posthog-mcp
Related Servers
Alternatives to posthog-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables interaction with PostHog's product analytics platform through natural language, allowing users to manage feature flags, view errors, and access other platform features.25 npm1MIT
- AlicenseAqualityFmaintenanceConnects AI assistants to PostHog to query events, persons, insights, dashboards, feature flags, cohorts, and experiments through the Model Context Protocol.1335 npmMIT
- AlicenseBqualityDmaintenanceEnables interaction with PostHog analytics platform, allowing users to list projects, create annotations, and search insights through natural language in Claude Desktop.5MIT
- AlicenseNot gradedqualityDmaintenanceEnables interaction with PostHog product analytics API, supporting project listing, event queries, insight analysis, feature flag management, and annotation creation.MIT
- AlicenseBqualityAmaintenanceEnables AI agents to query self-hosted product analytics, investigate changes with evidence and coverage checks, and use optional management tools for saved reports, goals, and keys.201MIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to explore a project's captured events and properties, then run trend, funnel and retention analyses and create or list saved insights. Tools are model-oriented, returning trimmed, budgeted results and actionable errors, with the project resolved from the API key or bearer token rather than passed as an argument.MIT
TDQS
Scored across 5 tools
Each tool targets a distinct PostHog resource: feature flags, insights, persons, events, and trends. There is no overlap in functionality, making it clear which tool to use for each task.
The naming pattern is inconsistent: three tools use 'get_', one uses 'list_', and one uses 'query_'. Furthermore, 'get_insights' suggests a single insight but actually retrieves by ID, while 'get_feature_flags' returns a list. This could cause confusion.
With five tools, the server covers essential read operations for a PostHog integration. The count is reasonable but slightly on the low side for a comprehensive analytics platform; it could include a few more tools.
The tool surface is entirely read-only, missing create, update, and delete operations for all resources. There are no tools for managing cohorts, experiments, or dashboards, leaving significant gaps for typical PostHog workflows.