{ "data": { "a": { "slug": "flagsmith", "name": "Flagsmith", "vendor": "Bullet Train Ltd", "vendorUrl": "https://www.flagsmith.com", "kind": "http-api", "category": "product-analytics", "summary": "Flagsmith is an open-source feature flag, remote config and experimentation service from Bullet Train Ltd. Teams use it on Flagsmith Cloud or self-hosted, through SDKs, a Management API and a remote MCP server.", "url": "https://www.anchorterminal.com/tools/flagsmith", "markdownUrl": "https://www.anchorterminal.com/tools/flagsmith.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/flagsmith.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/flagsmith.json", "dns": "flagsmith.grade.anchorterminal.com", "repo": "https://github.com/Flagsmith/flagsmith", "license": "BSD-3-Clause", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://mcp.flagsmith.com", "packages": [ { "registry": "pypi", "name": "flagsmith" }, { "registry": "npm", "name": "flagsmith" } ], "auth": "mixed", "authNotes": "The hosted MCP server takes OAuth (the client discovers Flagsmith as the authorisation server and a person signs in) or an Organisation API key sent as `Authorization: Api-Key \u003ckey\u003e`. Organisation keys act as full organisation admin or with chosen RBAC roles; granular roles need Scale-Up or Enterprise. OIDC trust relationships let CI workloads such as GitHub Actions exchange their token for a short-lived one. SDK environment keys are separate.", "pricing": "freemium", "pricingNotes": "Free plan at $0 with 50,000 requests a month and one team member. Start-Up is $45 a month ($40 billed yearly) for 1,000,000 requests and three members, Scale-Up $300 a month ($250 yearly) for 5,000,000. Enterprise by quote. Extra API calls from $50 per million; the page also quotes $7 per 100,000 for Start-Up. The self-hosted edition is free under BSD-3-Clause.", "priceSummary": "$45 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI spec or the pricing page (checked 2026-11-06).", "endpoints": [] }, "toolCount": 54, "popularity": { "githubStars": 6639, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.flagsmith.com/", "openapi": "https://github.com/Flagsmith/flagsmith/blob/main/openapi.yaml", "capabilities": [ "analytics.flags", "analytics.experiments", "analytics.events" ], "tags": [ "official", "hosted", "open-source", "self-hosted", "mcp", "remote-mcp", "oauth", "openapi", "free-tier", "status-page", "soc2", "sla", "python", "typescript" ], "lastRelease": "2026-11-05", "graded": true, "anchor": { "graded": true, "score": 61.2, "grade": "C", "agentReady": false, "rank": 620, "ranked": true, "rankOf": 1486, "categoryRank": 12, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 55, "maintenance": 83, "payments": 40, "reliability": 65, "schema": 67, "security": 65, "transparency": 77 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -2, "negativeNotes": [ "6 November 2026. The self-hosted API sends a heartbeat to https://api.flagsmith.com/api/v1/analytics/telemetry/ with counts of organisations, projects, environments, feature flags, segments and users, on by default (`ENABLE_TELEMETRY = env.bool(\"ENABLE_TELEMETRY\", default=True)`). The flag isn't in the environment-variable reference or anywhere else in the docs we read. Counts only, self-hosted only, so the minimum deduction (https://github.com/Flagsmith/flagsmith/blob/main/api/app/settings/common.py ; https://github.com/Flagsmith/flagsmith/blob/main/api/telemetry/telemetry.py)." ], "verdict": "Flagsmith pairs a BSD-licensed core with a hosted MCP server whose 54 tools come from its OpenAPI spec and carry read and destructive hints. A public 99.95 per cent SLA and SOC 2 report back the Cloud service. The MCP server is still an early release, and fine-grained key roles need a paid Scale-Up or Enterprise plan.", "bestFor": "Feature flags and experiments for teams that want open source or self-hosting, managed by an agent through MCP.", "strengths": [ "Hosted MCP server at mcp.flagsmith.com with OAuth or an Organisation API key, and a stdio option for local use", "Each of the 54 MCP tools has readOnlyHint, destructiveHint and idempotentHint set from its HTTP method", "Public SLA of 99.95 per cent monthly uptime with service credits, and a status page with component history", "BSD-3-Clause source with a free self-hosted edition and 34 tagged releases in the last 90 days", "OIDC trust relationships let CI jobs get short-lived Management API tokens without stored secrets" ], "weaknesses": [ "The MCP docs call the server an early release, and experiment tools are marked beta", "54 tools load at once, with no toolsets or read-only mode on the server", "Granular API key roles, change requests and audit logs need Scale-Up or Enterprise", "No llms.txt, no documented 429 handling, and few documented error responses in the spec", "Self-hosted installs send a usage heartbeat by default through a flag the docs don't mention" ], "agentNotes": [ "Send the key as `Authorization: Api-Key \u003ckey\u003e`; the `Api-Key ` prefix is required and a bare key fails", "Check whether the environment uses v2 feature versioning before choosing between segment-override and version-state tools", "Use a key with a read-only RBAC role for analysis tasks, since a Free plan key has organisation admin rights", "Pace Management API calls under 500 a minute; no Retry-After guidance is documented", "Treat experiment results as possibly null until Flagsmith has computed them" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.2 } ], "editorialScores": { "ergonomics": 55, "maintenance": 83, "payments": 40, "reliability": 65, "schema": 67, "security": 65, "transparency": 67 }, "provenanceScore": 86, "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": { "http": "curl -H \"Authorization: Api-Key $FLAGSMITH_ORG_KEY\" https://api.flagsmith.com/api/v1/projects/", "claudeCode": "claude mcp add --transport http flagsmith https://mcp.flagsmith.com", "config": { "mcpServers": { "flagsmith": { "headers": { "Authorization": "Api-Key \u003cyour-api-key\u003e" }, "url": "https://mcp.flagsmith.com" } } } }, "letme": { "capability": "https://letme.dev/analytics.flags", "tool": "https://letme.dev/flagsmith" }, "area": "business", "unitPrices": [ { "item": "Start-Up plan", "unit": "month", "usd": 45, "note": "1,000,000 requests and 3 team members; $40 a month billed yearly" }, { "item": "Scale-Up plan", "unit": "month", "usd": 300, "note": "5,000,000 requests and 5 team members; $250 a month billed yearly" }, { "item": "Extra API calls", "unit": "1k-requests", "usd": 0.05, "note": "From $50 per million, lower with volume" }, { "item": "Extra Scale-Up team member", "unit": "seat-month", "usd": 50, "note": "Up to 20 members" } ], "provenance": { "legalEntity": "Bullet Train Ltd", "domain": "flagsmith.com", "domainRegistered": "2018-03-01", "endpointOnVendorDomain": true, "terms": "https://www.flagsmith.com/terms-of-service", "privacy": "https://www.flagsmith.com/privacy-policy", "statusPage": "https://status.flagsmith.com", "changelog": "https://github.com/Flagsmith/flagsmith/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The terms of service name Bullet Train Limited trading as Flagsmith, company number 12353266, registered at 66 Paul St, London, under the laws of England and Wales. Companies House lists the company with five active officers.", "The privacy policy was last updated in October 2023; the GDPR sub-processor list is dated 13 October 2025.", "www.flagsmith.com/robots.txt disallows only sign-up, login and similar paths. docs.flagsmith.com has no robots.txt. The terms contain no clause on automated access that we found.", "www.flagsmith.com/.well-known/security.txt returned 404. SECURITY.md in the repository asks for reports to support@flagsmith.com.", "RDAP gives flagsmith.com a registration date of 1 March 2018." ], "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/flagsmith.json", "live": { "slug": "flagsmith", "probe": { "target": "https://mcp.flagsmith.com", "method": "get", "lastAt": "2026-11-07T18:20:25.400493249Z", "lastOk": true, "lastStatus": 401, "lastMs": 94, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 27, "p95ms24h": 100, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://status.flagsmith.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:21:11.347876696Z" }, "versions": [ { "registry": "github", "name": "Flagsmith/flagsmith", "version": "v2.290.0", "released": "2026-11-05", "seenAt": "2026-11-06T23:26:24.068130998Z" }, { "registry": "npm", "name": "flagsmith", "version": "10.0.0", "seenAt": "2026-11-06T23:26:23.147625706Z" }, { "registry": "pypi", "name": "flagsmith", "version": "6.5.0", "released": "2026-11-06", "seenAt": "2026-11-06T23:26:23.005711379Z" } ], "githubStars": 6642, "npmWeekly": 156837, "pypiWeekly": 401488, "securityTxt": { "url": "https://flagsmith.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:18.95883898Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/Flagsmith/flagsmith/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:18:21.223652009Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "34b306151856" }, { "url": "https://www.flagsmith.com/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:28:36.671052285Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ba6cc5c7a64f" }, { "url": "https://www.flagsmith.com/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:28:38.746283857Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6ada20e0c356" } ], "mcpTools": { "url": "https://mcp.flagsmith.com", "checkedAt": "2026-11-07T01:44:38.567136868Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:44:38.567136868Z" }, "updatedAt": "2026-11-07T18:21:11.347876696Z" } }, "answer": "LaunchDarkly scores 71.3 (BB) on agent readiness against Flagsmith's 61.2 (C), and leads in 5 of 7 scored categories.", "b": { "slug": "launchdarkly", "name": "LaunchDarkly", "vendor": "Catamorphic, Co. (dba LaunchDarkly)", "vendorUrl": "https://launchdarkly.com", "kind": "http-api", "category": "product-analytics", "summary": "LaunchDarkly is a hosted feature flag and experimentation platform from Catamorphic, Co., with observability and AI configuration products. Agents reach it through an official hosted MCP server with OAuth and a REST API with a public OpenAPI spec.", "url": "https://www.anchorterminal.com/tools/launchdarkly", "markdownUrl": "https://www.anchorterminal.com/tools/launchdarkly.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/launchdarkly.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/launchdarkly.json", "dns": "launchdarkly.grade.anchorterminal.com", "repo": "https://github.com/launchdarkly/mcp-server", "license": "Proprietary service under LaunchDarkly's terms. The local MCP server is MIT and the ldcli CLI is Apache-2.0", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://mcp.launchdarkly.com/mcp/launchdarkly", "packages": [ { "registry": "npm", "name": "@launchdarkly/mcp-server" }, { "registry": "npm", "name": "launchdarkly-api" }, { "registry": "pypi", "name": "launchdarkly-api" }, { "registry": "npm", "name": "@launchdarkly/node-server-sdk" }, { "registry": "pypi", "name": "launchdarkly-server-sdk" } ], "auth": "mixed", "authNotes": "Self-serve. The hosted MCP server uses OAuth with PKCE and dynamic client registration, with reader, writer and observability scopes, and acts with the role of the member who approves it. The REST API, the CLI and the local MCP server take an access token in the `Authorization` header. A signed-in member creates the token with a Reader, Writer, Admin or Owner role, and it is shown once. Custom roles and inline policies need a plan with custom roles, and service tokens need Enterprise. SDK keys cannot call the REST API.", "pricing": "freemium", "pricingNotes": "The Developer plan is free with no card and no seat charge, with 5 service connections, 1,000 client-side MAU, 100,000 experimentation MAU and 5,000 AI runs a month. Foundation has a 14-day trial, then bills by usage with no platform fee. Enterprise is custom. API and MCP calls are not billed (https://launchdarkly.com/pricing/, checked 2026-10-08).", "priceSummary": "$10 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the API docs, the OpenAPI spec or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 141, "popularity": { "githubStars": null, "npmWeekly": 3291956, "pypiWeekly": 2207524, "asOf": "2026-10-08" }, "docsUrl": "https://launchdarkly.com/docs/home/getting-started/mcp", "llmsTxt": "https://launchdarkly.com/docs/llms.txt", "openapi": "https://app.launchdarkly.com/api/v2/openapi.json", "capabilities": [ "analytics.flags", "analytics.experiments", "observability.logs", "observability.errors" ], "tags": [ "official", "hosted", "mcp", "oauth", "openapi", "llms-txt", "free-tier", "no-card", "eu-region", "status-page", "soc2", "cli", "typescript", "python" ], "lastRelease": "2026-10-27", "graded": true, "anchor": { "graded": true, "score": 71.3, "grade": "BB", "agentReady": true, "rank": 162, "ranked": true, "rankOf": 1486, "categoryRank": 2, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 69, "maintenance": 82, "payments": 40, "reliability": 74, "schema": 89, "security": 66, "transparency": 81 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "LaunchDarkly suits agents that manage feature flags, rollouts and experiments. The hosted MCP server uses OAuth with dynamic client registration and marks its tools read-only or destructive, and the Developer plan is free without a card. The server lists 141 tools, numeric rate limits are unpublished, and every REST API version except 20240415 stops working on 31 December 2026.", "bestFor": "An agent that creates and targets feature flags, runs rollouts and experiments, reads experiment results and cleans up stale flags.", "strengths": [ "Public OpenAPI 3.0.3 spec with 401 operations, 399 of them described, with 1,853 examples and 429 documented on 287 operations", "Hosted MCP server with OAuth, PKCE, dynamic client registration, a revocation endpoint and reader, writer and observability scopes", "MCP tools cover experiment creation, iteration control and results, flag targeting, approval requests and flag removal readiness", "Developer plan is free with no card, unlimited seats, unlimited flags and 100,000 experimentation MAU a month", "Dated API versions set by header, with a written policy of 12 months' support after a new version" ], "weaknesses": [ "The hosted MCP server lists 141 tools, and no tool filter for it was found in the reviewed documentation", "The API docs say the numeric rate limits are not published and may change", "132 of 401 API operations are beta, need `LD-API-Version: beta` and may change without notice", "Every REST API version except 20240415 stops answering on 31 December 2026, announced on the status page on 25 August 2025", "Custom roles, inline token policies, service tokens and approvals need an Enterprise plan, and the hosted MCP server is absent from the EU and federal instances" ], "agentNotes": [ "Connect to https://mcp.launchdarkly.com/mcp/launchdarkly over streamable HTTP with OAuth. On the EU or federal instance run the local `@launchdarkly/mcp-server` with `--server-url`", "Authorise with a Reader role or the `reader` scope unless the task writes. A 403 after consent means the member's role lacks access", "Send `LD-API-Version: 20240415` on every REST call, and `LD-API-Version: beta` for beta resources, which answer 403 without it", "Read `X-Ratelimit-Global-Remaining`, `X-Ratelimit-Route-Remaining` and `X-Ratelimit-Reset` on each response, and wait `Retry-After` seconds on an IP limit", "Send `Content-Type: application/json; domain-model=launchdarkly.semanticpatch` for semantic patches, or the body is read as JSON patch and answers 400" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 71.3 } ], "editorialScores": { "ergonomics": 69, "maintenance": 82, "payments": 40, "reliability": 74, "schema": 89, "security": 66, "transparency": 74 }, "provenanceScore": 88, "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 --package @launchdarkly/mcp-server -- mcp start --api-key api-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx", "claudeCode": "claude mcp add --transport http \"launchdarkly\" \"https://mcp.launchdarkly.com/mcp/launchdarkly\"", "config": { "mcpServers": { "launchdarkly": { "type": "http", "url": "https://mcp.launchdarkly.com/mcp/launchdarkly" } } } }, "letme": { "capability": "https://letme.dev/analytics.flags", "tool": "https://letme.dev/launchdarkly" }, "area": "business", "unitPrices": [ { "item": "Foundation, service connection", "unit": "month", "usd": 10, "note": "per connection, billed yearly, first 5 included" }, { "item": "Foundation, client-side MAU", "unit": "user-month", "usd": 0.00833, "note": "$8.33 per 1,000, billed yearly" }, { "item": "Additional AI run", "unit": "tx", "usd": 0.005, "note": "$5 per 1,000 above 5,000 a month" } ], "provenance": { "legalEntity": "Catamorphic, Co. (dba LaunchDarkly)", "domain": "launchdarkly.com", "domainRegistered": "2014-07-15", "endpointOnVendorDomain": true, "terms": "https://launchdarkly.com/policies/subscription-terms/", "privacy": "https://launchdarkly.com/policies/privacy/", "statusPage": "https://status.launchdarkly.com", "changelog": "https://launchdarkly.com/docs/home/changelog", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of service for Developer and Foundation self-service customers (effective 8 September 2025) name Catamorphic, Co., a Delaware corporation doing business as LaunchDarkly. Enterprise customers have separate terms at https://launchdarkly.com/policies/subscription-terms-enterprise/.", "The privacy policy (effective 8 April 2025) says it does not apply to data LaunchDarkly processes for customers. The data processing addendum at https://launchdarkly.com/policies/data-processing-addendum/ covers that data.", "launchdarkly.com/.well-known/security.txt and app.launchdarkly.com/.well-known/security.txt return 404.", "The MCP server answers on mcp.launchdarkly.com and the API on app.launchdarkly.com. The MCP endpoint's headers name Gram, from Speakeasy, which is on the sub-processor list.", "RDAP for launchdarkly.com gives a registration date of 2014-07-15." ], "score": 88 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/launchdarkly.json", "live": { "slug": "launchdarkly", "probe": { "target": "https://mcp.launchdarkly.com/mcp/launchdarkly", "method": "get", "lastAt": "2026-11-07T18:20:34.705994114Z", "lastOk": true, "lastStatus": 401, "lastMs": 304, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 99.97, "p50ms24h": 272, "p95ms24h": 348, "samples24h": 239, "samples30d": 7440, "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": 251 }, { "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": 251 }, { "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": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://status.launchdarkly.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:21:19.93212016Z" }, "versions": [ { "registry": "github", "name": "launchdarkly/mcp-server", "version": "v0.7.2", "released": "2026-10-27", "seenAt": "2026-11-06T23:39:08.463151071Z" }, { "registry": "npm", "name": "@launchdarkly/mcp-server", "version": "0.7.2", "seenAt": "2026-11-06T23:39:01.769693206Z" }, { "registry": "npm", "name": "@launchdarkly/node-server-sdk", "version": "9.16.4", "seenAt": "2026-11-06T23:39:06.503221385Z" }, { "registry": "npm", "name": "launchdarkly-api", "version": "20.0.0", "seenAt": "2026-11-06T23:39:06.089281348Z" }, { "registry": "pypi", "name": "launchdarkly-api", "version": "25.1.1", "released": "2026-10-30", "seenAt": "2026-11-06T23:39:06.265421062Z" }, { "registry": "pypi", "name": "launchdarkly-server-sdk", "version": "9.20.0", "released": "2026-11-05", "seenAt": "2026-11-06T23:39:08.379675336Z" } ], "githubStars": 27, "npmWeekly": 74871, "pypiWeekly": 158016, "securityTxt": { "url": "https://launchdarkly.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:12.480495142Z" }, "llmsTxt": { "url": "https://launchdarkly.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:52.221951252Z" }, "domain": { "domain": "launchdarkly.com", "registered": "2014-07-15", "source": "https://rdap.verisign.com/com/v1/domain/launchdarkly.com", "checkedAt": "2026-11-01T14:15:37.540687608Z" }, "pages": [ { "url": "https://launchdarkly.com/docs/home/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:12:30.58917002Z", "changedAt": "2026-11-07T14:12:30.58917002Z", "fingerprint": "0a011833453c" }, { "url": "https://launchdarkly.com/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:12:36.764332808Z", "changedAt": "2026-11-05T12:36:00.509827916Z", "fingerprint": "b79702f6a1ef" }, { "url": "https://launchdarkly.com/policies/privacy/", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:12:32.788411037Z", "changedAt": "2026-11-05T12:35:56.273486473Z", "fingerprint": "07bd39fb47af" }, { "url": "https://launchdarkly.com/policies/subscription-terms/", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:12:35.303934026Z", "changedAt": "2026-11-05T12:35:58.580019987Z", "fingerprint": "b1228f73ebac" } ], "mcpTools": { "url": "https://mcp.launchdarkly.com/mcp/launchdarkly", "checkedAt": "2026-11-07T01:45:41.609636672Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:45:41.609636672Z" }, "github": { "repo": "launchdarkly/mcp-server", "checkedAt": "2026-11-02T09:00:03.111676849Z", "stars": 27, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T00:12:35Z", "openIssues": 11, "openPRs": 11, "issuesOpened90d": 7, "issuesClosed90d": 3, "prsMerged90d": 5, "ci": { "branch": "main", "runs": 27, "success": 13, "failure": 14, "other": 0, "latest": "success", "latestAt": "2026-10-27T21:32:58Z" }, "replies": { "sampled": 18, "unanswered": 10, "medianDays": 3.6 } }, "updatedAt": "2026-11-07T18:21:19.93212016Z" } }, "edges": [ { "by": 22, "category": "schema", "leads": "launchdarkly", "name": "Schema \u0026 documentation", "reasons": { "a": "openapi.yaml in the repository is OpenAPI 3.1 with 624 operations, and the MCP server builds its 54 tools from the operations tagged `mcp`, so every tool has a JSON Schema input (25). No llms.txt (404) and no Markdown served for agents on docs.flagsmith.com; the docs are Markdown only in the repository (0). Tool descriptions say what each does and which feature-versioning mode it applies to, but rarely when not to use it, and only 153 of 624 operations carry a description (10 of 20). 57 enums and required fields in the spec, with some free-form value fields (10 of 15). Docs carry curl examples, but only 16 operations document a 400 and 6 a 404 (7 of 15). A /api/v1 path, release-please changelog and dated release notes (15). 25+0+10+10+7+15 = 67.", "b": "OpenAPI 3.0.3 served without a login at app.launchdarkly.com/api/v2/openapi.json, with 253 paths and 401 operations (25). The hosted MCP input schemas need a sign-in and were not read. A docs index for agents at launchdarkly.com/docs/llms.txt, and docs pages answer as Markdown with .md (10). 399 of 401 operations have a description. The MCP tool descriptions on the server page average about 740 characters and state pagination, sorting, plan limits and which tool to call next (17). 169 enums across 746 schemas. JSON patch bodies and semantic patch instructions are loosely typed objects (9). 1,853 examples in the spec, 429 documented on 287 operations and 403 on 355, and an error table with a suggested fix for each status (13). Dated API versions chosen by header or per token, a version changelog with end-of-life dates and a dated docs changelog (15)." }, "scores": { "a": 67, "b": 89 } }, { "by": 14, "category": "ergonomics", "leads": "launchdarkly", "name": "Agent ergonomics", "reasons": { "a": "54 tools, more than 30, with no toolsets or read-only subset; enterprise tools only appear where installed (5 of 25). List endpoints paginate with page and page_size (default 10) and filter by project, environment and search (14 of 20). Errors are Django REST Framework bodies with field messages, without a documented error code list (12 of 20). Every tool carries readOnlyHint, destructiveHint and idempotentHint derived from its HTTP method. No idempotency keys for POST (14 of 20). Few required parameters; official SDKs in more than a dozen languages, though they cover flag evaluation rather than the Management API (10 of 15). 5+14+12+14+10 = 55.", "b": "The hosted MCP server lists 141 tools, far past 30 (5). The OAuth metadata names reader, writer and observability scopes, but no tool filter for the hosted server was found. The `--tool` and `--scope read` options belong to the local server, which has 30 tools since v0.7.2 (27 October 2026), so 3 of 10 added back (8). The API has `limit` and `offset` on 61 operations, filters and sorting, summary and detailed representations and an `expand` parameter on 40 (18). Errors carry `code`, `message` and `id`, with a table of statuses and fixes (15). The server page marks 73 tools read-only, 35 destructive and 89 idempotent. There are no idempotency keys on REST writes, and JSON patch can test a version before applying (15). Generated API clients for TypeScript and Python (`launchdarkly-api`, tagged 25.1.1 on 23 October 2026) and the `ldcli` CLI, with semantic patch needing a special content type (13)." }, "scores": { "a": 55, "b": 69 } }, { "by": 9, "category": "reliability", "leads": "launchdarkly", "name": "Reliability", "reasons": { "a": "Graded on Flagsmith Cloud with the hosted lines. Statuspage at status.flagsmith.com with components for the Edge API, Admin API, dashboard and website (20). In the 90 days from 8 August, an Admin and SDK API outage on 28 October marked critical, posted at 21:56 UTC and resolved at 22:12 with no cause given, and a minor delay in processing flag changes on 10 September. The posted span of the outage is 16 minutes and its start isn't stated, so we read it as one serious incident under an hour (15 of 30). The Management API limit of 500 requests a minute is documented (15). No 429 handling, Retry-After or idempotency guidance was found in the docs (0). A public SLA commits to 99.95 per cent monthly uptime with service credits (10). The Management API is generally available, but the MCP docs call the server an early release, so half (5 of 10). 20+15+15+0+10+5 = 65.", "b": "Graded on the hosted service with the hosted lines. Statuspage at status.launchdarkly.com with 51 components and incident history (20). Read from the history feed (the host's robots.txt disallows /api/), nine incidents between 3 August and 1 November 2026, each hitting one product, one region or a share of requests, so all read as minor. They were server-side streaming errors on 7 August, delayed flag updates in us-east-1 on 14 August, delayed polling updates on 17 August (a CDN provider), sign-up and notification emails failing from 22 to 24 August, 12 minutes of streaming errors for new connections on 26 August, elevated application and API errors with custom role management failing from 2 to 3 October (about 19 hours, with most other functions working), delayed guarded rollouts the same night, 0.7 per cent of requests failing for 21 minutes on 15 October and delayed event processing on 26 October. The 10 July outage, marked critical, has left the window (20). The API docs describe global, route, token and IP limits and say the numbers are not published. Limit and remaining headers report them at run time (5 of 15). 429s carry reset headers, IP limits carry `Retry-After`, and the docs ask for jitter and backoff. No idempotency keys were found, though JSON patch can test a resource version and 409 is documented as retryable (11 of 15). The SLA commits to 99.9 per cent for Enterprise support and 99.99 per cent for Premium support (10). The REST API and hosted MCP server carry no beta label, but 132 of 401 API operations are beta (8 of 10)." }, "scores": { "a": 65, "b": 74 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Bullet Train Ltd", "b": "Catamorphic, Co. (dba LaunchDarkly)", "name": "Vendor" }, { "a": "https://mcp.flagsmith.com", "b": "https://mcp.launchdarkly.com/mcp/launchdarkly", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, stdio", "b": "HTTP, Streamable HTTP, stdio", "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": "BSD-3-Clause", "b": "Proprietary service under LaunchDarkly's terms. The local MCP server is MIT and the ldcli CLI is Apache-2.0", "name": "Licence" }, { "a": "54", "b": "141", "name": "Tools exposed" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-05", "b": "2026-10-27", "name": "Last release" }, { "a": "2026-09-01", "b": "2025-09-08", "name": "Terms last updated" }, { "a": "2023-10-01", "b": "2025-04-08", "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": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "6.6k stars", "b": "3.3M npm/wk, 2.2M PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "LaunchDarkly scores 71.3 (BB) on agent readiness against Flagsmith's 61.2 (C), and leads in 5 of 7 scored categories.", "question": "Which is better for AI agents, Flagsmith or LaunchDarkly?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do Flagsmith and LaunchDarkly need an API key?" }, { "answer": "Yes. Flagsmith has a hosted endpoint at https://mcp.flagsmith.com and LaunchDarkly at https://mcp.launchdarkly.com/mcp/launchdarkly.", "question": "Can an agent call Flagsmith and LaunchDarkly without installing anything?" }, { "answer": "Flagsmith is open source (BSD-3-Clause). No open-source release is listed for LaunchDarkly.", "question": "Are Flagsmith and LaunchDarkly open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "Open source" ], "goodFor": "Feature flags and experiments for teams that want open source or self-hosting, managed by an agent through MCP.", "slug": "flagsmith", "watchFor": "The MCP docs call the server an early release, and experiment tools are marked beta" }, { "aheadOn": [ "Reliability, 74 against 65", "Schema \u0026 documentation, 89 against 67", "Agent ergonomics, 69 against 55" ], "also": [ "Agent-ready, a grade of BB or better", "Free to start without a card" ], "goodFor": "An agent that creates and targets feature flags, runs rollouts and experiments, reads experiment results and cleans up stale flags.", "slug": "launchdarkly", "watchFor": "The hosted MCP server lists 141 tools, and no tool filter for it was found in the reviewed documentation" } ], "history": { "flagsmith": null, "launchdarkly": [ { "causes": [ "time" ], "date": "2026-11-01", "delta": 2, "from": 69.3, "fromGrade": "B", "to": 71.3, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 69.2, "fromGrade": "B", "to": 69.3, "toGrade": "B" } ] }, "job": { "capability": "analytics.flags", "name": "Feature flags" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amplitude-vs-flagsmith.json", "title": "Amplitude vs Flagsmith", "url": "https://www.anchorterminal.com/compare/amplitude-vs-flagsmith" }, { "json": "https://www.anchorterminal.com/compare/amplitude-vs-launchdarkly.json", "title": "Amplitude vs LaunchDarkly", "url": "https://www.anchorterminal.com/compare/amplitude-vs-launchdarkly" }, { "json": "https://www.anchorterminal.com/compare/countly-vs-flagsmith.json", "title": "Countly vs Flagsmith", "url": "https://www.anchorterminal.com/compare/countly-vs-flagsmith" }, { "json": "https://www.anchorterminal.com/compare/countly-vs-launchdarkly.json", "title": "Countly vs LaunchDarkly", "url": "https://www.anchorterminal.com/compare/countly-vs-launchdarkly" }, { "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-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-mixpanel.json", "title": "Flagsmith vs Mixpanel", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-mixpanel" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-optimizely.json", "title": "Flagsmith vs Optimizely Experimentation", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-optimizely" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-posthog.json", "title": "Flagsmith vs PostHog", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-posthog" }, { "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/launchdarkly-vs-mixpanel.json", "title": "LaunchDarkly vs Mixpanel", "url": "https://www.anchorterminal.com/compare/launchdarkly-vs-mixpanel" }, { "json": "https://www.anchorterminal.com/compare/launchdarkly-vs-optimizely.json", "title": "LaunchDarkly vs Optimizely Experimentation", "url": "https://www.anchorterminal.com/compare/launchdarkly-vs-optimizely" }, { "json": "https://www.anchorterminal.com/compare/launchdarkly-vs-posthog.json", "title": "LaunchDarkly vs PostHog", "url": "https://www.anchorterminal.com/compare/launchdarkly-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/flagsmith-vs-fullstory.json", "title": "Flagsmith vs Fullstory", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-fullstory" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-heap.json", "title": "Flagsmith vs Heap", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-heap" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-openpanel.json", "title": "Flagsmith vs OpenPanel", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-openpanel" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-woopra.json", "title": "Flagsmith vs Woopra", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-woopra" }, { "json": "https://www.anchorterminal.com/compare/flagsmith-vs-matomo.json", "title": "Flagsmith vs Matomo", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-matomo" }, { "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-launchdarkly.json", "title": "GrowthBook vs LaunchDarkly", "url": "https://www.anchorterminal.com/compare/growthbook-vs-launchdarkly" }, { "json": "https://www.anchorterminal.com/compare/launchdarkly-vs-matomo.json", "title": "LaunchDarkly vs Matomo", "url": "https://www.anchorterminal.com/compare/launchdarkly-vs-matomo" }, { "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": 9, "edge": "launchdarkly", "flagsmith": 65, "key": "reliability", "launchdarkly": 74, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 22, "edge": "launchdarkly", "flagsmith": 67, "key": "schema", "launchdarkly": 89, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 14, "edge": "launchdarkly", "flagsmith": 55, "key": "ergonomics", "launchdarkly": 69, "name": "Agent ergonomics", "weight": 13 }, { "by": 1, "edge": "launchdarkly", "flagsmith": 65, "key": "security", "launchdarkly": 66, "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "edge": "", "flagsmith": 40, "key": "payments", "launchdarkly": 40, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 1, "edge": "flagsmith", "flagsmith": 83, "key": "maintenance", "launchdarkly": 82, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 4, "edge": "launchdarkly", "flagsmith": 77, "key": "transparency", "launchdarkly": 81, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "LaunchDarkly scores 71.3 (BB) on agent readiness against Flagsmith's 61.2 (C), and leads in 5 of 7 scored categories. Both do feature flags.", "tasks": null, "tutorials": [], "verdicts": { "flagsmith": "Flagsmith pairs a BSD-licensed core with a hosted MCP server whose 54 tools come from its OpenAPI spec and carry read and destructive hints. A public 99.95 per cent SLA and SOC 2 report back the Cloud service. The MCP server is still an early release, and fine-grained key roles need a paid Scale-Up or Enterprise plan.", "launchdarkly": "LaunchDarkly suits agents that manage feature flags, rollouts and experiments. The hosted MCP server uses OAuth with dynamic client registration and marks its tools read-only or destructive, and the Developer plan is free without a card. The server lists 141 tools, numeric rate limits are unpublished, and every REST API version except 20240415 stops working on 31 December 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/flagsmith-vs-launchdarkly", "json": "https://www.anchorterminal.com/compare/flagsmith-vs-launchdarkly.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/flagsmith-vs-launchdarkly.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/flagsmith-vs-launchdarkly.min.md" }, "markdown": "LaunchDarkly scores 71.3 (BB) on agent readiness against Flagsmith's 61.2 (C), and leads in 5 of 7 scored categories. Both do feature flags.\n\n- Flagsmith: grade C, 61.2/100, rank #620 of 1486. Markdown https://www.anchorterminal.com/tools/flagsmith.md · JSON https://www.anchorterminal.com/api/v1/tools/flagsmith.json\n- LaunchDarkly: grade BB, 71.3/100, rank #162 of 1486. Markdown https://www.anchorterminal.com/tools/launchdarkly.md · JSON https://www.anchorterminal.com/api/v1/tools/launchdarkly.json\n- Best product analytics and experimentation tools for AI agents: https://www.anchorterminal.com/best/product-analytics/index.md\n- All 153 product analytics comparisons: https://www.anchorterminal.com/compare/product-analytics/index.md\n\n## Which one, for what\n\n### Flagsmith (C)\n\nGood for: Feature flags and experiments for teams that want open source or self-hosting, managed by an agent through MCP.\n\nAlso in its favour:\n- Open source\n\nWatch for: The MCP docs call the server an early release, and experiment tools are marked beta\n\n### LaunchDarkly (BB)\n\nGood for: An agent that creates and targets feature flags, runs rollouts and experiments, reads experiment results and cleans up stale flags.\n\nAhead on:\n- Reliability, 74 against 65\n- Schema \u0026 documentation, 89 against 67\n- Agent ergonomics, 69 against 55\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Free to start without a card\n\nWatch for: The hosted MCP server lists 141 tools, and no tool filter for it was found in the reviewed documentation\n\n\n## Why the edge\n\n### Schema \u0026 documentation: LaunchDarkly +22\n\n- Flagsmith (67): openapi.yaml in the repository is OpenAPI 3.1 with 624 operations, and the MCP server builds its 54 tools from the operations tagged `mcp`, so every tool has a JSON Schema input (25). No llms.txt (404) and no Markdown served for agents on docs.flagsmith.com; the docs are Markdown only in the repository (0). Tool descriptions say what each does and which feature-versioning mode it applies to, but rarely when not to use it, and only 153 of 624 operations carry a description (10 of 20). 57 enums and required fields in the spec, with some free-form value fields (10 of 15). Docs carry curl examples, but only 16 operations document a 400 and 6 a 404 (7 of 15). A /api/v1 path, release-please changelog and dated release notes (15). 25+0+10+10+7+15 = 67.\n- LaunchDarkly (89): OpenAPI 3.0.3 served without a login at app.launchdarkly.com/api/v2/openapi.json, with 253 paths and 401 operations (25). The hosted MCP input schemas need a sign-in and were not read. A docs index for agents at launchdarkly.com/docs/llms.txt, and docs pages answer as Markdown with .md (10). 399 of 401 operations have a description. The MCP tool descriptions on the server page average about 740 characters and state pagination, sorting, plan limits and which tool to call next (17). 169 enums across 746 schemas. JSON patch bodies and semantic patch instructions are loosely typed objects (9). 1,853 examples in the spec, 429 documented on 287 operations and 403 on 355, and an error table with a suggested fix for each status (13). Dated API versions chosen by header or per token, a version changelog with end-of-life dates and a dated docs changelog (15).\n\n### Agent ergonomics: LaunchDarkly +14\n\n- Flagsmith (55): 54 tools, more than 30, with no toolsets or read-only subset; enterprise tools only appear where installed (5 of 25). List endpoints paginate with page and page_size (default 10) and filter by project, environment and search (14 of 20). Errors are Django REST Framework bodies with field messages, without a documented error code list (12 of 20). Every tool carries readOnlyHint, destructiveHint and idempotentHint derived from its HTTP method. No idempotency keys for POST (14 of 20). Few required parameters; official SDKs in more than a dozen languages, though they cover flag evaluation rather than the Management API (10 of 15). 5+14+12+14+10 = 55.\n- LaunchDarkly (69): The hosted MCP server lists 141 tools, far past 30 (5). The OAuth metadata names reader, writer and observability scopes, but no tool filter for the hosted server was found. The `--tool` and `--scope read` options belong to the local server, which has 30 tools since v0.7.2 (27 October 2026), so 3 of 10 added back (8). The API has `limit` and `offset` on 61 operations, filters and sorting, summary and detailed representations and an `expand` parameter on 40 (18). Errors carry `code`, `message` and `id`, with a table of statuses and fixes (15). The server page marks 73 tools read-only, 35 destructive and 89 idempotent. There are no idempotency keys on REST writes, and JSON patch can test a version before applying (15). Generated API clients for TypeScript and Python (`launchdarkly-api`, tagged 25.1.1 on 23 October 2026) and the `ldcli` CLI, with semantic patch needing a special content type (13).\n\n### Reliability: LaunchDarkly +9\n\n- Flagsmith (65): Graded on Flagsmith Cloud with the hosted lines. Statuspage at status.flagsmith.com with components for the Edge API, Admin API, dashboard and website (20). In the 90 days from 8 August, an Admin and SDK API outage on 28 October marked critical, posted at 21:56 UTC and resolved at 22:12 with no cause given, and a minor delay in processing flag changes on 10 September. The posted span of the outage is 16 minutes and its start isn't stated, so we read it as one serious incident under an hour (15 of 30). The Management API limit of 500 requests a minute is documented (15). No 429 handling, Retry-After or idempotency guidance was found in the docs (0). A public SLA commits to 99.95 per cent monthly uptime with service credits (10). The Management API is generally available, but the MCP docs call the server an early release, so half (5 of 10). 20+15+15+0+10+5 = 65.\n- LaunchDarkly (74): Graded on the hosted service with the hosted lines. Statuspage at status.launchdarkly.com with 51 components and incident history (20). Read from the history feed (the host's robots.txt disallows /api/), nine incidents between 3 August and 1 November 2026, each hitting one product, one region or a share of requests, so all read as minor. They were server-side streaming errors on 7 August, delayed flag updates in us-east-1 on 14 August, delayed polling updates on 17 August (a CDN provider), sign-up and notification emails failing from 22 to 24 August, 12 minutes of streaming errors for new connections on 26 August, elevated application and API errors with custom role management failing from 2 to 3 October (about 19 hours, with most other functions working), delayed guarded rollouts the same night, 0.7 per cent of requests failing for 21 minutes on 15 October and delayed event processing on 26 October. The 10 July outage, marked critical, has left the window (20). The API docs describe global, route, token and IP limits and say the numbers are not published. Limit and remaining headers report them at run time (5 of 15). 429s carry reset headers, IP limits carry `Retry-After`, and the docs ask for jitter and backoff. No idempotency keys were found, though JSON patch can test a resource version and 409 is documented as retryable (11 of 15). The SLA commits to 99.9 per cent for Enterprise support and 99.99 per cent for Premium support (10). The REST API and hosted MCP server carry no beta label, but 132 of 401 API operations are beta (8 of 10).\n\n## Score by category\n\n| Category | Weight | Flagsmith | LaunchDarkly | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 65 | 74 | LaunchDarkly +9 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 67 | 89 | LaunchDarkly +22 |\n| Agent ergonomics | 13% (16.2 this run) | 55 | 69 | LaunchDarkly +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 65 | 66 | LaunchDarkly +1 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 40 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 82 | Flagsmith +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 77 | 81 | LaunchDarkly +4 |\n| Negative events | ≤15 | -2 | 0 | |\n| **Total** | | **61.2 · C** | **71.3 · BB** | |\n\n## Facts side by side\n\n| Fact | Flagsmith | LaunchDarkly |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Bullet Train Ltd | Catamorphic, Co. (dba LaunchDarkly) |\n| Hosted endpoint | `https://mcp.flagsmith.com` | `https://mcp.launchdarkly.com/mcp/launchdarkly` |\n| Transports | HTTP, Streamable HTTP, stdio | HTTP, Streamable HTTP, stdio |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | BSD-3-Clause | Proprietary service under LaunchDarkly's terms. The local MCP server is MIT and the ldcli CLI is Apache-2.0 |\n| Tools exposed | 54 | 141 |\n| Read-only variant documented | yes | no |\n| llms.txt | no | yes |\n| Last release | 2026-11-05 | 2026-10-27 |\n| Terms last updated | 2026-09-01 | 2025-09-08 |\n| Privacy policy last updated | 2023-10-01 | 2025-04-08 |\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 | not found in the text | yes |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 6.6k stars | 3.3M npm/wk, 2.2M PyPI/wk |\n| Agent reviews | none | 3.5/5 (4) |\n\n## How the scores have moved\n\n### Flagsmith\n\nNo score change since it was listed.\n\n### LaunchDarkly\n\n- +2.0 on 1 November 2026 (B to BB): time\n- +0.1 on 27 October 2026: checklist\n\n## Verdicts\n\n**Flagsmith.** Flagsmith pairs a BSD-licensed core with a hosted MCP server whose 54 tools come from its OpenAPI spec and carry read and destructive hints. A public 99.95 per cent SLA and SOC 2 report back the Cloud service. The MCP server is still an early release, and fine-grained key roles need a paid Scale-Up or Enterprise plan.\n\n**LaunchDarkly.** LaunchDarkly suits agents that manage feature flags, rollouts and experiments. The hosted MCP server uses OAuth with dynamic client registration and marks its tools read-only or destructive, and the Developer plan is free without a card. The server lists 141 tools, numeric rate limits are unpublished, and every REST API version except 20240415 stops working on 31 December 2026.\n\n## Before you call either\n\n### Flagsmith\n\n1. Send the key as `Authorization: Api-Key \u003ckey\u003e`; the `Api-Key ` prefix is required and a bare key fails\n2. Check whether the environment uses v2 feature versioning before choosing between segment-override and version-state tools\n3. Use a key with a read-only RBAC role for analysis tasks, since a Free plan key has organisation admin rights\n4. Pace Management API calls under 500 a minute; no Retry-After guidance is documented\n5. Treat experiment results as possibly null until Flagsmith has computed them\n\n### LaunchDarkly\n\n1. Connect to https://mcp.launchdarkly.com/mcp/launchdarkly over streamable HTTP with OAuth. On the EU or federal instance run the local `@launchdarkly/mcp-server` with `--server-url`\n2. Authorise with a Reader role or the `reader` scope unless the task writes. A 403 after consent means the member's role lacks access\n3. Send `LD-API-Version: 20240415` on every REST call, and `LD-API-Version: beta` for beta resources, which answer 403 without it\n4. Read `X-Ratelimit-Global-Remaining`, `X-Ratelimit-Route-Remaining` and `X-Ratelimit-Reset` on each response, and wait `Retry-After` seconds on an IP limit\n5. Send `Content-Type: application/json; domain-model=launchdarkly.semanticpatch` for semantic patches, or the body is read as JSON patch and answers 400\n\n## Questions\n\n### Which is better for AI agents, Flagsmith or LaunchDarkly?\n\nLaunchDarkly scores 71.3 (BB) on agent readiness against Flagsmith's 61.2 (C), and leads in 5 of 7 scored categories.\n\n### Do Flagsmith and LaunchDarkly need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call Flagsmith and LaunchDarkly without installing anything?\n\nYes. Flagsmith has a hosted endpoint at https://mcp.flagsmith.com and LaunchDarkly at https://mcp.launchdarkly.com/mcp/launchdarkly.\n\n### Are Flagsmith and LaunchDarkly open source?\n\nFlagsmith is open source (BSD-3-Clause). No open-source release is listed for LaunchDarkly.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/flagsmith-vs-launchdarkly.json, and with the fewest tokens: https://www.anchorterminal.com/compare/flagsmith-vs-launchdarkly.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"flagsmith\", \"b\": \"launchdarkly\"}`. From a terminal: `anchor compare flagsmith launchdarkly`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/flagsmith.json and https://www.anchorterminal.com/api/v1/tools/launchdarkly.json\n\n## Other comparisons with Flagsmith or LaunchDarkly\n\n- [Amplitude vs Flagsmith](https://www.anchorterminal.com/compare/amplitude-vs-flagsmith.md)\n- [Amplitude vs LaunchDarkly](https://www.anchorterminal.com/compare/amplitude-vs-launchdarkly.md)\n- [Countly vs Flagsmith](https://www.anchorterminal.com/compare/countly-vs-flagsmith.md)\n- [Countly vs LaunchDarkly](https://www.anchorterminal.com/compare/countly-vs-launchdarkly.md)\n- [Flagsmith vs GrowthBook](https://www.anchorterminal.com/compare/flagsmith-vs-growthbook.md)\n- [Flagsmith vs Harness Feature Management \u0026 Experimentation](https://www.anchorterminal.com/compare/flagsmith-vs-harness-fme.md)\n- [Flagsmith vs Mixpanel](https://www.anchorterminal.com/compare/flagsmith-vs-mixpanel.md)\n- [Flagsmith vs Optimizely Experimentation](https://www.anchorterminal.com/compare/flagsmith-vs-optimizely.md)\n- [Flagsmith vs PostHog](https://www.anchorterminal.com/compare/flagsmith-vs-posthog.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- [LaunchDarkly vs Mixpanel](https://www.anchorterminal.com/compare/launchdarkly-vs-mixpanel.md)\n- [LaunchDarkly vs Optimizely Experimentation](https://www.anchorterminal.com/compare/launchdarkly-vs-optimizely.md)\n- [LaunchDarkly vs PostHog](https://www.anchorterminal.com/compare/launchdarkly-vs-posthog.md)\n- [LaunchDarkly vs Statsig](https://www.anchorterminal.com/compare/launchdarkly-vs-statsig.md)\n- [Flagsmith vs Fullstory](https://www.anchorterminal.com/compare/flagsmith-vs-fullstory.md)\n- [Flagsmith vs Heap](https://www.anchorterminal.com/compare/flagsmith-vs-heap.md)\n- [Flagsmith vs OpenPanel](https://www.anchorterminal.com/compare/flagsmith-vs-openpanel.md)\n- [Flagsmith vs Woopra](https://www.anchorterminal.com/compare/flagsmith-vs-woopra.md)\n- [Flagsmith vs Matomo](https://www.anchorterminal.com/compare/flagsmith-vs-matomo.md)\n- [Flagsmith vs Mostly Good Metrics](https://www.anchorterminal.com/compare/flagsmith-vs-mostly-good-metrics.md)\n- [GrowthBook vs LaunchDarkly](https://www.anchorterminal.com/compare/growthbook-vs-launchdarkly.md)\n- [LaunchDarkly vs Matomo](https://www.anchorterminal.com/compare/launchdarkly-vs-matomo.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": "Flagsmith vs LaunchDarkly", "url": "" } ], "description": "LaunchDarkly scores 71.3 (BB) to Flagsmith's 61.2 (C) for feature flags. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Flagsmith C 61.2", "LaunchDarkly BB 71.3", "scores" ], "h1": "Flagsmith vs LaunchDarkly", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/flagsmith-vs-launchdarkly", "published": "2026-10-01", "section": "tools", "title": "Flagsmith vs LaunchDarkly for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/flagsmith-vs-launchdarkly" }, "tokens": { "markdown": 4050, "slim": 2080 }, "version": 1 }