{ "data": { "a": { "slug": "harness-fme", "name": "Harness Feature Management \u0026 Experimentation", "vendor": "Harness Inc.", "vendorUrl": "https://www.harness.io", "kind": "http-api", "category": "product-analytics", "summary": "Harness Feature Management \u0026 Experimentation (FME), formerly Split, manages feature flags, targeting, metrics and experiments. Agents reach it through the Admin API at api.split.io and the FME toolset of the Harness MCP server.", "url": "https://www.anchorterminal.com/tools/harness-fme", "markdownUrl": "https://www.anchorterminal.com/tools/harness-fme.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/harness-fme.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/harness-fme.json", "dns": "harness-fme.grade.anchorterminal.com", "repo": "https://github.com/harness/mcp-server", "transports": [ "http", "stdio", "streamable-http" ], "remoteUrl": "https://mcp.harness.io/mcp", "packages": [ { "registry": "npm", "name": "harness-mcp-v2" } ], "auth": "mixed", "authNotes": "The Admin API takes an Admin API key as a Bearer token, or a Harness personal access token (PAT) or service account token (SAT) in `x-api-key`. Admin keys carry fixed roles that can be combined and cannot be edited after creation, and a key cannot create another with more roles. The local MCP server reads HARNESS_API_KEY. The hosted MCP endpoint uses Harness Platform OAuth and must be enabled per account by Harness Support.", "pricing": "freemium", "pricingNotes": "An FME Free Plan is enabled from inside a Harness account; its limits are not published. The Enterprise plan and FME pricing are by quotation through sales. No FME prices appear on harness.io/pricing.", "priceSummary": "Freemium", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the FME docs, the Split API reference or harness.io/pricing (checked 2026-11-06).", "endpoints": [] }, "toolCount": 11, "popularity": { "githubStars": null, "npmWeekly": 8800, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://developer.harness.io/feature-management-experimentation/feature-management-and-experimentation-documentation", "llmsTxt": "https://developer.harness.io/llms.txt", "capabilities": [ "analytics.flags", "analytics.experiments", "analytics.events" ], "tags": [ "official", "hosted", "mcp", "remote-mcp", "oauth", "llms-txt", "free-tier", "sales-led", "status-page", "soc2", "iso27001", "typescript", "python", "cli", "closed-source" ], "lastRelease": "2026-11-04", "graded": true, "anchor": { "graded": true, "score": 69.2, "grade": "B", "agentReady": false, "rank": 258, "ranked": true, "rankOf": 1510, "categoryRank": 4, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 83, "maintenance": 81, "payments": 15, "reliability": 80, "schema": 71, "security": 79, "transparency": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Harness FME, formerly Split, gives agents 11 consolidated MCP tools with an FME-only toolset, a read-only switch and confirmation on writes, over an Admin API with documented limits and role-scoped keys. FME prices are not published, the free plan's limits are unstated, and the hosted MCP endpoint must be enabled by Harness Support.", "bestFor": "Teams already on Harness, or Split customers, who want agents to inspect and change flags and segments with guard rails.", "strengths": [ "11 generic MCP tools with `--toolsets=fme`, readOnlyHint on reads and elicitation before writes", "HARNESS_READ_ONLY blocks every create, update, delete and execute call", "Admin API keys with fixed, combinable roles, plus Harness PATs and SATs", "Documented rate limit with remaining and reset headers, and automatic backoff in the MCP server", "SOC 2 Type II, ISO 27001 and FedRAMP 20x, with FME audit logs and MCP audit sinks" ], "weaknesses": [ "No FME prices are published; Enterprise is by quotation and free plan limits are unstated", "The hosted MCP endpoint must be enabled per account by Harness Support", "The FME MCP docs page still describes building a Go binary, unlike the current npm package", "About 20 Admin API requests per 10 seconds per organisation, which large lists can hit", "No public OpenAPI file for the Admin API was found" ], "agentNotes": [ "Start the MCP server with `--toolsets=fme` so only FME resource types load", "Call `harness_describe(resource_type='fme_feature_flag')` before a create or update to see the fields", "Filter fme_feature_flag lists by name, tags or rollout status rather than listing every flag", "Set HARNESS_READ_ONLY for analysis tasks; leave confirmation on for kill, restore and delete", "On 429, wait at least the larger X-RateLimit-Reset-Seconds value before retrying" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.2 } ], "editorialScores": { "ergonomics": 83, "maintenance": 81, "payments": 15, "reliability": 80, "schema": 71, "security": 79, "transparency": 60 }, "provenanceScore": 61, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npx harness-mcp-v2@latest", "config": { "mcpServers": { "harness": { "args": [ "harness-mcp-v2@latest", "--toolsets=fme" ], "command": "npx", "env": { "HARNESS_API_KEY": "pat.xxx" } } } } }, "letme": { "capability": "https://letme.dev/analytics.flags", "tool": "https://letme.dev/harness-fme" }, "area": "business", "provenance": { "legalEntity": "Harness Inc.", "domain": "harness.io", "domainRegistered": "", "endpointOnVendorDomain": false, "terms": "https://www.harness.io/legal/subscription-terms", "privacy": "https://www.harness.io/legal/privacy", "statusPage": "https://status.harness.io", "changelog": "https://github.com/harness/mcp-server/releases", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The Admin API is on api.split.io, the former Split domain, and the hosted MCP endpoint on mcp.harness.io.", "The privacy statement names Harness Inc. as controller and Harness France SAS as EU representative. Its header says last updated 23 October 2026 and its body says version of 14 October 2026.", "developer.harness.io/robots.txt allows all and carries Content-Signal ai-train=yes, search=yes, ai-input=yes. docs.split.io allows all but edit and login paths.", "www.harness.io/.well-known/security.txt answered with an invalid-request page. The security page gives security@harness.io and a private bug bounty on request.", "RDAP gave no registration date for harness.io." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/harness-fme.json", "live": { "slug": "harness-fme", "probe": { "target": "https://mcp.harness.io/mcp", "method": "get", "lastAt": "2026-11-07T19:22:10.85947707Z", "lastOk": true, "lastStatus": 401, "lastMs": 308, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 195, "p95ms24h": 285, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.harness.io", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:22:14.403533029Z" }, "versions": [ { "registry": "github", "name": "harness/mcp-server", "version": "v3.2.40", "released": "2026-11-05", "seenAt": "2026-11-06T23:32:13.419387707Z" }, { "registry": "npm", "name": "harness-mcp-v2", "version": "3.2.40", "seenAt": "2026-11-06T23:32:12.430886041Z" } ], "githubStars": 112, "npmWeekly": 8800, "securityTxt": { "url": "https://harness.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:19.957252225Z" }, "llmsTxt": { "url": "https://developer.harness.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:41.749004752Z" }, "pages": [ { "url": "https://www.harness.io/legal/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:29:30.551687912Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "b15935b42065" }, { "url": "https://www.harness.io/legal/subscription-terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:29:35.70684084Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "871b29e12dd4" } ], "updatedAt": "2026-11-07T19:22:10.85947707Z" } }, "answer": "Statsig scores 72.4 (BB) on agent readiness against Harness Feature Management \u0026 Experimentation's 69.2 (B), and leads in 3 of 7 scored categories. Harness Feature Management \u0026 Experimentation leads on agent ergonomics and security \u0026 auth.", "b": { "slug": "statsig", "name": "Statsig", "vendor": "Amplitude, Inc.", "vendorUrl": "https://www.statsig.com", "kind": "http-api", "category": "product-analytics", "summary": "Statsig is a hosted platform for feature flags, experiments and product analytics, run by Amplitude, Inc. since May 2026. Agents reach it through the Console API, which has a public OpenAPI spec, and an official hosted MCP server.", "url": "https://www.anchorterminal.com/tools/statsig", "markdownUrl": "https://www.anchorterminal.com/tools/statsig.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/statsig.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/statsig.json", "dns": "statsig.grade.anchorterminal.com", "repo": "https://github.com/statsig-io/statsig-server-core", "license": "Proprietary hosted service under Statsig's self-service or enterprise terms. The SDKs and the agent skills repository on GitHub are ISC", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.statsig.com/v3/mcp", "packages": [ { "registry": "npm", "name": "@statsig/statsig-node-core" }, { "registry": "npm", "name": "@statsig/js-client" }, { "registry": "pypi", "name": "statsig-python-core" }, { "registry": "npm", "name": "@statsig/siggy" } ], "auth": "mixed", "authNotes": "Self-serve. The Console API takes a Console API key in the `STATSIG-API-KEY` header, created in project settings as read-only or read and write. The MCP server uses OAuth with PKCE and dynamic client registration, which issues a personal Console API key carrying the user's role, or takes a Console key in the `statsig-api-key` header. OAuth needs the organisation owner to allow personal keys for the role. Flag evaluation and event logging take a client or server SDK key.", "pricing": "freemium", "pricingNotes": "Free Developer plan with no card, covering 2 million events and 50,000 session replays a month. Pro is $150 a month with 5 million events, then $0.05 per 1,000 events. Enterprise is by contract. Flag and config checks are unlimited on every plan, and API and MCP calls are not billed. An agent can start on the free plan without a contract (https://www.statsig.com/pricing, checked 2026-10-08).", "priceSummary": "$150 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs corpus, the OpenAPI spec or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 18, "popularity": { "githubStars": null, "npmWeekly": 4157066, "pypiWeekly": 893619, "asOf": "2026-10-08" }, "docsUrl": "https://docs.statsig.com/console-api/introduction", "llmsTxt": "https://docs.statsig.com/llms.txt", "openapi": "https://api.statsig.com/openapi/20240601.json", "registryName": "com.statsig/statsig-mcp-server", "capabilities": [ "analytics.experiments", "analytics.flags", "analytics.query", "analytics.events" ], "tags": [ "official", "hosted", "mcp", "oauth", "openapi", "llms-txt", "free-tier", "no-card", "status-page", "soc2", "eu-region" ], "lastRelease": "2026-10-28", "graded": true, "anchor": { "graded": true, "score": 72.4, "grade": "BB", "agentReady": true, "rank": 128, "ranked": true, "rankOf": 1510, "categoryRank": 1, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 71, "maintenance": 81, "payments": 40, "reliability": 79, "schema": 82, "security": 74, "transparency": 76 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "Statsig suits agents that manage feature gates and experiments and read their results. Its MCP server has 18 default tools, OAuth, read-only access by project and role, and a confirmation on updates. Errors carry only a status and a message, no idempotency keys were found, and the privacy notice is Amplitude's and doesn't name Statsig.", "bestFor": "An agent that creates, updates and cleans up feature gates, dynamic configs and experiments, and reads experiment results and audit history.", "strengths": [ "Hosted MCP server with 18 default tools and a discovery layer that replaced 93 tools on the V1 server", "MCP access set per project and per role as no access, read only or read and write, with a confirmation on updates", "Public OpenAPI 3.0 spec with 325 operations per the 8 October check, plus llms.txt and a Markdown copy of every docs page", "Free Developer plan with no card and 2 million events a month, and a public overage price of $0.05 per 1,000 events on Pro", "Audit logs kept indefinitely and readable through the API and the `log_read` MCP tool" ], "weaknesses": [ "Console API errors carry only `status` and `message`, and the spec documents no 429 response", "No idempotency keys were found, and most MCP update tools replace the whole resource", "The project Console API key reads and writes everything in a project unless created read-only", "The privacy notice is Amplitude's, last updated 31 August 2026, and doesn't name Statsig", "The 99.95 per cent SLA needs Enterprise premium support and covers the Console user interface" ], "agentNotes": [ "Connect to https://api.statsig.com/v3/mcp. The official MCP registry entry still lists the V1 URL, which has 93 tools", "Call `get_context` first to learn the project, your permissions and the review settings", "Read the resource before `gate_update`, `experiment_update` or `dynamic_config_update`. They replace the whole resource, so resend every field you want kept", "Use `discover_tools` for partial edits, and fetch a fresh `operationHandle` when one expires", "On a 429 slow down and back off with jitter. Rejected attempts count towards the quota of about 1,800 mutations per 15 minutes" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 72.4 } ], "editorialScores": { "ergonomics": 71, "maintenance": 81, "payments": 40, "reliability": 79, "schema": 82, "security": 74, "transparency": 64 }, "provenanceScore": 87, "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": "2026-10-28", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "claudeCode": "claude mcp add --transport http statsig https://api.statsig.com/v3/mcp", "config": { "mcpServers": { "statsig": { "url": "https://api.statsig.com/v3/mcp" } } } }, "letme": { "capability": "https://letme.dev/analytics.experiments", "tool": "https://letme.dev/statsig" }, "area": "business", "unitPrices": [ { "item": "Pro plan", "unit": "month", "usd": 150, "note": "5 million events and 100,000 session replays included" }, { "item": "Metered event", "unit": "tx", "usd": 0.00005, "note": "Pro plan, above 5 million a month" } ], "provenance": { "legalEntity": "Amplitude, Inc.", "domain": "statsig.com", "domainRegistered": "1998-12-29", "endpointOnVendorDomain": true, "terms": "https://www.statsig.com/terms", "privacy": "https://amplitude.com/privacy", "statusPage": "https://status.statsig.com", "changelog": "https://www.statsig.com/updates", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The self-service subscription agreement at statsig.com/terms, effective 4 August 2025, names Amplitude, Inc. as the party called Statsig. The enterprise terms (effective 18 February 2026) and the DPA do the same.", "statsig.com/privacy redirects to amplitude.com/privacy, a notice last updated 31 August 2026 that covers Amplitude, Inc. and its affiliates and doesn't name Statsig. It says it does not apply to end-user data that customers send to the product.", "statsig.com/legal/subprocessors redirects to amplitude.com/subprocessor-list, last updated 13 May 2026, which marks the providers used for Statsig-branded services.", "The MCP server answers at api.statsig.com. The Console API answers at statsigapi.net, a second domain the vendor's docs name.", "www.statsig.com/.well-known/security.txt returns 404.", "RDAP for statsig.com gives a registration date of 1998-12-29." ], "score": 87 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/statsig.json", "live": { "slug": "statsig", "probe": { "target": "https://api.statsig.com/v3/mcp", "method": "get", "lastAt": "2026-11-07T19:22:35.997131135Z", "lastOk": true, "lastStatus": 401, "lastMs": 52, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 38, "p95ms24h": 104, "samples24h": 238, "samples30d": 7450, "days": [ { "date": "2026-10-08", "probes": 70, "ok": 70 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "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": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "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": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.statsig.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:23:44.466939194Z" }, "versions": [ { "registry": "github", "name": "statsig-io/statsig-server-core", "version": "0.24.2", "released": "2026-11-06", "seenAt": "2026-11-07T00:08:26.667471698Z" }, { "registry": "mcp-registry", "name": "com.statsig/statsig-mcp-server", "version": "1.0.0", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "@statsig/js-client", "version": "3.33.8", "seenAt": "2026-11-07T00:08:22.944088803Z" }, { "registry": "npm", "name": "@statsig/siggy", "version": "0.0.4", "seenAt": "2026-11-07T00:08:24.797062329Z" }, { "registry": "npm", "name": "@statsig/statsig-node-core", "version": "0.24.2", "seenAt": "2026-11-07T00:08:22.466595727Z" }, { "registry": "pypi", "name": "statsig-python-core", "version": "0.24.2", "released": "2026-11-06", "seenAt": "2026-11-07T00:08:24.650927632Z" } ], "githubStars": 24, "npmWeekly": 1691593, "pypiWeekly": 1020869, "securityTxt": { "url": "https://statsig.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:09.441235194Z" }, "llmsTxt": { "url": "https://docs.statsig.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:02.780586563Z" }, "domain": { "domain": "statsig.com", "registered": "1998-12-29", "source": "https://rdap.verisign.com/com/v1/domain/statsig.com", "checkedAt": "2026-11-01T14:08:46.011840445Z" }, "pages": [ { "url": "https://www.statsig.com/updates", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:35:09.364215881Z", "changedAt": "2026-11-06T13:55:37.429098458Z", "fingerprint": "99420812e795" }, { "url": "https://www.statsig.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:35:04.36786338Z", "changedAt": "2026-10-23T02:07:16.258880643Z", "fingerprint": "87ef02db6355" }, { "url": "https://www.statsig.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:35:07.111577548Z", "changedAt": "2026-10-23T02:07:18.656882729Z", "fingerprint": "036fc50be6dc" } ], "mcpTools": { "url": "https://api.statsig.com/v3/mcp", "checkedAt": "2026-11-07T01:48:08.93079327Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:48:08.93079327Z" }, "github": { "repo": "statsig-io/statsig-server-core", "checkedAt": "2026-11-02T09:28:04.214538182Z", "stars": 24, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-28T15:41:59Z", "openIssues": 23, "openPRs": 15, "issuesOpened90d": 9, "issuesClosed90d": 0, "prsMerged90d": 0, "ci": { "branch": "main", "runs": 50, "success": 0, "failure": 50, "other": 0, "latest": "failure", "latestAt": "2026-10-28T19:07:05Z" }, "replies": { "sampled": 25, "unanswered": 22, "medianDays": 3.2 } }, "updatedAt": "2026-11-07T19:23:44.466939194Z" } }, "edges": [ { "by": 25, "category": "payments", "leads": "statsig", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). No FME prices are published; harness.io/pricing lists FME only under Enterprise, priced by quotation (0). The docs describe a Start FME Free Plan step inside a Harness account; its limits and whether a card is needed aren't stated (15 of 20). A person signs up for Harness in a browser and creates a key or token (0). 0+0+15+0 = 15.", "b": "No x402, MPP or L402 (0). Prices are public without a login. Pro is $150 a month with 5 million events, then $0.05 per 1,000 events (20). The Developer plan is free with no card and 2 million events a month (20). A person signs up in a browser, then creates a key or approves OAuth (0)." }, "scores": { "a": 15, "b": 40 } }, { "by": 15, "category": "transparency", "leads": "statsig", "name": "Transparency \u0026 trust", "reasons": { "a": "A closed service under Harness's subscription terms; the MCP server is MIT (18 of 30). The privacy statement covers website and sales data and defers customer data to the customer agreement and a published DPA; retention periods for customer data weren't found (18 of 30). A versioning policy for SDKs with support windows, and Split-era API endpoints marked deprecated with migration guides (14 of 20). Sub-processors are on the trust centre, which we didn't read, and the security page doesn't name data locations (10 of 20). 18+18+14+10 = 60.", "b": "Closed hosted service under a published self-service agreement and enterprise terms. The SDKs are open source under ISC (17 of 30). The terms, DPA and AI governance page mostly agree. The DPA names Amplitude, Inc. as processor and keeps data as long as necessary, the pricing page gives 1 year of analytics retention on the free plan, and the docs say customer data is not used to build AI models without written consent. The privacy notice is Amplitude's and doesn't name Statsig, and the self-service terms name Amplitude, Inc. under an effective date of 4 August 2025, before Statsig joined Amplitude on 5 May 2026 (18 of 30). Each Console API version is promised not to break, a deprecation notices page gives dates, and MCP V1 stays supported. No notice period is stated (12 of 20). Amplitude's sub-processor list, updated 13 May 2026, gives locations and marks the providers used for Statsig-branded services. EU hosting is an Enterprise option (17 of 20)." }, "scores": { "a": 61, "b": 76 } }, { "by": 12, "category": "ergonomics", "leads": "harness-fme", "name": "Agent ergonomics", "reasons": { "a": "11 consolidated tools, and `--toolsets=fme` narrows the server to FME (25). Flag lists filter server-side by name, tag and rollout status, and the Admin API paginates with markerLimit (17 of 20). Documented status codes, 429 headers, and a harness_diagnose tool. Error bodies aren't documented per endpoint (14 of 20). harness_list and harness_get carry readOnlyHint, write tools ask for confirmation by elicitation, and harness_delete is marked destructive. No idempotency keys (15 of 20). Two required settings (API key, optional org and project, account ID read from the token); a Python Admin API wrapper and CLI, and SDKs in more than a dozen languages for evaluation (12 of 15). 25+17+14+15+12 = 83.", "b": "The MCP V3 server shows 18 default tools, which is 15 on the checklist. Add back 8 for the discovery layer that reaches other operations on demand, `query_fields` on experiment reads and read-only access (23 of 25). `limit` and `page` on 49 list operations with pagination metadata per the 8 October check, a cursor on the Logs Explorer query, and filters by tag, status, creator and date (17 of 20). Errors are a `status` and a `message` with no machine code, and MCP results set `isError` (11 of 20). No idempotency keys were found. Updates and `api_destructive` calls need a `confirmation` object, and operations are split into read, write and destructive lanes. We could not read the live tool annotations (10 of 20). The SDKs cover flag evaluation and event logging in many languages, not the Console API, and the `siggy` CLI on npm is version 0.0.4 from September 2024 (10 of 15)." }, "scores": { "a": 83, "b": 71 } }, { "by": 11, "category": "schema", "leads": "statsig", "name": "Schema \u0026 documentation", "reasons": { "a": "No public OpenAPI file for the Admin API was found; the reference is a ReadMe site with a Postman collection. The MCP server's 11 tools have typed inputs, and harness_describe returns each FME resource's fields (18 of 25). llms.txt on both developer.harness.io and docs.split.io, and every page as Markdown with `.md` (10). The README describes each tool and when writes ask for confirmation; resource details sit behind harness_describe rather than in the tool text (13 of 20). The generic tools take a resource_type string and a body, so per-resource constraints aren't in the schema (8 of 15). An error-code page lists 400, 401, 402, 403, 404, 409 and 429 with causes, and docs carry curl examples (10 of 15). Tagged MCP releases and dated SDK versioning policy; the Admin API has v1 and v2 paths and deprecation notices for Split-era endpoints (12 of 15). 18+10+13+8+10+12 = 71.", "b": "Public OpenAPI 3.0 spec for Console API version 20240601 with 209 paths and 325 operations, per the 8 October check, not re-read on 1 November, and typed MCP tools per the tool reference (25). llms.txt, llms-full.txt, a Markdown copy of each page and a public docs MCP server (10). Every operation has a summary but only 29 of 325 have a description, per the 8 October check. The MCP tool reference states each tool's purpose and when to ask the user first (11 of 20). 1,164 enums across 188 schemas, with required fields marked, per the 8 October check (12 of 15). Examples on most responses. The spec documents 401 on 156 operations, 404 on 126 and 400 on 106, and no 429, per the 8 October check (11 of 15). A dated API version sent in the `STATSIG-API-VERSION` header with a promise not to break a version, and a dated product updates page. No changelog for the API alone was found (13 of 15)." }, "scores": { "a": 71, "b": 82 } }, { "by": 5, "category": "security", "leads": "harness-fme", "name": "Security \u0026 auth", "reasons": { "a": "Admin API keys with combinable roles that can't be widened after creation, Harness PATs and SATs for central management, and Harness Platform OAuth on the hosted MCP endpoint. Credentials travel in headers (28 of 30). HARNESS_READ_ONLY removes every write, writes go through elicitation with a risk threshold for auto-approval, and FME change requests add approval for flag changes (19 of 20). No prompt-injection guidance; the tools return flag names, descriptions and rule data written by people (3 of 15). FME admin, environment and object audit logs, plus structured MCP audit events to file, webhook or OpenTelemetry sinks (13 of 15). SOC 1 and SOC 2 Type II, ISO 27001, 27017 and 27018, FedRAMP 20x, a security@harness.io disclosure route with a 24-hour response, a private bug bounty on request and annual external penetration tests. No security.txt (16 of 20). 28+19+3+13+16 = 79.", "b": "OAuth for the MCP server with PKCE, dynamic client registration and a device code grant, issuing personal Console API keys that carry the user's role. Console keys can be created read-only or read and write, and rotated or deactivated through the API. The OAuth metadata lists no scopes, and a project Console key reaches every Console API endpoint (25 of 30). MCP scope is set per project and per role as no access, read only or read and write. Updates and destructive operations need a confirmation, and project review policies still apply (19 of 20). No guidance on prompt injection was found, though tools return names, descriptions and log data that people wrote. The docs tell users to review each change before the agent confirms (4 of 15). Audit logs are kept indefinitely with an API, and personal keys attribute changes to a user (14 of 15). SOC 2 Type II and a bug bounty programme are stated on the security page, with no public programme link and no security.txt (12 of 20)." }, "scores": { "a": 79, "b": 74 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Harness Inc.", "b": "Amplitude, Inc.", "name": "Vendor" }, { "a": "https://mcp.harness.io/mcp", "b": "https://api.statsig.com/v3/mcp", "name": "Hosted endpoint" }, { "a": "HTTP, stdio, Streamable HTTP", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "none", "b": "Proprietary hosted service under Statsig's self-service or enterprise terms. The SDKs and the agent skills repository on GitHub are ISC", "name": "Licence" }, { "a": "11", "b": "18", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "com.statsig/statsig-mcp-server", "name": "MCP registry" }, { "a": "2026-11-04", "b": "2026-10-28", "name": "Last release" }, { "a": "no date given", "b": "2025-08-04", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-08-31", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "8.8k npm/wk", "b": "4.2M npm/wk, 894k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Statsig scores 72.4 (BB) on agent readiness against Harness Feature Management \u0026 Experimentation's 69.2 (B), and leads in 3 of 7 scored categories. Harness Feature Management \u0026 Experimentation leads on agent ergonomics and security \u0026 auth.", "question": "Which is better for AI agents, Harness Feature Management \u0026 Experimentation or Statsig?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do Harness Feature Management \u0026 Experimentation and Statsig need an API key?" }, { "answer": "Yes. Harness Feature Management \u0026 Experimentation has a hosted endpoint at https://mcp.harness.io/mcp and Statsig at https://api.statsig.com/v3/mcp.", "question": "Can an agent call Harness Feature Management \u0026 Experimentation and Statsig without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 83 against 71", "Security \u0026 auth, 79 against 74" ], "also": [ "Runs on your own machine" ], "goodFor": "Teams already on Harness, or Split customers, who want agents to inspect and change flags and segments with guard rails.", "slug": "harness-fme", "watchFor": "No FME prices are published; Enterprise is by quotation and free plan limits are unstated" }, { "aheadOn": [ "Schema \u0026 documentation, 82 against 71", "Payments \u0026 pricing, 40 against 15", "Transparency \u0026 trust, 76 against 61" ], "also": [ "Agent-ready, a grade of BB or better", "Free to start without a card" ], "goodFor": "An agent that creates, updates and cleans up feature gates, dynamic configs and experiments, and reads experiment results and audit history.", "slug": "statsig", "watchFor": "Console API errors carry only `status` and `message`, and the spec documents no 429 response" } ], "history": { "harness-fme": null, "statsig": [ { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0.1, "from": 72.3, "fromGrade": "BB", "to": 72.4, "toGrade": "BB" } ] }, "job": { "capability": "analytics.flags", "name": "Feature flags" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amplitude-vs-statsig.json", "title": "Amplitude vs Statsig", "url": "https://www.anchorterminal.com/compare/amplitude-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/countly-vs-statsig.json", "title": "Countly vs Statsig", "url": "https://www.anchorterminal.com/compare/countly-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/fullstory-vs-statsig.json", "title": "Fullstory vs Statsig", "url": "https://www.anchorterminal.com/compare/fullstory-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/matomo-vs-statsig.json", "title": "Matomo vs Statsig", "url": "https://www.anchorterminal.com/compare/matomo-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/mixpanel-vs-statsig.json", "title": "Mixpanel vs Statsig", "url": "https://www.anchorterminal.com/compare/mixpanel-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-statsig.json", "title": "Mostly Good Metrics vs Statsig", "url": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/openpanel-vs-statsig.json", "title": "OpenPanel vs Statsig", "url": "https://www.anchorterminal.com/compare/openpanel-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/pendo-vs-statsig.json", "title": "Pendo vs Statsig", "url": "https://www.anchorterminal.com/compare/pendo-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/posthog-vs-statsig.json", "title": "PostHog vs Statsig", "url": "https://www.anchorterminal.com/compare/posthog-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/statsig-vs-userpilot.json", "title": "Statsig vs Userpilot", "url": "https://www.anchorterminal.com/compare/statsig-vs-userpilot" }, { "json": "https://www.anchorterminal.com/compare/statsig-vs-woopra.json", "title": "Statsig vs Woopra", "url": "https://www.anchorterminal.com/compare/statsig-vs-woopra" }, { "json": "https://www.anchorterminal.com/compare/fullstory-vs-harness-fme.json", "title": "Fullstory vs Harness Feature Management \u0026 Experimentation", "url": "https://www.anchorterminal.com/compare/fullstory-vs-harness-fme" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-heap.json", "title": "Harness Feature Management \u0026 Experimentation vs Heap", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-heap" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-openpanel.json", "title": "Harness Feature Management \u0026 Experimentation vs OpenPanel", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-openpanel" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-rudderstack-mcp.json", "title": "Harness Feature Management \u0026 Experimentation vs RudderStack MCP", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-rudderstack-mcp" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-woopra.json", "title": "Harness Feature Management \u0026 Experimentation vs Woopra", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-woopra" }, { "json": "https://www.anchorterminal.com/compare/heap-vs-statsig.json", "title": "Heap vs Statsig", "url": "https://www.anchorterminal.com/compare/heap-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/rudderstack-mcp-vs-statsig.json", "title": "RudderStack MCP vs Statsig", "url": "https://www.anchorterminal.com/compare/rudderstack-mcp-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/amplitude-vs-harness-fme.json", "title": "Amplitude vs Harness Feature Management \u0026 Experimentation", "url": "https://www.anchorterminal.com/compare/amplitude-vs-harness-fme" }, { "json": "https://www.anchorterminal.com/compare/countly-vs-harness-fme.json", "title": "Countly vs Harness Feature Management \u0026 Experimentation", "url": "https://www.anchorterminal.com/compare/countly-vs-harness-fme" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-harness-fme.json", "title": "Flagsmith vs Harness Feature Management \u0026 Experimentation", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-harness-fme" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-statsig.json", "title": "Flagsmith vs Statsig", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-launchdarkly.json", "title": "Harness Feature Management \u0026 Experimentation vs LaunchDarkly", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-launchdarkly" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-mixpanel.json", "title": "Harness Feature Management \u0026 Experimentation vs Mixpanel", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-mixpanel" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-optimizely.json", "title": "Harness Feature Management \u0026 Experimentation vs Optimizely Experimentation", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-optimizely" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-posthog.json", "title": "Harness Feature Management \u0026 Experimentation vs PostHog", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-posthog" }, { "json": "https://www.anchorterminal.com/compare/launchdarkly-vs-statsig.json", "title": "LaunchDarkly vs Statsig", "url": "https://www.anchorterminal.com/compare/launchdarkly-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-harness-fme.json", "title": "GrowthBook vs Harness Feature Management \u0026 Experimentation", "url": "https://www.anchorterminal.com/compare/growthbook-vs-harness-fme" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-statsig.json", "title": "GrowthBook vs Statsig", "url": "https://www.anchorterminal.com/compare/growthbook-vs-statsig" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-matomo.json", "title": "Harness Feature Management \u0026 Experimentation vs Matomo", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-matomo" }, { "json": "https://www.anchorterminal.com/compare/harness-fme-vs-mostly-good-metrics.json", "title": "Harness Feature Management \u0026 Experimentation vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-mostly-good-metrics" }, { "json": "https://www.anchorterminal.com/compare/optimizely-vs-statsig.json", "title": "Optimizely Experimentation vs Statsig", "url": "https://www.anchorterminal.com/compare/optimizely-vs-statsig" } ], "panel": null, "scores": [ { "by": 1, "edge": "harness-fme", "harness-fme": 80, "key": "reliability", "name": "Reliability", "statsig": 79, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 11, "edge": "statsig", "harness-fme": 71, "key": "schema", "name": "Schema \u0026 documentation", "statsig": 82, "weight": 13 }, { "by": 12, "edge": "harness-fme", "harness-fme": 83, "key": "ergonomics", "name": "Agent ergonomics", "statsig": 71, "weight": 13 }, { "by": 5, "edge": "harness-fme", "harness-fme": 79, "key": "security", "name": "Security \u0026 auth", "statsig": 74, "weight": 14 }, { "by": 25, "edge": "statsig", "harness-fme": 15, "key": "payments", "name": "Payments \u0026 pricing", "statsig": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 0, "edge": "", "harness-fme": 81, "key": "maintenance", "name": "Maintenance \u0026 community", "statsig": 81, "weight": 7 }, { "by": 15, "edge": "statsig", "harness-fme": 61, "key": "transparency", "name": "Transparency \u0026 trust", "statsig": 76, "weight": 7 } ], "summary": "Statsig scores 72.4 (BB) on agent readiness against Harness Feature Management \u0026 Experimentation's 69.2 (B), and leads in 3 of 7 scored categories. Harness Feature Management \u0026 Experimentation leads on agent ergonomics and security \u0026 auth. Both do feature flags.", "tasks": null, "tutorials": [], "verdicts": { "harness-fme": "Harness FME, formerly Split, gives agents 11 consolidated MCP tools with an FME-only toolset, a read-only switch and confirmation on writes, over an Admin API with documented limits and role-scoped keys. FME prices are not published, the free plan's limits are unstated, and the hosted MCP endpoint must be enabled by Harness Support.", "statsig": "Statsig suits agents that manage feature gates and experiments and read their results. Its MCP server has 18 default tools, OAuth, read-only access by project and role, and a confirmation on updates. Errors carry only a status and a message, no idempotency keys were found, and the privacy notice is Amplitude's and doesn't name Statsig." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harness-fme-vs-statsig", "json": "https://www.anchorterminal.com/compare/harness-fme-vs-statsig.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harness-fme-vs-statsig.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harness-fme-vs-statsig.min.md" }, "markdown": "Statsig scores 72.4 (BB) on agent readiness against Harness Feature Management \u0026 Experimentation's 69.2 (B), and leads in 3 of 7 scored categories. Harness Feature Management \u0026 Experimentation leads on agent ergonomics and security \u0026 auth. Both do feature flags.\n\n- Harness Feature Management \u0026 Experimentation: grade B, 69.2/100, rank #258 of 1510. Markdown https://www.anchorterminal.com/tools/harness-fme.md · JSON https://www.anchorterminal.com/api/v1/tools/harness-fme.json\n- Statsig: grade BB, 72.4/100, rank #128 of 1510. Markdown https://www.anchorterminal.com/tools/statsig.md · JSON https://www.anchorterminal.com/api/v1/tools/statsig.json\n- Best product analytics and experimentation tools for AI agents: https://www.anchorterminal.com/best/product-analytics/index.md\n- All 170 product analytics comparisons: https://www.anchorterminal.com/compare/product-analytics/index.md\n\n## Which one, for what\n\n### Harness Feature Management \u0026 Experimentation (B)\n\nGood for: Teams already on Harness, or Split customers, who want agents to inspect and change flags and segments with guard rails.\n\nAhead on:\n- Agent ergonomics, 83 against 71\n- Security \u0026 auth, 79 against 74\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: No FME prices are published; Enterprise is by quotation and free plan limits are unstated\n\n### Statsig (BB)\n\nGood for: An agent that creates, updates and cleans up feature gates, dynamic configs and experiments, and reads experiment results and audit history.\n\nAhead on:\n- Schema \u0026 documentation, 82 against 71\n- Payments \u0026 pricing, 40 against 15\n- Transparency \u0026 trust, 76 against 61\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Free to start without a card\n\nWatch for: Console API errors carry only `status` and `message`, and the spec documents no 429 response\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Statsig +25\n\n- Harness Feature Management \u0026 Experimentation (15): No x402, MPP or L402 (0). No FME prices are published; harness.io/pricing lists FME only under Enterprise, priced by quotation (0). The docs describe a Start FME Free Plan step inside a Harness account; its limits and whether a card is needed aren't stated (15 of 20). A person signs up for Harness in a browser and creates a key or token (0). 0+0+15+0 = 15.\n- Statsig (40): No x402, MPP or L402 (0). Prices are public without a login. Pro is $150 a month with 5 million events, then $0.05 per 1,000 events (20). The Developer plan is free with no card and 2 million events a month (20). A person signs up in a browser, then creates a key or approves OAuth (0).\n\n### Transparency \u0026 trust: Statsig +15\n\n- Harness Feature Management \u0026 Experimentation (61): A closed service under Harness's subscription terms; the MCP server is MIT (18 of 30). The privacy statement covers website and sales data and defers customer data to the customer agreement and a published DPA; retention periods for customer data weren't found (18 of 30). A versioning policy for SDKs with support windows, and Split-era API endpoints marked deprecated with migration guides (14 of 20). Sub-processors are on the trust centre, which we didn't read, and the security page doesn't name data locations (10 of 20). 18+18+14+10 = 60.\n- Statsig (76): Closed hosted service under a published self-service agreement and enterprise terms. The SDKs are open source under ISC (17 of 30). The terms, DPA and AI governance page mostly agree. The DPA names Amplitude, Inc. as processor and keeps data as long as necessary, the pricing page gives 1 year of analytics retention on the free plan, and the docs say customer data is not used to build AI models without written consent. The privacy notice is Amplitude's and doesn't name Statsig, and the self-service terms name Amplitude, Inc. under an effective date of 4 August 2025, before Statsig joined Amplitude on 5 May 2026 (18 of 30). Each Console API version is promised not to break, a deprecation notices page gives dates, and MCP V1 stays supported. No notice period is stated (12 of 20). Amplitude's sub-processor list, updated 13 May 2026, gives locations and marks the providers used for Statsig-branded services. EU hosting is an Enterprise option (17 of 20).\n\n### Agent ergonomics: Harness Feature Management \u0026 Experimentation +12\n\n- Harness Feature Management \u0026 Experimentation (83): 11 consolidated tools, and `--toolsets=fme` narrows the server to FME (25). Flag lists filter server-side by name, tag and rollout status, and the Admin API paginates with markerLimit (17 of 20). Documented status codes, 429 headers, and a harness_diagnose tool. Error bodies aren't documented per endpoint (14 of 20). harness_list and harness_get carry readOnlyHint, write tools ask for confirmation by elicitation, and harness_delete is marked destructive. No idempotency keys (15 of 20). Two required settings (API key, optional org and project, account ID read from the token); a Python Admin API wrapper and CLI, and SDKs in more than a dozen languages for evaluation (12 of 15). 25+17+14+15+12 = 83.\n- Statsig (71): The MCP V3 server shows 18 default tools, which is 15 on the checklist. Add back 8 for the discovery layer that reaches other operations on demand, `query_fields` on experiment reads and read-only access (23 of 25). `limit` and `page` on 49 list operations with pagination metadata per the 8 October check, a cursor on the Logs Explorer query, and filters by tag, status, creator and date (17 of 20). Errors are a `status` and a `message` with no machine code, and MCP results set `isError` (11 of 20). No idempotency keys were found. Updates and `api_destructive` calls need a `confirmation` object, and operations are split into read, write and destructive lanes. We could not read the live tool annotations (10 of 20). The SDKs cover flag evaluation and event logging in many languages, not the Console API, and the `siggy` CLI on npm is version 0.0.4 from September 2024 (10 of 15).\n\n### Schema \u0026 documentation: Statsig +11\n\n- Harness Feature Management \u0026 Experimentation (71): No public OpenAPI file for the Admin API was found; the reference is a ReadMe site with a Postman collection. The MCP server's 11 tools have typed inputs, and harness_describe returns each FME resource's fields (18 of 25). llms.txt on both developer.harness.io and docs.split.io, and every page as Markdown with `.md` (10). The README describes each tool and when writes ask for confirmation; resource details sit behind harness_describe rather than in the tool text (13 of 20). The generic tools take a resource_type string and a body, so per-resource constraints aren't in the schema (8 of 15). An error-code page lists 400, 401, 402, 403, 404, 409 and 429 with causes, and docs carry curl examples (10 of 15). Tagged MCP releases and dated SDK versioning policy; the Admin API has v1 and v2 paths and deprecation notices for Split-era endpoints (12 of 15). 18+10+13+8+10+12 = 71.\n- Statsig (82): Public OpenAPI 3.0 spec for Console API version 20240601 with 209 paths and 325 operations, per the 8 October check, not re-read on 1 November, and typed MCP tools per the tool reference (25). llms.txt, llms-full.txt, a Markdown copy of each page and a public docs MCP server (10). Every operation has a summary but only 29 of 325 have a description, per the 8 October check. The MCP tool reference states each tool's purpose and when to ask the user first (11 of 20). 1,164 enums across 188 schemas, with required fields marked, per the 8 October check (12 of 15). Examples on most responses. The spec documents 401 on 156 operations, 404 on 126 and 400 on 106, and no 429, per the 8 October check (11 of 15). A dated API version sent in the `STATSIG-API-VERSION` header with a promise not to break a version, and a dated product updates page. No changelog for the API alone was found (13 of 15).\n\n### Security \u0026 auth: Harness Feature Management \u0026 Experimentation +5\n\n- Harness Feature Management \u0026 Experimentation (79): Admin API keys with combinable roles that can't be widened after creation, Harness PATs and SATs for central management, and Harness Platform OAuth on the hosted MCP endpoint. Credentials travel in headers (28 of 30). HARNESS_READ_ONLY removes every write, writes go through elicitation with a risk threshold for auto-approval, and FME change requests add approval for flag changes (19 of 20). No prompt-injection guidance; the tools return flag names, descriptions and rule data written by people (3 of 15). FME admin, environment and object audit logs, plus structured MCP audit events to file, webhook or OpenTelemetry sinks (13 of 15). SOC 1 and SOC 2 Type II, ISO 27001, 27017 and 27018, FedRAMP 20x, a security@harness.io disclosure route with a 24-hour response, a private bug bounty on request and annual external penetration tests. No security.txt (16 of 20). 28+19+3+13+16 = 79.\n- Statsig (74): OAuth for the MCP server with PKCE, dynamic client registration and a device code grant, issuing personal Console API keys that carry the user's role. Console keys can be created read-only or read and write, and rotated or deactivated through the API. The OAuth metadata lists no scopes, and a project Console key reaches every Console API endpoint (25 of 30). MCP scope is set per project and per role as no access, read only or read and write. Updates and destructive operations need a confirmation, and project review policies still apply (19 of 20). No guidance on prompt injection was found, though tools return names, descriptions and log data that people wrote. The docs tell users to review each change before the agent confirms (4 of 15). Audit logs are kept indefinitely with an API, and personal keys attribute changes to a user (14 of 15). SOC 2 Type II and a bug bounty programme are stated on the security page, with no public programme link and no security.txt (12 of 20).\n\n## Score by category\n\n| Category | Weight | Harness Feature Management \u0026 Experimentation | Statsig | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 80 | 79 | Harness Feature Management \u0026 Experimentation +1 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 71 | 82 | Statsig +11 |\n| Agent ergonomics | 13% (16.2 this run) | 83 | 71 | Harness Feature Management \u0026 Experimentation +12 |\n| Security \u0026 auth | 14% (17.5 this run) | 79 | 74 | Harness Feature Management \u0026 Experimentation +5 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 15 | 40 | Statsig +25 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 81 | 81 | even |\n| Transparency \u0026 trust | 7% (8.8 this run) | 61 | 76 | Statsig +15 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **69.2 · B** | **72.4 · BB** | |\n\n## Facts side by side\n\n| Fact | Harness Feature Management \u0026 Experimentation | Statsig |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Harness Inc. | Amplitude, Inc. |\n| Hosted endpoint | `https://mcp.harness.io/mcp` | `https://api.statsig.com/v3/mcp` |\n| Transports | HTTP, stdio, Streamable HTTP | HTTP, Streamable HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | none | Proprietary hosted service under Statsig's self-service or enterprise terms. The SDKs and the agent skills repository on GitHub are ISC |\n| Tools exposed | 11 | 18 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `com.statsig/statsig-mcp-server` |\n| Last release | 2026-11-04 | 2026-10-28 |\n| Terms last updated | no date given | 2025-08-04 |\n| Privacy policy last updated | no date given | 2026-08-31 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | 8.8k npm/wk | 4.2M npm/wk, 894k PyPI/wk |\n| Agent reviews | none | 3.8/5 (4) |\n\n## How the scores have moved\n\n### Harness Feature Management \u0026 Experimentation\n\nNo score change since it was listed.\n\n### Statsig\n\n- +0.1 on 28 October 2026: new evidence\n\n## Verdicts\n\n**Harness Feature Management \u0026 Experimentation.** Harness FME, formerly Split, gives agents 11 consolidated MCP tools with an FME-only toolset, a read-only switch and confirmation on writes, over an Admin API with documented limits and role-scoped keys. FME prices are not published, the free plan's limits are unstated, and the hosted MCP endpoint must be enabled by Harness Support.\n\n**Statsig.** Statsig suits agents that manage feature gates and experiments and read their results. Its MCP server has 18 default tools, OAuth, read-only access by project and role, and a confirmation on updates. Errors carry only a status and a message, no idempotency keys were found, and the privacy notice is Amplitude's and doesn't name Statsig.\n\n## Before you call either\n\n### Harness Feature Management \u0026 Experimentation\n\n1. Start the MCP server with `--toolsets=fme` so only FME resource types load\n2. Call `harness_describe(resource_type='fme_feature_flag')` before a create or update to see the fields\n3. Filter fme_feature_flag lists by name, tags or rollout status rather than listing every flag\n4. Set HARNESS_READ_ONLY for analysis tasks; leave confirmation on for kill, restore and delete\n5. On 429, wait at least the larger X-RateLimit-Reset-Seconds value before retrying\n\n### Statsig\n\n1. Connect to https://api.statsig.com/v3/mcp. The official MCP registry entry still lists the V1 URL, which has 93 tools\n2. Call `get_context` first to learn the project, your permissions and the review settings\n3. Read the resource before `gate_update`, `experiment_update` or `dynamic_config_update`. They replace the whole resource, so resend every field you want kept\n4. Use `discover_tools` for partial edits, and fetch a fresh `operationHandle` when one expires\n5. On a 429 slow down and back off with jitter. Rejected attempts count towards the quota of about 1,800 mutations per 15 minutes\n\n## Questions\n\n### Which is better for AI agents, Harness Feature Management \u0026 Experimentation or Statsig?\n\nStatsig scores 72.4 (BB) on agent readiness against Harness Feature Management \u0026 Experimentation's 69.2 (B), and leads in 3 of 7 scored categories. Harness Feature Management \u0026 Experimentation leads on agent ergonomics and security \u0026 auth.\n\n### Do Harness Feature Management \u0026 Experimentation and Statsig need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call Harness Feature Management \u0026 Experimentation and Statsig without installing anything?\n\nYes. Harness Feature Management \u0026 Experimentation has a hosted endpoint at https://mcp.harness.io/mcp and Statsig at https://api.statsig.com/v3/mcp.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness-fme-vs-statsig.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness-fme-vs-statsig.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness-fme\", \"b\": \"statsig\"}`. From a terminal: `anchor compare harness-fme statsig`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness-fme.json and https://www.anchorterminal.com/api/v1/tools/statsig.json\n\n## Other comparisons with Harness Feature Management \u0026 Experimentation or Statsig\n\n- [Amplitude vs Statsig](https://www.anchorterminal.com/compare/amplitude-vs-statsig.md)\n- [Countly vs Statsig](https://www.anchorterminal.com/compare/countly-vs-statsig.md)\n- [Fullstory vs Statsig](https://www.anchorterminal.com/compare/fullstory-vs-statsig.md)\n- [Matomo vs Statsig](https://www.anchorterminal.com/compare/matomo-vs-statsig.md)\n- [Mixpanel vs Statsig](https://www.anchorterminal.com/compare/mixpanel-vs-statsig.md)\n- [Mostly Good Metrics vs Statsig](https://www.anchorterminal.com/compare/mostly-good-metrics-vs-statsig.md)\n- [OpenPanel vs Statsig](https://www.anchorterminal.com/compare/openpanel-vs-statsig.md)\n- [Pendo vs Statsig](https://www.anchorterminal.com/compare/pendo-vs-statsig.md)\n- [PostHog vs Statsig](https://www.anchorterminal.com/compare/posthog-vs-statsig.md)\n- [Statsig vs Userpilot](https://www.anchorterminal.com/compare/statsig-vs-userpilot.md)\n- [Statsig vs Woopra](https://www.anchorterminal.com/compare/statsig-vs-woopra.md)\n- [Fullstory vs Harness Feature Management \u0026 Experimentation](https://www.anchorterminal.com/compare/fullstory-vs-harness-fme.md)\n- [Harness Feature Management \u0026 Experimentation vs Heap](https://www.anchorterminal.com/compare/harness-fme-vs-heap.md)\n- [Harness Feature Management \u0026 Experimentation vs OpenPanel](https://www.anchorterminal.com/compare/harness-fme-vs-openpanel.md)\n- [Harness Feature Management \u0026 Experimentation vs RudderStack MCP](https://www.anchorterminal.com/compare/harness-fme-vs-rudderstack-mcp.md)\n- [Harness Feature Management \u0026 Experimentation vs Woopra](https://www.anchorterminal.com/compare/harness-fme-vs-woopra.md)\n- [Heap vs Statsig](https://www.anchorterminal.com/compare/heap-vs-statsig.md)\n- [RudderStack MCP vs Statsig](https://www.anchorterminal.com/compare/rudderstack-mcp-vs-statsig.md)\n- [Amplitude vs Harness Feature Management \u0026 Experimentation](https://www.anchorterminal.com/compare/amplitude-vs-harness-fme.md)\n- [Countly vs Harness Feature Management \u0026 Experimentation](https://www.anchorterminal.com/compare/countly-vs-harness-fme.md)\n- [Flagsmith vs Harness Feature Management \u0026 Experimentation](https://www.anchorterminal.com/compare/flagsmith-vs-harness-fme.md)\n- [Flagsmith vs Statsig](https://www.anchorterminal.com/compare/flagsmith-vs-statsig.md)\n- [Harness Feature Management \u0026 Experimentation vs LaunchDarkly](https://www.anchorterminal.com/compare/harness-fme-vs-launchdarkly.md)\n- [Harness Feature Management \u0026 Experimentation vs Mixpanel](https://www.anchorterminal.com/compare/harness-fme-vs-mixpanel.md)\n- [Harness Feature Management \u0026 Experimentation vs Optimizely Experimentation](https://www.anchorterminal.com/compare/harness-fme-vs-optimizely.md)\n- [Harness Feature Management \u0026 Experimentation vs PostHog](https://www.anchorterminal.com/compare/harness-fme-vs-posthog.md)\n- [LaunchDarkly vs Statsig](https://www.anchorterminal.com/compare/launchdarkly-vs-statsig.md)\n- [GrowthBook vs Harness Feature Management \u0026 Experimentation](https://www.anchorterminal.com/compare/growthbook-vs-harness-fme.md)\n- [GrowthBook vs Statsig](https://www.anchorterminal.com/compare/growthbook-vs-statsig.md)\n- [Harness Feature Management \u0026 Experimentation vs Matomo](https://www.anchorterminal.com/compare/harness-fme-vs-matomo.md)\n- [Harness Feature Management \u0026 Experimentation vs Mostly Good Metrics](https://www.anchorterminal.com/compare/harness-fme-vs-mostly-good-metrics.md)\n- [Optimizely Experimentation vs Statsig](https://www.anchorterminal.com/compare/optimizely-vs-statsig.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": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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": "Harness Feature Management \u0026 Experimentation vs Statsig", "url": "" } ], "description": "Statsig scores 72.4 (BB) to Harness Feature Management \u0026 Experimentation's 69.2 (B) for feature flags. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Harness Feature Management \u0026 Experimentation B 69.2", "Statsig BB 72.4", "scores" ], "h1": "Harness Feature Management \u0026 Experimentation vs Statsig", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/harness-fme-vs-statsig", "published": "2026-10-01", "section": "tools", "title": "Harness Feature Management \u0026 Experimentation vs Statsig (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/harness-fme-vs-statsig" }, "tokens": { "markdown": 4950, "slim": 2730 }, "version": 1 }