{ "data": { "a": { "slug": "growthbook", "name": "GrowthBook", "vendor": "GrowthBook, Inc.", "vendorUrl": "https://www.growthbook.io", "kind": "http-api", "category": "product-analytics", "summary": "GrowthBook is an open-source platform for feature flags, experiments and product analytics, sold as GrowthBook Cloud or run self-hosted. Agents reach it through a REST API with a public OpenAPI spec and an official MCP server.", "url": "https://www.anchorterminal.com/tools/growthbook", "markdownUrl": "https://www.anchorterminal.com/tools/growthbook.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/growthbook.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/growthbook.json", "dns": "growthbook.grade.anchorterminal.com", "repo": "https://github.com/growthbook/growthbook", "license": "MIT for the core and for the MCP server. Three enterprise directories in the main repository are under GrowthBook's enterprise licence. GrowthBook Cloud is a hosted service under the Customer Agreement", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://mcp.growthbook.io/mcp", "packages": [ { "registry": "npm", "name": "@growthbook/mcp" }, { "registry": "npm", "name": "@growthbook/growthbook" }, { "registry": "pypi", "name": "growthbook" } ], "auth": "mixed", "authNotes": "The hosted MCP server uses OAuth with PKCE, dynamic client registration, refresh tokens and a revocation endpoint, with api.growthbook.io as the authorisation server. A person signs in and consents in a browser. The only scopes are openid, profile, email and offline_access, so the token carries the user's own permissions. The REST API takes a Personal Access Token or a Secret Key as a Bearer token or as the HTTP Basic username. Both are self-serve in the app. A Secret Key can hold any built-in or custom role with per-project overrides and environment limits, and both key types can expire. On the Free plan members can only hold the Admin role.", "pricing": "freemium", "pricingNotes": "Starter is free with no card, for up to 3 users and 1 project, so an agent's owner can start without a contract. Pro is $40 a seat a month for up to 30 users. Enterprise is by contract. Flags, experiments and traffic are unlimited on every plan, and API and MCP calls are not billed. Pro meters CDN requests, CDN bandwidth and Managed Warehouse events above its allowance. Self-hosting the open-source edition is free (https://www.growthbook.io/pricing, checked 2026-10-08).", "priceSummary": "$40 / seat-mo", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the OpenAPI spec, the MCP server source or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 4, "popularity": { "githubStars": 8484, "npmWeekly": 1290544, "pypiWeekly": 432892, "asOf": "2026-10-08" }, "docsUrl": "https://docs.growthbook.io", "llmsTxt": "https://docs.growthbook.io/llms.txt", "openapi": "https://api.growthbook.io/api/v1/openapi.yaml", "registryName": "io.github.growthbook/growthbook-mcp", "capabilities": [ "analytics.experiments", "analytics.flags", "analytics.query", "analytics.events" ], "tags": [ "official", "hosted", "open-source", "self-hosted", "mcp", "oauth", "openapi", "llms-txt", "free-tier", "no-card", "status-page", "soc2" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 68.6, "grade": "B", "agentReady": false, "rank": 279, "ranked": true, "rankOf": 1510, "categoryRank": 5, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 76, "maintenance": 89, "payments": 40, "reliability": 86, "schema": 76, "security": 76, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -6, "negativeNotes": [ "10 August 2026. MCP server 2.1.0 replaced `growthbook_call_api` with two tools in a minor version, eleven days after 2.0.0 removed every 1.x tool, while the docs tell users to install `@growthbook/mcp@latest`. Both are marked breaking in the changelog with migration steps, and we found no advance notice, so the deduction is the minimum (https://github.com/growthbook/growthbook-mcp/blob/main/CHANGELOG.md).", "13 to 30 October 2026. Security fixes merged into the main repository after GrowthBook 5.1.0 (21 September), the newest release, and in no release on 1 November. Commit 900a546b (#7172, 13 October) says the OAuth consent page's Deny button \"redirected to the raw redirect_uri query param with no server check\", so a `javascript:` redirect URI \"ran attacker script on the app origin after one click\", and dynamic client registration accepted `javascript:` and `data:` redirect URIs. Commit 106fc6a7 (#7519, 30 October) says `PUT /organization` let any org admin use `ownerEmail` as \"a regex oracle over every user's email across tenants\". `git tag --contains` finds neither in a release, and the consent page and the user lookup they fix are both in v5.1.0. One term at the floor for fixes in no release, as composio-rube and microsoft-execution-containers took, whatever their age. The repository's deploy workflow builds every push to main that touches `packages/` and rolls it to GrowthBook Cloud's production API services, so Cloud probably runs both fixes, though its run history wasn't readable. That doesn't lower the term. On Cloud they read as fixed, vendor-described flaws with no advisory, a script redirect on the app origin and a cross-tenant lookup, which this run deducts at -3 (terraform-mcp, spree-commerce). The two fold into one term, as claude-code's and claude-agent-sdk's repeated changelog-only security fixes fold into one. https://github.com/growthbook/growthbook/commit/900a546b1abbb3ed6d867146aa7ce8eed59af0e2 and https://github.com/growthbook/growthbook/commit/106fc6a75a749bb7234b705aa2ad43c2f28cc532 and https://github.com/growthbook/growthbook/blob/main/.github/workflows/deploy.yml" ], "verdict": "GrowthBook Cloud's MCP server has four annotated tools, OAuth whose consent page can grant read-only or confirmation-gated access, and a 442-operation OpenAPI spec behind it. The free plan needs no card. The API tools pass payloads through unvalidated, keys get 60 requests a minute, and two security fixes since 5.1.0 are unreleased.", "bestFor": "Teams that want flags and experiments analysed against their own warehouse, with an open-source core and a self-hosted option.", "strengths": [ "The MCP server has four tools, each with readOnlyHint and destructiveHint, and a second endpoint with only the two API tools", "OAuth consent can grant Read only, Human-in-the-Loop or custom permissions, and keys and tokens expire and rotate in place", "Human-in-the-Loop holds risky REST writes, MCP ones included, until a person confirms them, with each decision in the audit log", "Public OpenAPI 3.1 spec with 324 paths and 442 operations, plus llms.txt and a Markdown copy of every docs page", "Starter plan is free with no card, with unlimited flags, experiments and traffic for up to 3 users" ], "weaknesses": [ "The API tools take a path and a JSON string and don't validate payloads, so correct calls depend on the bundled skills", "Two security fixes merged in October 2026, an OAuth consent-page script redirect and a cross-tenant email oracle, are in no release", "API keys are limited to 60 requests a minute on Cloud, and no idempotency keys were found", "Confirmation and audit logs are on Enterprise only, and Free plan connections can only take Full access", "MCP 2.0.0 and 2.1.0 replaced the whole tool surface in July and August 2026, the second in a minor version" ], "agentNotes": [ "Connect to https://mcp.growthbook.io/mcp and complete OAuth in a browser. Ask for Read only at consent unless the task needs writes", "Call `growthbook_list_skills` and `growthbook_read_skill` before writing. The API tools don't validate payloads, so use the paths the skill names", "Expect a 202 with a confirmation link when Human-in-the-Loop holds a write. Tell the user and wait; a held request expires after an hour", "Stay under 60 requests a minute per key. On 429 wait for the `RateLimit-Reset` seconds before retrying", "List calls return 10 items by default. Pass `limit` up to 100 and `offset` to page" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 68.6 } ], "editorialScores": { "ergonomics": 76, "maintenance": 89, "payments": 40, "reliability": 86, "schema": 76, "security": 76, "transparency": 66 }, "provenanceScore": 84, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npx -y @growthbook/mcp@latest", "http": "curl https://api.growthbook.io/api/v1/features -H \"Authorization: Bearer secret_abc123DEF456\"", "claudeCode": "claude mcp add --transport http growthbook https://mcp.growthbook.io/mcp", "config": { "mcpServers": { "growthbook": { "url": "https://mcp.growthbook.io/mcp" } } } }, "letme": { "capability": "https://letme.dev/analytics.experiments", "tool": "https://letme.dev/growthbook" }, "area": "business", "unitPrices": [ { "item": "Pro plan seat", "unit": "seat-month", "usd": 40, "note": "Up to 30 users and 3 projects" }, { "item": "CDN requests", "unit": "1k-requests", "usd": 0.01, "note": "Pro plan, above 2 million a month ($10 per million)" }, { "item": "Managed Warehouse event", "unit": "tx", "usd": 0.00003, "note": "Pro plan, above 2 million a month ($30 per million)" }, { "item": "CDN bandwidth", "unit": "gb", "usd": 1, "note": "Pro plan, above 20 GB a month" } ], "provenance": { "legalEntity": "GrowthBook, Inc.", "domain": "growthbook.io", "domainRegistered": "2020-05-19", "endpointOnVendorDomain": true, "terms": "https://www.growthbook.io/legal/customer-agreement", "privacy": "https://www.growthbook.io/legal/privacy-notice", "statusPage": "https://status.growthbook.io", "changelog": "https://github.com/growthbook/growthbook/releases", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The Customer Agreement (effective 19 June 2025) is between the customer and GrowthBook, Inc., with notices to 1950 W Corporate Way #34560, Anaheim, CA 92801, under California law.", "The Privacy Notice (effective 8 June 2026) covers the website and related services and names GrowthBook, Inc. at the same address. The Customer Agreement refers to it for Customer Data.", "The MCP server answers at mcp.growthbook.io and the REST API at api.growthbook.io. OAuth metadata names https://api.growthbook.io as issuer.", "www.growthbook.io/.well-known/security.txt and growthbook.io/.well-known/security.txt return 404 (re-read 1 November 2026). Reports go to a form on the disclosure page or to security@growthbook.io.", "RDAP for growthbook.io gives a registration date of 2020-05-19.", "The MCP server keeps its own changelog at https://github.com/growthbook/growthbook-mcp/blob/main/CHANGELOG.md." ], "score": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/growthbook.json", "live": { "slug": "growthbook", "probe": { "target": "https://mcp.growthbook.io/mcp", "method": "get", "lastAt": "2026-11-07T19:22:10.546299675Z", "lastOk": true, "lastStatus": 401, "lastMs": 368, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 267, "p95ms24h": 368, "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": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.growthbook.io", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:53.006708259Z" }, "versions": [ { "registry": "github", "name": "growthbook/growthbook", "version": "v5.2.0", "released": "2026-11-03", "seenAt": "2026-11-06T23:31:45.349646939Z" }, { "registry": "mcp-registry", "name": "io.github.growthbook/growthbook-mcp", "version": "2.2.0", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "@growthbook/growthbook", "version": "2.0.0", "seenAt": "2026-11-06T23:31:43.632815176Z" }, { "registry": "npm", "name": "@growthbook/mcp", "version": "2.2.0", "seenAt": "2026-11-06T23:31:42.874342993Z" }, { "registry": "pypi", "name": "growthbook", "version": "4.0.0", "released": "2026-11-02", "seenAt": "2026-11-06T23:31:45.155880521Z" } ], "githubStars": 8572, "npmWeekly": 9185, "pypiWeekly": 479785, "securityTxt": { "url": "https://growthbook.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:40.20454516Z" }, "llmsTxt": { "url": "https://docs.growthbook.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:39.975912104Z" }, "domain": { "domain": "growthbook.io", "checkedAt": "2026-11-01T14:23:41.368538454Z" }, "pages": [ { "url": "https://www.growthbook.io/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:29:29.272041513Z", "changedAt": "2026-11-04T08:40:45.015836681Z", "fingerprint": "18a31fd99466" }, { "url": "https://www.growthbook.io/legal/privacy-notice", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:29:27.3205356Z", "changedAt": "2026-11-06T13:50:11.648366307Z", "fingerprint": "2862dd2e25f5" }, { "url": "https://www.growthbook.io/legal/customer-agreement", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:29:25.188738505Z", "changedAt": "2026-11-04T08:40:40.81521479Z", "fingerprint": "84ab8480f2bd" } ], "mcpTools": { "url": "https://mcp.growthbook.io/mcp", "checkedAt": "2026-11-07T01:45:18.456947997Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:45:18.456947997Z" }, "github": { "repo": "growthbook/growthbook", "checkedAt": "2026-11-02T08:53:22.52476929Z", "stars": 8556, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T08:46:13Z", "openIssues": 524, "openPRs": 356, "issuesOpened90d": 59, "issuesClosed90d": 158, "prsMerged90d": 662, "ci": { "branch": "main", "runs": 50, "success": 49, "failure": 1, "other": 0, "latest": "success", "latestAt": "2026-10-30T21:20:54Z" }, "advisories": [ { "ghsa": "GHSA-c4m3-8cgx-p88g", "severity": "critical", "published": "2026-08-19T19:38:41Z" }, { "ghsa": "GHSA-j24q-55xh-wm4r", "cve": "CVE-2022-36065", "severity": "high", "published": "2022-08-30T17:05:17Z" } ], "replies": { "sampled": 25, "unanswered": 17, "medianDays": 0.6 } }, "updatedAt": "2026-11-07T19:22:10.546299675Z" } }, "answer": "GrowthBook scores 68.6 (B) on agent readiness against Mostly Good Metrics's 41.7 (E), and leads in every scored category.", "b": { "slug": "mostly-good-metrics", "name": "Mostly Good Metrics", "vendor": "Mostly Good Metrics", "vendorUrl": "https://mostlygoodmetrics.com", "kind": "http-api", "category": "product-analytics", "summary": "Mostly Good Metrics is a product analytics service in public beta for indie developers and small teams. Apps send events through five SDKs or an HTTP API, and agents query funnels, retention and experiments through a hosted MCP server.", "url": "https://www.anchorterminal.com/tools/mostly-good-metrics", "markdownUrl": "https://www.anchorterminal.com/tools/mostly-good-metrics.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/mostly-good-metrics.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/mostly-good-metrics.json", "dns": "mostly-good-metrics.grade.anchorterminal.com", "repo": "https://github.com/Mostly-Good-Metrics", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://app.mostlygoodmetrics.com/mcp", "packages": [ { "registry": "npm", "name": "@mostly-good-metrics/javascript" }, { "registry": "npm", "name": "@mostly-good-metrics/react-native" } ], "auth": "mixed", "authNotes": "The MCP server and the `mgm` CLI use browser OAuth 2.0 with PKCE (S256) and dynamic client registration; the advertised scopes are mcp:tools plus support and newsletter scopes. Event ingestion uses a project API key as a Bearer token, which can be pinned to web origins, Apple bundle IDs or Android package names. Keys are created in the dashboard, the CLI or through MCP tools.", "pricing": "freemium", "pricingNotes": "Free plan at $0 with 50,000 to 100,000 events a month and no card. Starter $9 a month ($90 a year) for 500,000 events and Pro $29 a month ($290 a year) for 5,000,000, both quoted as lifetime beta prices against $12 and $49. Enterprise has unlimited ingestion.", "priceSummary": "$9 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or on the pricing section of the home page (checked 2026-11-06).", "endpoints": [] }, "toolCount": 53, "popularity": { "githubStars": null, "npmWeekly": 81, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.mostlygoodmetrics.com", "capabilities": [ "analytics.query", "analytics.funnels", "analytics.events", "analytics.experiments" ], "tags": [ "hosted", "mcp", "remote-mcp", "oauth", "free-tier", "no-card", "beta", "closed-source", "typescript", "cli" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 41.7, "grade": "E", "agentReady": false, "rank": 1295, "ranked": true, "rankOf": 1510, "categoryRank": 18, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 49, "maintenance": 74, "payments": 30, "reliability": 29, "schema": 49, "security": 33, "transparency": 45 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-06" }, "negative": 0, "verdict": "Mostly Good Metrics lets an agent run ad-hoc funnels, retention and up to ten metric queries per call through a hosted MCP server with OAuth, at prices from $0. It is a public beta built by one developer, with no status page, no named legal entity and no security policy found.", "bestFor": "Indie and small-team apps that want simple funnels and retention an agent can query.", "strengths": [ "Hosted MCP server with OAuth, PKCE and dynamic client registration; no API key to copy", "execute_funnel, execute_retention and execute_query accept inline definitions without saving anything", "query_metrics runs 1 to 10 aggregate queries in one call with per-item results", "Free plan with no card, and paid plans from $9 a month", "Ingestion keys can be pinned to web origins and app bundle IDs" ], "weaknesses": [ "Public beta run by one developer, with no named legal entity in the terms", "No status page, SLA, security.txt or disclosure policy found", "53 MCP tools load at once and one scope grants all of them, including deletes and key revocation", "No OpenAPI file or llms.txt", "The CLI is installed from source because it isn't on npm yet" ], "agentNotes": [ "Use query_metrics for several aggregate questions instead of repeated execute_query calls", "Pass inline definitions to execute_funnel and execute_retention rather than creating saved objects", "Confirm with the user before delete, revoke_api_key or stop_experiment calls, since the server doesn't ask", "Start a fresh agent session after connecting, since a running client may not reload the tool list", "On 429 from ingestion, wait for Retry-After before resending events" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 41.7 } ], "editorialScores": { "ergonomics": 49, "maintenance": 74, "payments": 30, "reliability": 29, "schema": 49, "security": 33, "transparency": 51 }, "provenanceScore": 39, "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": { "claudeCode": "claude mcp add --transport http mgm https://app.mostlygoodmetrics.com/mcp", "config": { "mcpServers": { "mgm": { "url": "https://app.mostlygoodmetrics.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/analytics.query", "tool": "https://letme.dev/mostly-good-metrics" }, "area": "business", "unitPrices": [ { "item": "Starter plan", "unit": "month", "usd": 9, "note": "500,000 events a month, lifetime beta price" }, { "item": "Pro plan", "unit": "month", "usd": 29, "note": "5,000,000 events a month, lifetime beta price" } ], "provenance": { "legalEntity": "", "domain": "mostlygoodmetrics.com", "domainRegistered": "2025-12-05", "endpointOnVendorDomain": true, "terms": "https://mostlygoodmetrics.com/terms", "privacy": "https://mostlygoodmetrics.com/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The terms and privacy policy, both last updated December 2025, name only Mostly Good Metrics and give no legal entity, address or governing law.", "mostlygoodmetrics.com/robots.txt has every rule commented out; docs.mostlygoodmetrics.com has no robots.txt.", "/.well-known/security.txt returned 404 and no status page was found.", "RDAP gives mostlygoodmetrics.com a registration date of 5 December 2025." ], "score": 39 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/mostly-good-metrics.json", "live": { "slug": "mostly-good-metrics", "probe": { "target": "https://app.mostlygoodmetrics.com/mcp", "method": "get", "lastAt": "2026-11-07T19:22:20.651338144Z", "lastOk": true, "lastStatus": 401, "lastMs": 138, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 167, "p95ms24h": 298, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "versions": [ { "registry": "npm", "name": "@mostly-good-metrics/javascript", "version": "0.13.1", "seenAt": "2026-11-06T23:47:33.682933227Z" }, { "registry": "npm", "name": "@mostly-good-metrics/react-native", "version": "0.9.1", "seenAt": "2026-11-06T23:47:34.884784704Z" } ], "npmWeekly": 81, "securityTxt": { "url": "https://mostlygoodmetrics.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:38.90553607Z" }, "pages": [ { "url": "https://mostlygoodmetrics.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:14:39.017388202Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "f43e747ad9a3" }, { "url": "https://mostlygoodmetrics.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:14:41.227658165Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "99ed64144abf" } ], "mcpTools": { "url": "https://app.mostlygoodmetrics.com/mcp", "checkedAt": "2026-11-07T01:46:16.716952564Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:46:16.716952564Z" }, "updatedAt": "2026-11-07T19:22:20.651338144Z" } }, "edges": [ { "by": 57, "category": "reliability", "leads": "growthbook", "name": "Reliability", "reasons": { "a": "Graded on GrowthBook Cloud with the hosted lines. Instatus page at status.growthbook.io with three components (GrowthBook Cloud App, Api, CDN) and a notice history (20). No notices from August to October 2026, and the newest entry in the feed, re-read on 1 November, is still dated 21 August 2025. The MCP server is not a listed component, and the 2.2.0 changelog fixes intermittent 502s in HTTP mode that were not posted, so 25 of 30. API keys are limited to 60 requests a minute on Cloud, re-read in the API introduction and the OpenAPI spec on 1 November; since 19 October self-hosted servers can set per-key limits (15). The docs say only to try again later on 429. The server source sends standard RateLimit headers and the MCP server waits for `RateLimit-Reset` and retries three times, but no backoff guidance or idempotency keys were found in the docs (8 of 15). The pricing page lists a 99.99 per cent uptime SLA on Enterprise, re-read on 1 November. The SLA document itself was not found in public (8 of 10). The REST API's /v1 is described as stable and the MCP docs carry no beta label (10). 20+25+15+8+8+10 = 86.", "b": "Graded on the hosted service with the hosted lines. No status page was found (0) and no incident history could be read (5). Ingestion limits are documented per plan (1,000 to 100,000 events a minute and 10,000 to 1,000,000 an hour), but no limit for MCP or query calls was found (12 of 15). 429 with Retry-After in the header and body, and the SDKs queue events and back off. No idempotency or safe-retry guidance for writes (12 of 15). No SLA (0). The press kit calls the product a public beta (0). 0+5+12+12+0+0 = 29." }, "scores": { "a": 86, "b": 29 } }, { "by": 43, "category": "security", "leads": "growthbook", "name": "Security \u0026 auth", "reasons": { "a": "OAuth with PKCE, dynamic client registration, refresh tokens and a revocation endpoint for the hosted MCP server. Since October the consent page asks what the connection may do, Read only, Human-in-the-Loop, Full access or a custom base role limited by project or environment, so a token no longer has to carry the user's full permissions. Secret Keys take any built-in or custom role with per-project overrides, environment limits and expiry, Personal Access Tokens can be scoped below their user (7 October), and since 21 October keys and tokens rotate in place with a grace period for the old secret. Secrets travel in headers only (30). A Read Only option, an endpoint with the API tools alone, and read and write tools with annotations. Since 16 October Human-in-the-Loop holds risky or destructive REST writes, including those from the hosted MCP endpoint, until a person confirms them on a linked page, and each decision goes to the audit log. Human-in-the-Loop is an Enterprise preset, and on a plan with only the admin role, which includes Free, Full access is the only option (18 of 20). No guidance on prompt injection was found, though the tools return names and descriptions that people wrote (3 of 15). Audit logging, with export, is on Enterprise only. Personal tokens attribute actions to a user, Secret Keys can name the member behind a request with `X-GrowthBook-Requested-By` (13 October), and the MCP server labels its API calls with `X-GB-MCP-*` headers (10 of 15). SOC 2 Type II, a disclosure process with a form and SECURITY.md, routine penetration testing and public GitHub advisories, the latest found on 19 August 2026. Rewards are merchandise only and www.growthbook.io/.well-known/security.txt still answered 404 on 1 November (15 of 20). 30+18+3+10+15 = 76. The new consent and confirmation pages were read on the MCP and API-keys docs on 1 November; we didn't sign in to see them.", "b": "OAuth 2.0 with PKCE, dynamic client registration and a revocation endpoint for MCP and the CLI; project ingest keys in a Bearer header that can be pinned to origins or app IDs. The only tool scope advertised is mcp:tools, so a connection gets every tool the user can use (24 of 30). Restricted keys and a confirmation step for unrestricted keys in the CLI; no read-only MCP mode or approval for deletes was found (6 of 20). Event properties come from apps and end users and reach the agent, and no prompt-injection guidance was found (3 of 15). No audit log was found (0). No security.txt, disclosure policy or certification was found (0). 24+6+3+0+0 = 33." }, "scores": { "a": 76, "b": 33 } }, { "by": 30, "category": "transparency", "leads": "growthbook", "name": "Transparency \u0026 trust", "reasons": { "a": "The core and the MCP server are MIT. Three enterprise directories in the main repository are under GrowthBook's enterprise licence and are part of what Cloud runs (25 of 30). A Customer Agreement, a Privacy Notice of 8 June 2026 and a DPA of 19 June 2025 are published. The agreement grants GrowthBook an unrestricted right to use Customer Data, including to train its AI algorithms, then limits personal information to performing the Services. The Privacy Notice gives no retention periods, and the docs say only aggregate results are stored. We did not read the DPA, which is a download (16 of 30). Legacy v1 routes and 34 operations are marked deprecated with no removal dates, and no deprecation policy was found. The MCP changelog gives migration steps (8 of 20). The sub-processor list of 11 May 2026 names seven providers with locations, mostly in the United States. Notice of new ones is promised only as far as the law requires (17 of 20). 25+16+8+17 = 66. The legal documents are per the 8 October check, not re-read on 1 November.", "b": "The service is closed; the SDKs and CLI are MIT. Terms of December 2025 with no legal entity named (18 of 30). The privacy policy and terms agree on raw-event retention for the subscription's life and deletion within 14 days of account deletion; the about page says data is not used to train models. No DPA was found (18 of 30). The legacy X-MGM-Key header is still supported, and no deprecation policy was found (3 of 20). The terms name eight sub-processors with their purpose, without data locations (12 of 20). 18+18+3+12 = 51." }, "scores": { "a": 75, "b": 45 } }, { "by": 27, "category": "schema", "leads": "growthbook", "name": "Schema \u0026 documentation", "reasons": { "a": "Public OpenAPI 3.1 spec, version 5.1.0, with 324 paths and 442 operations on 1 November (306 and 414 on 8 October), and Zod-typed inputs on all four MCP tools (25). llms.txt and a Markdown copy of each docs page (10). 441 of 442 operations have a summary and 205 have a description. The MCP tool descriptions say when to use each tool, and the bundled skills carry the workflows (13 of 20). The spec has 1,445 enums and marks required fields, but `growthbook_api_write` takes the path as a string and the body as a JSON string, and the docs still say the API tools do not validate payloads (9 of 15). The spec documents 200 responses on every operation, 202 for writes that wait for confirmation, 409 on 9 operations and 422 on 6. The introduction lists eight status codes and a `message` body (6 of 15). Path versions /v1 and /v2, 34 operations marked deprecated, GitHub releases, and an MCP changelog with breaking changes called out (13 of 15). 25+10+13+9+6+13 = 76.", "b": "No OpenAPI file was found. The docs say every MCP tool describes its own parameters, and the query definition object is documented in full; we didn't open an MCP session to read the schemas (12 of 25). No llms.txt (404) and no Markdown pages served for agents (0). Each tool area is documented with examples, and the docs say when to use query_metrics instead of repeated execute_query calls (10 of 20). The query definition lists metrics, dimensions, date ranges and filter operators (9 of 15). The ingestion API documents its error body and status codes, and query_metrics reports per-item errors (11 of 15). /v1 and /api/v2 paths and dated SDK tags, but no product changelog (7 of 15). 12+0+10+9+11+7 = 49." }, "scores": { "a": 76, "b": 49 } }, { "by": 27, "category": "ergonomics", "leads": "growthbook", "name": "Agent ergonomics", "reasons": { "a": "Four compact MCP tools, with skills loaded on demand and a /mcp/api endpoint that drops the skill tools (25). `limit` (default 10, maximum 100) and `offset` on 40 list operations, with filters by project, data source and status. No field selection was found, and the API tools return the raw response body (15 of 20). Errors are a status code and a `message` with no machine code. 422 marks a soft warning that can be resubmitted with `ignoreWarnings`, and the MCP server adds recovery hints for 401, 403, 404 and 429 (13 of 20). All four tools carry readOnlyHint and destructiveHint, and reads and writes are separate tools. Every write is marked destructive, and no idempotency keys were found (13 of 20). The API tools need one to three parameters. The SDKs cover flag evaluation in many languages, not the REST API (10 of 15). 25+15+13+13+10 = 76. Not re-read on 1 November beyond the MCP page and the spec, which still support each line.", "b": "53 tools, more than 30 (5). We added 3 because Goals and Alerts tools load only where enabled and query_metrics batches up to 10 queries (8 of 25). Date ranges, grouping and filters on queries; no documented page or limit parameters for lists (12 of 20). JSON errors with a message, and per-item status in batch results (13 of 20). Annotations weren't readable without a session, the tool list includes deletes and key revocation, and no idempotency keys were found (4 of 20). Five client SDKs and a CLI with `--json` output (12 of 15). 8+12+13+4+12 = 49." }, "scores": { "a": 76, "b": 49 } }, { "by": 15, "category": "maintenance", "leads": "growthbook", "name": "Maintenance \u0026 community", "reasons": { "a": "MCP server 2.2.0 is dated 5 October 2026 and published to the registry on 6 October, GrowthBook 5.1.0 was tagged on 21 September 2026, and the main repository's commit releasing the JavaScript and React SDKs 2.0.0 landed on 30 October (npm not readable from here) (30). In the 90 days from 3 August, GrowthBook 5.0.1 (19 August) and 5.1.0, MCP 2.1.0 (10 August) and 2.2.0, and the SDK 2.0.0 release commit (20). The main repository's 200 newest commits run from 5 to 30 October 2026, and there is a community Slack. We did not read how quickly issues are answered (15 of 25). `io.github.growthbook/growthbook-mcp` is in the official MCP registry at 2.2.0, published 6 October 2026 and still latest on 1 November (15). The MCP repository runs CI on Node 22 and 26 and took dependency updates on 8 and 27 October 2026, both still unreleased. The package states Node 18 or later, which CI does not test (9 of 10). 30+20+15+15+9 = 89.", "b": "CLI v0.1.4 was tagged on 16 October 2026 (30). The JavaScript SDK released 0.12.0, 0.13.0 and 0.13.1 between 5 September and 2 October, and the Swift SDK 1.0.0 and 1.0.1 on 2 October (20). A closed service with no public changelog, support by email and GitHub repositories for the SDKs; issue activity wasn't read because the GitHub API refused us for its rate limit (6 of 25). Not in the official MCP registry; official SDKs in five languages are current (10 of 15). CI workflows on the SDK and CLI repositories (8 of 10). 30+20+6+10+8 = 74." }, "scores": { "a": 89, "b": 74 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "GrowthBook, Inc.", "b": "Mostly Good Metrics", "name": "Vendor" }, { "a": "https://mcp.growthbook.io/mcp", "b": "https://app.mostlygoodmetrics.com/mcp", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, stdio", "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": "MIT for the core and for the MCP server. Three enterprise directories in the main repository are under GrowthBook's enterprise licence. GrowthBook Cloud is a hosted service under the Customer Agreement", "b": "none", "name": "Licence" }, { "a": "4", "b": "53", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "io.github.growthbook/growthbook-mcp", "b": "not listed", "name": "MCP registry" }, { "a": "2026-10-06", "b": "2026-10-16", "name": "Last release" }, { "a": "2025-06-19", "b": "2025-12-01", "name": "Terms last updated" }, { "a": "2026-06-08", "b": "2025-12-01", "name": "Privacy policy last updated" }, { "a": "yes", "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": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "8.5k stars, 1.3M npm/wk, 433k PyPI/wk", "b": "81 npm/wk", "name": "Popularity" }, { "a": "3.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "GrowthBook scores 68.6 (B) on agent readiness against Mostly Good Metrics's 41.7 (E), and leads in every scored category.", "question": "Which is better for AI agents, GrowthBook or Mostly Good Metrics?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do GrowthBook and Mostly Good Metrics need an API key?" }, { "answer": "Yes. GrowthBook has a hosted endpoint at https://mcp.growthbook.io/mcp and Mostly Good Metrics at https://app.mostlygoodmetrics.com/mcp.", "question": "Can an agent call GrowthBook and Mostly Good Metrics without installing anything?" }, { "answer": "GrowthBook is open source (MIT for the core and for the MCP server. Three enterprise directories in the main repository are under GrowthBook's enterprise licence. GrowthBook Cloud is a hosted service under the Customer Agreement). No open-source release is listed for Mostly Good Metrics.", "question": "Are GrowthBook and Mostly Good Metrics open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 86 against 29", "Schema \u0026 documentation, 76 against 49", "Agent ergonomics, 76 against 49", "Security \u0026 auth, 76 against 33", "Payments \u0026 pricing, 40 against 30", "Maintenance \u0026 community, 89 against 74", "Transparency \u0026 trust, 75 against 45" ], "also": [ "Runs on your own machine", "Open source" ], "goodFor": "Teams that want flags and experiments analysed against their own warehouse, with an open-source core and a self-hosted option.", "slug": "growthbook", "watchFor": "The API tools take a path and a JSON string and don't validate payloads, so correct calls depend on the bundled skills" }, { "aheadOn": null, "also": [ "No incidents deducted, where GrowthBook loses 6 points for them" ], "goodFor": "Indie and small-team apps that want simple funnels and retention an agent can query.", "slug": "mostly-good-metrics", "watchFor": "Public beta run by one developer, with no named legal entity in the terms" } ], "history": { "growthbook": [ { "causes": [ "product", "event" ], "date": "2026-11-01", "delta": -1.5, "from": 70.1, "fromGrade": "BB", "to": 68.6, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0, "from": 70.1, "fromGrade": "BB", "to": 70.1, "toGrade": "BB" } ], "mostly-good-metrics": null }, "job": { "capability": "analytics.experiments", "name": "Feature flags and experiments" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amplitude-vs-growthbook.json", "title": "Amplitude vs GrowthBook", "url": "https://www.anchorterminal.com/compare/amplitude-vs-growthbook" }, { "json": "https://www.anchorterminal.com/compare/amplitude-vs-mostly-good-metrics.json", "title": "Amplitude vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/amplitude-vs-mostly-good-metrics" }, { "json": "https://www.anchorterminal.com/compare/basedash-mcp-vs-mostly-good-metrics.json", "title": "Basedash MCP vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/basedash-mcp-vs-mostly-good-metrics" }, { "json": "https://www.anchorterminal.com/compare/countly-vs-growthbook.json", "title": "Countly vs GrowthBook", "url": "https://www.anchorterminal.com/compare/countly-vs-growthbook" }, { "json": "https://www.anchorterminal.com/compare/countly-vs-mostly-good-metrics.json", "title": "Countly vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/countly-vs-mostly-good-metrics" }, { "json": "https://www.anchorterminal.com/compare/fullstory-vs-growthbook.json", "title": "Fullstory vs GrowthBook", "url": "https://www.anchorterminal.com/compare/fullstory-vs-growthbook" }, { "json": "https://www.anchorterminal.com/compare/fullstory-vs-mostly-good-metrics.json", "title": "Fullstory vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/fullstory-vs-mostly-good-metrics" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-openpanel.json", "title": "GrowthBook vs OpenPanel", "url": "https://www.anchorterminal.com/compare/growthbook-vs-openpanel" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-pendo.json", "title": "GrowthBook vs Pendo", "url": "https://www.anchorterminal.com/compare/growthbook-vs-pendo" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-userpilot.json", "title": "GrowthBook vs Userpilot", "url": "https://www.anchorterminal.com/compare/growthbook-vs-userpilot" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-woopra.json", "title": "GrowthBook vs Woopra", "url": "https://www.anchorterminal.com/compare/growthbook-vs-woopra" }, { "json": "https://www.anchorterminal.com/compare/matomo-vs-mostly-good-metrics.json", "title": "Matomo vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/matomo-vs-mostly-good-metrics" }, { "json": "https://www.anchorterminal.com/compare/mixpanel-vs-mostly-good-metrics.json", "title": "Mixpanel vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/mixpanel-vs-mostly-good-metrics" }, { "json": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-openpanel.json", "title": "Mostly Good Metrics vs OpenPanel", "url": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-openpanel" }, { "json": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-optimizely.json", "title": "Mostly Good Metrics vs Optimizely Experimentation", "url": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-optimizely" }, { "json": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-pendo.json", "title": "Mostly Good Metrics vs Pendo", "url": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-pendo" }, { "json": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-posthog.json", "title": "Mostly Good Metrics vs PostHog", "url": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-posthog" }, { "json": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-rudderstack-mcp.json", "title": "Mostly Good Metrics vs RudderStack MCP", "url": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-rudderstack-mcp" }, { "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/mostly-good-metrics-vs-userpilot.json", "title": "Mostly Good Metrics vs Userpilot", "url": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-userpilot" }, { "json": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-woopra.json", "title": "Mostly Good Metrics vs Woopra", "url": "https://www.anchorterminal.com/compare/mostly-good-metrics-vs-woopra" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-heap.json", "title": "GrowthBook vs Heap", "url": "https://www.anchorterminal.com/compare/growthbook-vs-heap" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-rudderstack-mcp.json", "title": "GrowthBook vs RudderStack MCP", "url": "https://www.anchorterminal.com/compare/growthbook-vs-rudderstack-mcp" }, { "json": "https://www.anchorterminal.com/compare/heap-vs-mostly-good-metrics.json", "title": "Heap vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/heap-vs-mostly-good-metrics" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-growthbook.json", "title": "Flagsmith vs GrowthBook", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-growthbook" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-mostly-good-metrics.json", "title": "Flagsmith vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-mostly-good-metrics" }, { "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-launchdarkly.json", "title": "GrowthBook vs LaunchDarkly", "url": "https://www.anchorterminal.com/compare/growthbook-vs-launchdarkly" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-matomo.json", "title": "GrowthBook vs Matomo", "url": "https://www.anchorterminal.com/compare/growthbook-vs-matomo" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-mixpanel.json", "title": "GrowthBook vs Mixpanel", "url": "https://www.anchorterminal.com/compare/growthbook-vs-mixpanel" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-optimizely.json", "title": "GrowthBook vs Optimizely Experimentation", "url": "https://www.anchorterminal.com/compare/growthbook-vs-optimizely" }, { "json": "https://www.anchorterminal.com/compare/growthbook-vs-posthog.json", "title": "GrowthBook vs PostHog", "url": "https://www.anchorterminal.com/compare/growthbook-vs-posthog" }, { "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-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/launchdarkly-vs-mostly-good-metrics.json", "title": "LaunchDarkly vs Mostly Good Metrics", "url": "https://www.anchorterminal.com/compare/launchdarkly-vs-mostly-good-metrics" } ], "panel": null, "scores": [ { "by": 57, "edge": "growthbook", "growthbook": 86, "key": "reliability", "mostly-good-metrics": 29, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 27, "edge": "growthbook", "growthbook": 76, "key": "schema", "mostly-good-metrics": 49, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 27, "edge": "growthbook", "growthbook": 76, "key": "ergonomics", "mostly-good-metrics": 49, "name": "Agent ergonomics", "weight": 13 }, { "by": 43, "edge": "growthbook", "growthbook": 76, "key": "security", "mostly-good-metrics": 33, "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "edge": "growthbook", "growthbook": 40, "key": "payments", "mostly-good-metrics": 30, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 15, "edge": "growthbook", "growthbook": 89, "key": "maintenance", "mostly-good-metrics": 74, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 30, "edge": "growthbook", "growthbook": 75, "key": "transparency", "mostly-good-metrics": 45, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "GrowthBook scores 68.6 (B) on agent readiness against Mostly Good Metrics's 41.7 (E), and leads in every scored category. Both do feature flags and experiments.", "tasks": null, "tutorials": [], "verdicts": { "growthbook": "GrowthBook Cloud's MCP server has four annotated tools, OAuth whose consent page can grant read-only or confirmation-gated access, and a 442-operation OpenAPI spec behind it. The free plan needs no card. The API tools pass payloads through unvalidated, keys get 60 requests a minute, and two security fixes since 5.1.0 are unreleased.", "mostly-good-metrics": "Mostly Good Metrics lets an agent run ad-hoc funnels, retention and up to ten metric queries per call through a hosted MCP server with OAuth, at prices from $0. It is a public beta built by one developer, with no status page, no named legal entity and no security policy found." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/growthbook-vs-mostly-good-metrics", "json": "https://www.anchorterminal.com/compare/growthbook-vs-mostly-good-metrics.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/growthbook-vs-mostly-good-metrics.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/growthbook-vs-mostly-good-metrics.min.md" }, "markdown": "GrowthBook scores 68.6 (B) on agent readiness against Mostly Good Metrics's 41.7 (E), and leads in every scored category. Both do feature flags and experiments.\n\n- GrowthBook: grade B, 68.6/100, rank #279 of 1510. Markdown https://www.anchorterminal.com/tools/growthbook.md · JSON https://www.anchorterminal.com/api/v1/tools/growthbook.json\n- Mostly Good Metrics: grade E, 41.7/100, rank #1295 of 1510. Markdown https://www.anchorterminal.com/tools/mostly-good-metrics.md · JSON https://www.anchorterminal.com/api/v1/tools/mostly-good-metrics.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### GrowthBook (B)\n\nGood for: Teams that want flags and experiments analysed against their own warehouse, with an open-source core and a self-hosted option.\n\nAhead on:\n- Reliability, 86 against 29\n- Schema \u0026 documentation, 76 against 49\n- Agent ergonomics, 76 against 49\n- Security \u0026 auth, 76 against 33\n- Payments \u0026 pricing, 40 against 30\n- Maintenance \u0026 community, 89 against 74\n- Transparency \u0026 trust, 75 against 45\n\nAlso in its favour:\n- Runs on your own machine\n- Open source\n\nWatch for: The API tools take a path and a JSON string and don't validate payloads, so correct calls depend on the bundled skills\n\n### Mostly Good Metrics (E)\n\nGood for: Indie and small-team apps that want simple funnels and retention an agent can query.\n\nAlso in its favour:\n- No incidents deducted, where GrowthBook loses 6 points for them\n\nWatch for: Public beta run by one developer, with no named legal entity in the terms\n\n\n## Why the edge\n\n### Reliability: GrowthBook +57\n\n- GrowthBook (86): Graded on GrowthBook Cloud with the hosted lines. Instatus page at status.growthbook.io with three components (GrowthBook Cloud App, Api, CDN) and a notice history (20). No notices from August to October 2026, and the newest entry in the feed, re-read on 1 November, is still dated 21 August 2025. The MCP server is not a listed component, and the 2.2.0 changelog fixes intermittent 502s in HTTP mode that were not posted, so 25 of 30. API keys are limited to 60 requests a minute on Cloud, re-read in the API introduction and the OpenAPI spec on 1 November; since 19 October self-hosted servers can set per-key limits (15). The docs say only to try again later on 429. The server source sends standard RateLimit headers and the MCP server waits for `RateLimit-Reset` and retries three times, but no backoff guidance or idempotency keys were found in the docs (8 of 15). The pricing page lists a 99.99 per cent uptime SLA on Enterprise, re-read on 1 November. The SLA document itself was not found in public (8 of 10). The REST API's /v1 is described as stable and the MCP docs carry no beta label (10). 20+25+15+8+8+10 = 86.\n- Mostly Good Metrics (29): Graded on the hosted service with the hosted lines. No status page was found (0) and no incident history could be read (5). Ingestion limits are documented per plan (1,000 to 100,000 events a minute and 10,000 to 1,000,000 an hour), but no limit for MCP or query calls was found (12 of 15). 429 with Retry-After in the header and body, and the SDKs queue events and back off. No idempotency or safe-retry guidance for writes (12 of 15). No SLA (0). The press kit calls the product a public beta (0). 0+5+12+12+0+0 = 29.\n\n### Security \u0026 auth: GrowthBook +43\n\n- GrowthBook (76): OAuth with PKCE, dynamic client registration, refresh tokens and a revocation endpoint for the hosted MCP server. Since October the consent page asks what the connection may do, Read only, Human-in-the-Loop, Full access or a custom base role limited by project or environment, so a token no longer has to carry the user's full permissions. Secret Keys take any built-in or custom role with per-project overrides, environment limits and expiry, Personal Access Tokens can be scoped below their user (7 October), and since 21 October keys and tokens rotate in place with a grace period for the old secret. Secrets travel in headers only (30). A Read Only option, an endpoint with the API tools alone, and read and write tools with annotations. Since 16 October Human-in-the-Loop holds risky or destructive REST writes, including those from the hosted MCP endpoint, until a person confirms them on a linked page, and each decision goes to the audit log. Human-in-the-Loop is an Enterprise preset, and on a plan with only the admin role, which includes Free, Full access is the only option (18 of 20). No guidance on prompt injection was found, though the tools return names and descriptions that people wrote (3 of 15). Audit logging, with export, is on Enterprise only. Personal tokens attribute actions to a user, Secret Keys can name the member behind a request with `X-GrowthBook-Requested-By` (13 October), and the MCP server labels its API calls with `X-GB-MCP-*` headers (10 of 15). SOC 2 Type II, a disclosure process with a form and SECURITY.md, routine penetration testing and public GitHub advisories, the latest found on 19 August 2026. Rewards are merchandise only and www.growthbook.io/.well-known/security.txt still answered 404 on 1 November (15 of 20). 30+18+3+10+15 = 76. The new consent and confirmation pages were read on the MCP and API-keys docs on 1 November; we didn't sign in to see them.\n- Mostly Good Metrics (33): OAuth 2.0 with PKCE, dynamic client registration and a revocation endpoint for MCP and the CLI; project ingest keys in a Bearer header that can be pinned to origins or app IDs. The only tool scope advertised is mcp:tools, so a connection gets every tool the user can use (24 of 30). Restricted keys and a confirmation step for unrestricted keys in the CLI; no read-only MCP mode or approval for deletes was found (6 of 20). Event properties come from apps and end users and reach the agent, and no prompt-injection guidance was found (3 of 15). No audit log was found (0). No security.txt, disclosure policy or certification was found (0). 24+6+3+0+0 = 33.\n\n### Transparency \u0026 trust: GrowthBook +30\n\n- GrowthBook (75): The core and the MCP server are MIT. Three enterprise directories in the main repository are under GrowthBook's enterprise licence and are part of what Cloud runs (25 of 30). A Customer Agreement, a Privacy Notice of 8 June 2026 and a DPA of 19 June 2025 are published. The agreement grants GrowthBook an unrestricted right to use Customer Data, including to train its AI algorithms, then limits personal information to performing the Services. The Privacy Notice gives no retention periods, and the docs say only aggregate results are stored. We did not read the DPA, which is a download (16 of 30). Legacy v1 routes and 34 operations are marked deprecated with no removal dates, and no deprecation policy was found. The MCP changelog gives migration steps (8 of 20). The sub-processor list of 11 May 2026 names seven providers with locations, mostly in the United States. Notice of new ones is promised only as far as the law requires (17 of 20). 25+16+8+17 = 66. The legal documents are per the 8 October check, not re-read on 1 November.\n- Mostly Good Metrics (45): The service is closed; the SDKs and CLI are MIT. Terms of December 2025 with no legal entity named (18 of 30). The privacy policy and terms agree on raw-event retention for the subscription's life and deletion within 14 days of account deletion; the about page says data is not used to train models. No DPA was found (18 of 30). The legacy X-MGM-Key header is still supported, and no deprecation policy was found (3 of 20). The terms name eight sub-processors with their purpose, without data locations (12 of 20). 18+18+3+12 = 51.\n\n### Schema \u0026 documentation: GrowthBook +27\n\n- GrowthBook (76): Public OpenAPI 3.1 spec, version 5.1.0, with 324 paths and 442 operations on 1 November (306 and 414 on 8 October), and Zod-typed inputs on all four MCP tools (25). llms.txt and a Markdown copy of each docs page (10). 441 of 442 operations have a summary and 205 have a description. The MCP tool descriptions say when to use each tool, and the bundled skills carry the workflows (13 of 20). The spec has 1,445 enums and marks required fields, but `growthbook_api_write` takes the path as a string and the body as a JSON string, and the docs still say the API tools do not validate payloads (9 of 15). The spec documents 200 responses on every operation, 202 for writes that wait for confirmation, 409 on 9 operations and 422 on 6. The introduction lists eight status codes and a `message` body (6 of 15). Path versions /v1 and /v2, 34 operations marked deprecated, GitHub releases, and an MCP changelog with breaking changes called out (13 of 15). 25+10+13+9+6+13 = 76.\n- Mostly Good Metrics (49): No OpenAPI file was found. The docs say every MCP tool describes its own parameters, and the query definition object is documented in full; we didn't open an MCP session to read the schemas (12 of 25). No llms.txt (404) and no Markdown pages served for agents (0). Each tool area is documented with examples, and the docs say when to use query_metrics instead of repeated execute_query calls (10 of 20). The query definition lists metrics, dimensions, date ranges and filter operators (9 of 15). The ingestion API documents its error body and status codes, and query_metrics reports per-item errors (11 of 15). /v1 and /api/v2 paths and dated SDK tags, but no product changelog (7 of 15). 12+0+10+9+11+7 = 49.\n\n### Agent ergonomics: GrowthBook +27\n\n- GrowthBook (76): Four compact MCP tools, with skills loaded on demand and a /mcp/api endpoint that drops the skill tools (25). `limit` (default 10, maximum 100) and `offset` on 40 list operations, with filters by project, data source and status. No field selection was found, and the API tools return the raw response body (15 of 20). Errors are a status code and a `message` with no machine code. 422 marks a soft warning that can be resubmitted with `ignoreWarnings`, and the MCP server adds recovery hints for 401, 403, 404 and 429 (13 of 20). All four tools carry readOnlyHint and destructiveHint, and reads and writes are separate tools. Every write is marked destructive, and no idempotency keys were found (13 of 20). The API tools need one to three parameters. The SDKs cover flag evaluation in many languages, not the REST API (10 of 15). 25+15+13+13+10 = 76. Not re-read on 1 November beyond the MCP page and the spec, which still support each line.\n- Mostly Good Metrics (49): 53 tools, more than 30 (5). We added 3 because Goals and Alerts tools load only where enabled and query_metrics batches up to 10 queries (8 of 25). Date ranges, grouping and filters on queries; no documented page or limit parameters for lists (12 of 20). JSON errors with a message, and per-item status in batch results (13 of 20). Annotations weren't readable without a session, the tool list includes deletes and key revocation, and no idempotency keys were found (4 of 20). Five client SDKs and a CLI with `--json` output (12 of 15). 8+12+13+4+12 = 49.\n\n### Maintenance \u0026 community: GrowthBook +15\n\n- GrowthBook (89): MCP server 2.2.0 is dated 5 October 2026 and published to the registry on 6 October, GrowthBook 5.1.0 was tagged on 21 September 2026, and the main repository's commit releasing the JavaScript and React SDKs 2.0.0 landed on 30 October (npm not readable from here) (30). In the 90 days from 3 August, GrowthBook 5.0.1 (19 August) and 5.1.0, MCP 2.1.0 (10 August) and 2.2.0, and the SDK 2.0.0 release commit (20). The main repository's 200 newest commits run from 5 to 30 October 2026, and there is a community Slack. We did not read how quickly issues are answered (15 of 25). `io.github.growthbook/growthbook-mcp` is in the official MCP registry at 2.2.0, published 6 October 2026 and still latest on 1 November (15). The MCP repository runs CI on Node 22 and 26 and took dependency updates on 8 and 27 October 2026, both still unreleased. The package states Node 18 or later, which CI does not test (9 of 10). 30+20+15+15+9 = 89.\n- Mostly Good Metrics (74): CLI v0.1.4 was tagged on 16 October 2026 (30). The JavaScript SDK released 0.12.0, 0.13.0 and 0.13.1 between 5 September and 2 October, and the Swift SDK 1.0.0 and 1.0.1 on 2 October (20). A closed service with no public changelog, support by email and GitHub repositories for the SDKs; issue activity wasn't read because the GitHub API refused us for its rate limit (6 of 25). Not in the official MCP registry; official SDKs in five languages are current (10 of 15). CI workflows on the SDK and CLI repositories (8 of 10). 30+20+6+10+8 = 74.\n\n## Score by category\n\n| Category | Weight | GrowthBook | Mostly Good Metrics | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 86 | 29 | GrowthBook +57 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 76 | 49 | GrowthBook +27 |\n| Agent ergonomics | 13% (16.2 this run) | 76 | 49 | GrowthBook +27 |\n| Security \u0026 auth | 14% (17.5 this run) | 76 | 33 | GrowthBook +43 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 30 | GrowthBook +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 89 | 74 | GrowthBook +15 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 75 | 45 | GrowthBook +30 |\n| Negative events | ≤15 | -6 | 0 | |\n| **Total** | | **68.6 · B** | **41.7 · E** | |\n\n## Facts side by side\n\n| Fact | GrowthBook | Mostly Good Metrics |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | GrowthBook, Inc. | Mostly Good Metrics |\n| Hosted endpoint | `https://mcp.growthbook.io/mcp` | `https://app.mostlygoodmetrics.com/mcp` |\n| Transports | HTTP, Streamable HTTP, stdio | HTTP, Streamable HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | MIT for the core and for the MCP server. Three enterprise directories in the main repository are under GrowthBook's enterprise licence. GrowthBook Cloud is a hosted service under the Customer Agreement | none |\n| Tools exposed | 4 | 53 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| MCP registry | `io.github.growthbook/growthbook-mcp` | not listed |\n| Last release | 2026-10-06 | 2026-10-16 |\n| Terms last updated | 2025-06-19 | 2025-12-01 |\n| Privacy policy last updated | 2026-06-08 | 2025-12-01 |\n| Customer content may train models | yes | 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 | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 8.5k stars, 1.3M npm/wk, 433k PyPI/wk | 81 npm/wk |\n| Agent reviews | 3.3/5 (4) | none |\n\n## How the scores have moved\n\n### GrowthBook\n\n- -1.5 on 1 November 2026 (BB to B): product, negative event\n- no change on 27 October 2026: checklist\n\n### Mostly Good Metrics\n\nNo score change since it was listed.\n\n## Verdicts\n\n**GrowthBook.** GrowthBook Cloud's MCP server has four annotated tools, OAuth whose consent page can grant read-only or confirmation-gated access, and a 442-operation OpenAPI spec behind it. The free plan needs no card. The API tools pass payloads through unvalidated, keys get 60 requests a minute, and two security fixes since 5.1.0 are unreleased.\n\n**Mostly Good Metrics.** Mostly Good Metrics lets an agent run ad-hoc funnels, retention and up to ten metric queries per call through a hosted MCP server with OAuth, at prices from $0. It is a public beta built by one developer, with no status page, no named legal entity and no security policy found.\n\n## Before you call either\n\n### GrowthBook\n\n1. Connect to https://mcp.growthbook.io/mcp and complete OAuth in a browser. Ask for Read only at consent unless the task needs writes\n2. Call `growthbook_list_skills` and `growthbook_read_skill` before writing. The API tools don't validate payloads, so use the paths the skill names\n3. Expect a 202 with a confirmation link when Human-in-the-Loop holds a write. Tell the user and wait; a held request expires after an hour\n4. Stay under 60 requests a minute per key. On 429 wait for the `RateLimit-Reset` seconds before retrying\n5. List calls return 10 items by default. Pass `limit` up to 100 and `offset` to page\n\n### Mostly Good Metrics\n\n1. Use query_metrics for several aggregate questions instead of repeated execute_query calls\n2. Pass inline definitions to execute_funnel and execute_retention rather than creating saved objects\n3. Confirm with the user before delete, revoke_api_key or stop_experiment calls, since the server doesn't ask\n4. Start a fresh agent session after connecting, since a running client may not reload the tool list\n5. On 429 from ingestion, wait for Retry-After before resending events\n\n## Questions\n\n### Which is better for AI agents, GrowthBook or Mostly Good Metrics?\n\nGrowthBook scores 68.6 (B) on agent readiness against Mostly Good Metrics's 41.7 (E), and leads in every scored category.\n\n### Do GrowthBook and Mostly Good Metrics need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call GrowthBook and Mostly Good Metrics without installing anything?\n\nYes. GrowthBook has a hosted endpoint at https://mcp.growthbook.io/mcp and Mostly Good Metrics at https://app.mostlygoodmetrics.com/mcp.\n\n### Are GrowthBook and Mostly Good Metrics open source?\n\nGrowthBook is open source (MIT for the core and for the MCP server. Three enterprise directories in the main repository are under GrowthBook's enterprise licence. GrowthBook Cloud is a hosted service under the Customer Agreement). No open-source release is listed for Mostly Good Metrics.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/growthbook-vs-mostly-good-metrics.json, and with the fewest tokens: https://www.anchorterminal.com/compare/growthbook-vs-mostly-good-metrics.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"growthbook\", \"b\": \"mostly-good-metrics\"}`. From a terminal: `anchor compare growthbook mostly-good-metrics`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/growthbook.json and https://www.anchorterminal.com/api/v1/tools/mostly-good-metrics.json\n\n## Other comparisons with GrowthBook or Mostly Good Metrics\n\n- [Amplitude vs GrowthBook](https://www.anchorterminal.com/compare/amplitude-vs-growthbook.md)\n- [Amplitude vs Mostly Good Metrics](https://www.anchorterminal.com/compare/amplitude-vs-mostly-good-metrics.md)\n- [Basedash MCP vs Mostly Good Metrics](https://www.anchorterminal.com/compare/basedash-mcp-vs-mostly-good-metrics.md)\n- [Countly vs GrowthBook](https://www.anchorterminal.com/compare/countly-vs-growthbook.md)\n- [Countly vs Mostly Good Metrics](https://www.anchorterminal.com/compare/countly-vs-mostly-good-metrics.md)\n- [Fullstory vs GrowthBook](https://www.anchorterminal.com/compare/fullstory-vs-growthbook.md)\n- [Fullstory vs Mostly Good Metrics](https://www.anchorterminal.com/compare/fullstory-vs-mostly-good-metrics.md)\n- [GrowthBook vs OpenPanel](https://www.anchorterminal.com/compare/growthbook-vs-openpanel.md)\n- [GrowthBook vs Pendo](https://www.anchorterminal.com/compare/growthbook-vs-pendo.md)\n- [GrowthBook vs Userpilot](https://www.anchorterminal.com/compare/growthbook-vs-userpilot.md)\n- [GrowthBook vs Woopra](https://www.anchorterminal.com/compare/growthbook-vs-woopra.md)\n- [Matomo vs Mostly Good Metrics](https://www.anchorterminal.com/compare/matomo-vs-mostly-good-metrics.md)\n- [Mixpanel vs Mostly Good Metrics](https://www.anchorterminal.com/compare/mixpanel-vs-mostly-good-metrics.md)\n- [Mostly Good Metrics vs OpenPanel](https://www.anchorterminal.com/compare/mostly-good-metrics-vs-openpanel.md)\n- [Mostly Good Metrics vs Optimizely Experimentation](https://www.anchorterminal.com/compare/mostly-good-metrics-vs-optimizely.md)\n- [Mostly Good Metrics vs Pendo](https://www.anchorterminal.com/compare/mostly-good-metrics-vs-pendo.md)\n- [Mostly Good Metrics vs PostHog](https://www.anchorterminal.com/compare/mostly-good-metrics-vs-posthog.md)\n- [Mostly Good Metrics vs RudderStack MCP](https://www.anchorterminal.com/compare/mostly-good-metrics-vs-rudderstack-mcp.md)\n- [Mostly Good Metrics vs Statsig](https://www.anchorterminal.com/compare/mostly-good-metrics-vs-statsig.md)\n- [Mostly Good Metrics vs Userpilot](https://www.anchorterminal.com/compare/mostly-good-metrics-vs-userpilot.md)\n- [Mostly Good Metrics vs Woopra](https://www.anchorterminal.com/compare/mostly-good-metrics-vs-woopra.md)\n- [GrowthBook vs Heap](https://www.anchorterminal.com/compare/growthbook-vs-heap.md)\n- [GrowthBook vs RudderStack MCP](https://www.anchorterminal.com/compare/growthbook-vs-rudderstack-mcp.md)\n- [Heap vs Mostly Good Metrics](https://www.anchorterminal.com/compare/heap-vs-mostly-good-metrics.md)\n- [Flagsmith vs GrowthBook](https://www.anchorterminal.com/compare/flagsmith-vs-growthbook.md)\n- [Flagsmith vs Mostly Good Metrics](https://www.anchorterminal.com/compare/flagsmith-vs-mostly-good-metrics.md)\n- [GrowthBook vs Harness Feature Management \u0026 Experimentation](https://www.anchorterminal.com/compare/growthbook-vs-harness-fme.md)\n- [GrowthBook vs LaunchDarkly](https://www.anchorterminal.com/compare/growthbook-vs-launchdarkly.md)\n- [GrowthBook vs Matomo](https://www.anchorterminal.com/compare/growthbook-vs-matomo.md)\n- [GrowthBook vs Mixpanel](https://www.anchorterminal.com/compare/growthbook-vs-mixpanel.md)\n- [GrowthBook vs Optimizely Experimentation](https://www.anchorterminal.com/compare/growthbook-vs-optimizely.md)\n- [GrowthBook vs PostHog](https://www.anchorterminal.com/compare/growthbook-vs-posthog.md)\n- [GrowthBook vs Statsig](https://www.anchorterminal.com/compare/growthbook-vs-statsig.md)\n- [Harness Feature Management \u0026 Experimentation vs Mostly Good Metrics](https://www.anchorterminal.com/compare/harness-fme-vs-mostly-good-metrics.md)\n- [LaunchDarkly vs Mostly Good Metrics](https://www.anchorterminal.com/compare/launchdarkly-vs-mostly-good-metrics.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": "GrowthBook vs Mostly Good Metrics", "url": "" } ], "description": "GrowthBook scores 68.6 (B) to Mostly Good Metrics's 41.7 (E) for feature flags and experiments. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "GrowthBook B 68.6", "Mostly Good Metrics E 41.7", "scores" ], "h1": "GrowthBook vs Mostly Good Metrics", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/growthbook-vs-mostly-good-metrics", "published": "2026-10-01", "section": "tools", "title": "GrowthBook vs Mostly Good Metrics for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/growthbook-vs-mostly-good-metrics" }, "tokens": { "markdown": 5750, "slim": 3480 }, "version": 1 }