M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
P

PostHog

Official
Open-source product analytics platform PostHog, steerable from Claude Code, Cursor, and other MCP-compatible agents.
How to install ↓ Compare GitHub source repository ↗
Category
Other #196 of 230
Stars
★ 40.6k Very popular
Runtime
Hosted (no local runtime)
Credentials
API key / credential required
License
Other / unspecified
Last commit
41FMRS · D

PostHog is a broad, open-source product analytics platform whose README mentions MCP connectivity into Claude Code, Cursor, and other MCP-compatible agents, but the source material does not provide a specific MCP tool list, transport details, or installation config, so those fields are left without fabricated evidence.

Strongest · Maintenance 17/20 Weakest · Reliability 4/20

Reliability
4/20
Security and permissions
8/20
Maintenance
17/20
Documentation
7/20
Setup experience
5/20
Why each score
Reliability 4/20
No manifest is cached, and the README provides no MCP tool list, no initialization/handshake description, and no test or CI evidence specific to the MCP server. The repository is PostHog's large monolithic codebase; 'server path: repository root' does not pinpoint the MCP server's actual location, so there is no way to verify a clean start or that declared tools match real behavior. Per the static calibration rule, reliability is capped at 12 without verifiable execution evidence (real CI workflows plus tests covering key paths), and here that evidence is essentially absent, so it is scored 4.
Security and permissions 8/20
The README contains no discussion of credential handling, permission scoping, confirmation for dangerous operations, or data boundaries, and the missing manifest means the MCP's access scope to PostHog cloud accounts/API keys cannot be verified. No red-line issue (malware, hardcoded secrets, unconfirmed destructive defaults) is evident, but absent evidence must be treated as a deduction rather than assumed best-case least-privilege design, so it is scored 8.
Maintenance 17/20
PostHog is a highly active open-source project with 37,510 stars and 5,612 open issues; the README shows commit-activity badges, closed-issue counts, clear contribution guidelines, a roadmap link, and an explicit MIT license (except the ee directory, which links its own license), plus a separate FOSS-only repository. Governance and update paths are clear, though the repo metadata's NOASSERTION license field is a minor inconsistency with the README's MIT claim, so it is not given full marks and scored 17.
Documentation 7/20
The README is largely product marketing, listing feature areas and links to an external docs site, but it contains no installation steps, authentication method, tool parameters, rate limits, or troubleshooting guidance specific to the MCP server itself — only a single 'connect the MCP' pointer to an external page. This is insufficient on-page evidence for a user to configure and debug the MCP independently, so it is scored 7.
Setup experience 5/20
The README only offers a one-line Docker hobby self-host command for the entire PostHog platform, with no MCP-specific installation steps or client configuration examples (e.g., Claude Desktop/Cursor config snippets). Per the static calibration rule, setup cannot exceed 15 without real CI and test evidence, and here there isn't even an MCP-specific setup path, so evidence is severely lacking and it is scored 5.

Static review · not runListed 2026-08-06

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

  • Teams already using PostHog for product analytics, feature flags, or experiments who want to control it from an AI agent
  • Developers who want product signals (errors, rage clicks, etc.) surfaced directly inside Claude Code, Cursor, or similar agent environments

Not for

  • Users who only need a narrow, single-purpose MCP tool (e.g., pure database or file-system access) — PostHog's surface area is broad
  • Users requiring a strictly FOSS codebase — the `ee` directory in this repo is under a separate, non-MIT license
  • Self-hosted deployments needing vendor support — the README explicitly states no customer support or guarantees are provided for open-source deployments

Required permissions

  • Access to data within a PostHog project/account, including events, session recordings, feature flags, experiments, error tracking, surveys, and data warehouse records
  • Write access to modify project configuration if using the agent to create or change feature flags/experiments

Risks and side effects

  • PostHog aggregates substantial user behavioral and product data; agent access to it carries exposure risk for sensitive information (user identifiers, session content)
  • Repository licensing is mixed (MIT for the main repo, separate proprietary license for the `ee` directory) — confirm which features are covered before relying on them in production
  • Self-hosted open-source deployments are explicitly unsupported by the vendor and are recommended only up to roughly 100k events/month before needing to migrate to Cloud

Setup

Before you start

Runtime：Hosted (no local runtime)

The README does not give explicit MCP installation commands or a client config JSON. Based on what is documented: 1) sign up for PostHog Cloud (US or EU); 2) for self-hosting, run the repo's one-line hobby deploy script (bin/deploy-hobby) on Linux with Docker (4GB memory recommended); 3) follow the official instructions at posthog.com/mcp to connect the MCP into Claude Code, Cursor, or another MCP-compatible client. No further detail on MCP-specific setup (auth, keys, config file) is present in the source material.

Check that it works

After connecting the PostHog MCP (see https://posthog.com/mcp) to an MCP-compatible client such as Claude Code or Cursor, confirm the PostHog tools appear in the client's tool list to verify the connection.

Troubleshooting

  1. For self-hosting issues, consult the official self-hosting and troubleshooting docs referenced in the README
  2. If the one-line hobby deploy script (`bin/deploy-hobby`) fails, verify Docker is installed and the recommended 4GB memory is available
  3. For MCP connection issues with Claude Code/Cursor, refer to the official instructions at posthog.com/mcp — the repository README does not include MCP-specific troubleshooting steps

Things to try

Once connected, you can ask your AI assistant things like:

  • Connect the PostHog MCP to Claude Code and show me my product analytics.
  • Use PostHog to list my current feature flags.
  • Check my recent error tracking issues in PostHog.

Use cases

Querying product analytics, web analytics, or session replay data through an agent
Having an agent turn signals like errors or failed queries into diagnostic reports or fix suggestions ('self-driving mode')
Creating or adjusting feature flags and experiments via an agent
Reviewing logs or data warehouse records from within a coding/agent workflow to help diagnose issues

Overview

PostHog is an open-source platform for building 'self-driving products,' combining product analytics, web analytics, session replay, feature flags, experiments, error tracking, logs, surveys, data warehouse/pipelines (CDP), and AI observability. Per the repository README, in addition to Slack, the web app, and PostHog Desktop, users can connect PostHog via MCP (posthog.com/mcp) to bring it into Claude Code, Cursor, or any MCP-compatible agent. The README does not enumerate specific MCP tools or provide a client configuration example, so this profile reflects only what is explicitly stated in the source material.

Similar servers

BioMCP 75 · B

One binary. One grammar. Evidence from the biomedical sources you already trust.

★ 672 · Tools 11 Compare with this →
Compare with other MCP servers

Source revision 81cc6b95d833 Data synced 2026-11-04 Read the FMRS scoring method