{
  "listings": [
    {
      "slug": "launchdarkly",
      "name": "LaunchDarkly",
      "company": "Catamorphic, Co. (dba LaunchDarkly)",
      "grade": "BB",
      "fit": "yes",
      "why": "create-flag, update-flag-targeting, update-targeting-rules and update-rollout take semantic-patch instructions that change only what is named, and start-experiment-iteration starts an experiment; approvals apply where an environment requires them.",
      "source": "https://mcp.launchdarkly.com/mcp",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/launchdarkly"
    },
    {
      "slug": "amplitude",
      "name": "Amplitude",
      "company": "Amplitude, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Management API PATCH takes optional fields including startDate and decision, but targetSegments replaces existing segments and doesn't support cohorts. The MCP no-start issue (acc-18) was closed as resolved internally, not confirmed in docs.",
      "source": "https://amplitude.com/docs/apis/experiment/experiment-management-api-experiments.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/amplitude"
    },
    {
      "slug": "countly",
      "name": "Countly",
      "company": "Countly Ltd",
      "grade": "E",
      "fit": "caveat",
      "why": "ab_experiments_create makes a draft with targeting and ab_experiments_start begins it, but remote_config_parameters_update and conditions_update replace the whole resource, so other fields must be resent.",
      "source": "https://github.com/Countly/countly-mcp-server/blob/HEAD/src/tools/ab-testing.ts",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/countly"
    },
    {
      "slug": "flagsmith",
      "name": "Flagsmith",
      "company": "Bullet Train Ltd",
      "grade": "B",
      "fit": "caveat",
      "why": "create_feature, create_segment_override or versioned feature states and update_feature_state cover flags, but tools differ by v2 versioning, update_experiment only edits name and hypothesis, change requests are Enterprise, and a partial PATCH of a multivariate option returned 500 (issue 8901).",
      "source": "https://docs.flagsmith.com/integrating-with-flagsmith/mcp-server",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/flagsmith"
    },
    {
      "slug": "growthbook",
      "name": "GrowthBook",
      "company": "GrowthBook, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Feature revisions add, update and publish rules in drafts and experiments start through /start or a status update, but some experiment fields replace the whole stored object, approval rules can hold writes, and the open MCP issue 58 says a plain flag needed a data source.",
      "source": "https://docs.growthbook.io/api/experiments/operation/updateExperiment.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/growthbook"
    },
    {
      "slug": "harness-fme",
      "name": "Harness Feature Management \u0026 Experimentation",
      "company": "Harness Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "fme_feature_flag update sends a merge-patch, definitions are created and updated, and segment keys are added by execute actions, but legacy and Harness-native scoping differ per resource, identity writes aren't implemented natively, and change requests can hold writes.",
      "source": "https://github.com/harness/mcp-server/blob/HEAD/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/harness-fme"
    },
    {
      "slug": "matomo",
      "name": "Matomo",
      "company": "InnoCraft Limited",
      "grade": "B",
      "fit": "caveat",
      "why": "The AbTesting API manages experiments, but Matomo has no feature flags or percentage rollouts by targeting rule, and the create and start parameters couldn't be read.",
      "source": "https://developer.matomo.org/api-reference/api",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/matomo"
    },
    {
      "slug": "mixpanel",
      "name": "Mixpanel",
      "company": "Mixpanel, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Create- and Update-Feature-Flag and Update-Experiment (which manages lifecycle) exist, but audience and cohort targeting aren't supported through the MCP, and whether updates are partial isn't stated.",
      "source": "https://docs.mixpanel.com/docs/mcp.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/mixpanel"
    },
    {
      "slug": "mostly-good-metrics",
      "name": "Mostly Good Metrics",
      "company": "Mostly Good Metrics",
      "grade": "E",
      "fit": "caveat",
      "why": "create_experiment, update_experiment, start_experiment and stop_experiment cover the lifecycle, but there are no feature flags, targeting rules or rollout percentages, only variants.",
      "source": "https://docs.mostlygoodmetrics.com/integrations/mcp-server",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mostly-good-metrics"
    },
    {
      "slug": "optimizely",
      "name": "Optimizely Experimentation",
      "company": "Optimizely North America Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Ruleset updates take JSON Patch and an enable endpoint turns a ruleset on, but the MCP's exp_manage_entity_lifecycle asks the person to confirm every live change, so unattended runs need the REST API.",
      "source": "https://docs.optimizely.com/feature-experimentation/api/update-the-ruleset-for-a-flag-in-an-environment.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/optimizely"
    },
    {
      "slug": "posthog",
      "name": "PostHog",
      "company": "PostHog Inc. (formerly Hiberly Inc.)",
      "grade": "B",
      "fit": "caveat",
      "why": "create-feature-flag, update-feature-flag, release-condition rollout and experiment-launch cover it, but feature-flag-rules-update replaces all rules, and the schema rejected a multi-value equals the UI accepts (acc-06, open).",
      "source": "https://posthog.com/docs/model-context-protocol/tools.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/posthog"
    },
    {
      "slug": "statsig",
      "name": "Statsig",
      "company": "Amplitude, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Gates and experiments can be created and started (PUT /experiments/{id}/start), but gate_update and experiment_update replace the whole resource, partial edits need discover_tools, and updates require a confirmation.",
      "source": "https://docs.statsig.com/api/content/integrations/mcp/tool-reference",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/statsig"
    },
    {
      "slug": "fullstory",
      "name": "Fullstory",
      "company": "Fullstory, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "No feature flags or experiments; the MCP only creates drafts of segments, metrics, funnels, journeys and dashboards.",
      "source": "https://developer.fullstory.com/mcp/tools-reference/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/fullstory"
    },
    {
      "slug": "heap",
      "name": "Heap",
      "company": "Content Square, Inc.",
      "grade": "D",
      "fit": "no",
      "why": "No feature flags or experiments.",
      "source": "https://developers.heap.io/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/heap"
    },
    {
      "slug": "openpanel",
      "name": "OpenPanel",
      "company": "OpenPanel AB",
      "grade": "B",
      "fit": "no",
      "why": "No feature flags or experiments.",
      "source": "https://openpanel.dev/docs/mcp",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/openpanel"
    },
    {
      "slug": "pendo",
      "name": "Pendo",
      "company": "Pendo.io, Inc.",
      "grade": "E",
      "fit": "no",
      "why": "No feature flags, and guide experiments are listed, not created or started, over MCP.",
      "source": "https://support.pendo.io/hc/en-us/articles/42476316360731-Pendo-MCP-tools-for-AI-agents",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/pendo"
    },
    {
      "slug": "rudderstack-mcp",
      "name": "RudderStack MCP",
      "company": "RudderStack, Inc.",
      "grade": "C",
      "fit": "no",
      "why": "No feature flags or experiments.",
      "source": "https://www.rudderstack.com/docs/ai-features/rudderstack-mcp/tool-reference/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/rudderstack-mcp"
    },
    {
      "slug": "userpilot",
      "name": "Userpilot",
      "company": "Userpilot, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "No feature flags or experiments in the MCP or API reference.",
      "source": "https://docs.userpilot.com/ai/userpilot-mcp-server.md",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/userpilot"
    },
    {
      "slug": "woopra",
      "name": "Woopra",
      "company": "Woopra, Inc.",
      "grade": "D",
      "fit": "no",
      "why": "No feature flags or experiments.",
      "source": "https://docs.woopra.com/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/woopra"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "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": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "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"
  },
  "useCase": {
    "accounts": 8,
    "after": [
      "product-analytics.experiment-readout"
    ],
    "area": "business",
    "asks": [
      "create a flag for the new checkout",
      "turn this flag on for users in Canada",
      "roll out to 20 per cent",
      "launch an experiment on iOS and Android",
      "add these emails to the flag"
    ],
    "before": [
      "code.add-flag-check"
    ],
    "blockers": [
      "an update replaces the whole resource and resets targeting",
      "the MCP schema rejects targeting the UI accepts",
      "starting an experiment only possible in the UI",
      "flag creation demands an experiment data source",
      "writes held for human approval or change requests"
    ],
    "capabilities": [
      "analytics.flags",
      "analytics.experiments"
    ],
    "category": "product-analytics",
    "categoryName": "Product analytics \u0026 experimentation",
    "checked": "2026-11-15",
    "companies": {
      "fit": 1,
      "fitWithLimit": 10,
      "tagged": 12
    },
    "competition": "one",
    "fits": [
      "launchdarkly"
    ],
    "fitsWithLimit": [
      "amplitude",
      "countly",
      "flagsmith",
      "growthbook",
      "harness-fme",
      "matomo",
      "mixpanel",
      "mostly-good-metrics",
      "optimizely",
      "posthog",
      "statsig"
    ],
    "id": "product-analytics.flag-experiment-change",
    "listings": {
      "caveat": 11,
      "no": 7,
      "notRead": 0,
      "tagged": 13,
      "unchecked": 0,
      "yes": 1
    },
    "name": "Create, target or roll out a feature flag or experiment",
    "status": "draft",
    "success": "The flag or experiment exists with precisely the requested targeting and split, other fields unchanged, and (for experiments) a running state with a start date, confirmed by a read-back. Measured: this takes at most 4 calls.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/product-analytics.flag-experiment-change.json",
    "weight": 15,
    "weightBasis": "8 of 55 account links, nearly all GitHub issues about writes that silently did the wrong thing"
  }
}
