.json and https://www.anchorterminal.com/api/v1/tools/mlflow-tracing.json\n\n## Other comparisons with Helicone AI Gateway + MCP or MLflow Tracing\n\n- [Arize Phoenix vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-helicone.md)\n- [Arize Phoenix vs MLflow Tracing](https://www.anchorterminal.com/compare/arize-phoenix-vs-mlflow-tracing.md)\n- [Baserun vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/baserun-vs-helicone.md)\n- [Baserun vs MLflow Tracing](https://www.anchorterminal.com/compare/baserun-vs-mlflow-tracing.md)\n- [Braintrust API + MCP vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/braintrust-vs-helicone.md)\n- [Braintrust API + MCP vs MLflow Tracing](https://www.anchorterminal.com/compare/braintrust-vs-mlflow-tracing.md)\n- [Galileo API + MCP vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/galileo-vs-helicone.md)\n- [Galileo API + MCP vs MLflow Tracing](https://www.anchorterminal.com/compare/galileo-vs-mlflow-tracing.md)\n- [Helicone AI Gateway + MCP vs HoneyHive](https://www.anchorterminal.com/compare/helicone-vs-honeyhive.md)\n- [Helicone AI Gateway + MCP vs Laminar API + MCP](https://www.anchorterminal.com/compare/helicone-vs-laminar.md)\n- [Helicone AI Gateway + MCP vs Langfuse API + MCP](https://www.anchorterminal.com/compare/helicone-vs-langfuse.md)\n- [Helicone AI Gateway + MCP vs LangSmith API + MCP](https://www.anchorterminal.com/compare/helicone-vs-langsmith.md)\n- [Helicone AI Gateway + MCP vs LangWatch](https://www.anchorterminal.com/compare/helicone-vs-langwatch.md)\n- [Helicone AI Gateway + MCP vs Prefactor](https://www.anchorterminal.com/compare/helicone-vs-prefactor.md)\n- [Helicone AI Gateway + MCP vs Pydantic Logfire](https://www.anchorterminal.com/compare/helicone-vs-pydantic-logfire.md)\n- [Helicone AI Gateway + MCP vs Respan API + MCP](https://www.anchorterminal.com/compare/helicone-vs-respan.md)\n- [Helicone AI Gateway + MCP vs W\u0026B Weave](https://www.anchorterminal.com/compare/helicone-vs-wandb-weave.md)\n- [HoneyHive vs MLflow Tracing](https://www.anchorterminal.com/compare/honeyhive-vs-mlflow-tracing.md)\n- [Laminar API + MCP vs MLflow Tracing](https://www.anchorterminal.com/compare/laminar-vs-mlflow-tracing.md)\n- [Langfuse API + MCP vs MLflow Tracing](https://www.anchorterminal.com/compare/langfuse-vs-mlflow-tracing.md)\n- [LangSmith API + MCP vs MLflow Tracing](https://www.anchorterminal.com/compare/langsmith-vs-mlflow-tracing.md)\n- [LangWatch vs MLflow Tracing](https://www.anchorterminal.com/compare/langwatch-vs-mlflow-tracing.md)\n- [MLflow Tracing vs Prefactor](https://www.anchorterminal.com/compare/mlflow-tracing-vs-prefactor.md)\n- [MLflow Tracing vs Pydantic Logfire](https://www.anchorterminal.com/compare/mlflow-tracing-vs-pydantic-logfire.md)\n- [MLflow Tracing vs Respan API + MCP](https://www.anchorterminal.com/compare/mlflow-tracing-vs-respan.md)\n- [MLflow Tracing vs W\u0026B Weave](https://www.anchorterminal.com/compare/mlflow-tracing-vs-wandb-weave.md)\n- [DeepEval vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/deepeval-vs-helicone.md)\n- [DeepEval vs MLflow Tracing](https://www.anchorterminal.com/compare/deepeval-vs-mlflow-tracing.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Helicone AI Gateway + MCP vs MLflow Tracing", "url": "" } ], "description": "MLflow Tracing scores 61.2 (C) to Helicone AI Gateway's 46.9 (D) for agent tracing. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Helicone AI Gateway + MCP D 46.9", "MLflow Tracing C 61.2", "scores" ], "h1": "Helicone AI Gateway + MCP vs MLflow Tracing", "image": "https://www.anchorterminal.com/assets/og/compare-helicone-vs-mlflow-tracing.png", "path": "/compare/helicone-vs-mlflow-tracing", "published": "2026-10-01", "section": "tools", "title": "Helicone AI Gateway vs MLflow Tracing for AI agents (2026)", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/helicone-vs-mlflow-tracing" }, "tokens": { "markdown": 2750, "slim": 730 }, "version": 1 }