PostHog + Claude

How to connect PostHog to Claude

Set up PostHog for Claude with Agent200, then check which tools are available to your agent.

On this page
  1. Overview
  2. Before you start
  3. Setup steps
  4. Test your connection
  5. Instructions for AI agents
  6. PostHog tools
  7. How it works
  8. Troubleshooting

Overview

This guide connects PostHog to Claude through Agent200's MCP server. When you finish, Claude can search, read and act in PostHog with the tools Agent200 provides, whenever a request needs them.

You add one MCP server to Claude with your Agent200 API key. Your PostHog account is connected through managed OAuth: you approve access once on PostHog's own page, and Agent200 keeps the connection working.

Connector
PostHog
Works with
Claude ยท Agent app, through MCP
Authentication
Managed OAuth, per end user
Tools
7 tools
MCP server
https://api.agent200.com/mcp/

Before you start

  • An Agent200 API key. Create one on the API keys page of the dashboard.
  • PostHog enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
  • An end user with a PostHog account. They approve access once, on PostHog's own page.
  • Claude, with custom MCP servers allowed. Custom connectors are on every Claude plan (Free: one). Sending an API key uses the Request headers option, a beta that only some accounts have; on Team and Enterprise an Owner adds the connector for everyone.

Connect PostHog to Claude

  1. 1

    Step 1: Create your Agent200 API key

    Open the API keys page in the Agent200 dashboard and choose Create an API key. You add it to Claude in the next step, as "Authorization: Bearer <your key>". One key covers PostHog and every other connector enabled for your project. Keep it out of chats and source control.

  2. 2

    Step 2: Open Connectors in Claude

    On a Free, Pro, Max or Ultra plan, go to Customize > Connectors. On Team or Enterprise, an Owner goes to Organization settings > Connectors; members then find the connector under Customize > Connectors.

  3. 3

    Step 3: Add a custom connector

    Select Add, then Add custom connector. Enter a name, Agent200, and the remote MCP server URL, then choose Continue.

  4. 4

    Step 4: Send your key as a request header

    Under Authentication choose No sign-in. Open Request headers, pick authorization, enter Bearer followed by a space and your key, mark it Required and choose Add. Claude sends the value exactly as typed.

    Add custom connector
    MCP: Claude custom connector (URL and request header)
    Remote MCP server URL:  https://api.agent200.com/mcp/
    Authentication:         No sign-in
    Request header name:    authorization
    Value:                  Bearer YOUR_AGENT200_API_KEY
  5. 5

    Step 5: Turn it on in a chat

    In a chat, select + > Connectors and turn Agent200 on. Ask Claude to list the Agent200 tools to check the connection; Claude asks before a tool runs the first time.

  6. 6

    Step 6: Connect your PostHog account

    The first time you ask Claude for something in PostHog, Agent200 returns an authorization link. Open it and approve access on PostHog's own page. Agent200 stores the connection and keeps it working; your password never reaches Claude or Agent200.

Test your connection

Run one request to check everything is wired up.

Ask

Ask Claude to list the Agent200 tools available for PostHog, including which are read-only.

What should come back

  • A list of the PostHog tools enabled for this Agent200 project, with their names and descriptions. If no tools appear, check that the connector is available to the project and its tools are enabled.

If no tools appear, check your Agent200 project access for PostHog and make sure its tools are enabled. Tool availability depends on your project setup.

Get your API key

Create a key in the Agent200 dashboard. It reaches PostHog and every other connector enabled for your project.

Read the SDK docs

Instructions for AI agents

Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect PostHog to Claude.

Agent brief
Goal: connect PostHog to Claude with Agent200, through its MCP server.
Guide: https://www.agent200.com/connectors/posthog/framework/claude/

1. The user needs an Agent200 API key. If they have none, send them to https://agent200.com/platform/apikeys/ to choose "Create an API key". They paste it into Claude's settings themselves: never ask for it in chat and never write it into files you share.
2. Make sure PostHog is enabled for their project in the Agent200 dashboard (Connectors), with the tools the task needs.
3. Add Agent200's MCP server to Claude: URL https://api.agent200.com/mcp/, transport streamable HTTP, header "Authorization: Bearer <the user's Agent200 API key>". Follow the setup steps on the guide page for Claude's exact menus or commands.
4. The first PostHog request returns an authorization link if the user has not connected PostHog yet: show it to them and continue once they have approved access on PostHog's own page.
5. Check it works with this request: "Ask Claude to list the Agent200 tools available for PostHog, including which are read-only."
   What should come back:
   - A list of the PostHog tools enabled for this Agent200 project, with their names and descriptions. If no tools appear, check that the connector is available to the project and its tools are enabled.
6. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in PostHog, then retry.

The whole guide is also available as Markdown, for agents and LLMs: /connectors/posthog/framework/claude.md

PostHog tools Claude can call

  • Run a query

    Read
    posthog_run_query

    Run a HogQL query on the project's events.

  • List insights

    Read
    posthog_list_insights

    List the saved insights in a project.

  • List dashboards

    Read
    posthog_list_dashboards

    List the dashboards in a project.

  • List persons

    Read
    posthog_list_persons

    Search and list persons.

  • List feature flags

    Read
    posthog_list_feature_flags

    List the feature flags in a project.

  • Create a feature flag

    Write
    posthog_create_feature_flag

    Create a new feature flag.

  • Update a feature flag

    Write
    posthog_update_feature_flag

    Change a flag's rollout or turn it on or off.

How it works

  1. 01

    You ask Claude

    In your own words, for something in PostHog.

  2. 02

    Claude picks a tool

    It sees the PostHog tools on the Agent200 MCP server and calls the one the request needs.

  3. 03

    Agent200 runs the call

    With your own PostHog connection, within the tools and scopes your project allows.

  4. 04

    Claude answers

    It gets the result back from the MCP server and uses it in its reply or its next step.

Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's PostHog account.

Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and PostHog enforces what its API grants.

Troubleshooting

There is no Request headers section

Request headers are a Claude beta that only some accounts have. Without it, Claude cannot send an API key to a custom connector: use Claude Code, or the Agent200 SDK in your own agent.

Claude cannot reach the server

Check the header value is Bearer, a space, then your key, and that the URL is exactly the Agent200 MCP server address.

A Team or Enterprise member cannot add the connector

Only an Owner adds custom connectors, in Organization settings > Connectors. Members then connect it under Customize > Connectors.

You created a new API key

Claude does not let you edit a connector’s authentication. Remove the Agent200 connector and add it again with the new key.

Claude does not use the PostHog tools

Open + > Connectors in that chat and check Agent200 is on, and that no tool is set to Blocked under Customize > Connectors. Naming PostHog in the request also helps.

Claude shows a PostHog authorization link

You have not connected PostHog yet, or the connection needs to be approved again. Open the link, approve access on PostHog's own page, then ask Claude again.

A tool call is refused or returns less than expected

Agent200 runs only what your project allows. Check that PostHog and the tools you need are enabled in the dashboard's Connectors settings, and that you granted PostHog the access the task needs.

The API key was pasted into a chat or committed

Create a new key on the API keys page, replace it in Claude's MCP settings, and stop using the old one. Paste the key only into Claude's settings, never into a chat.

Use PostHog with another framework

200 OK

PostHog, connected to Claude.
One SDK. One API key.

Agent200 handles the OAuth, the tokens and every tool call. You keep your agent, your model and your code.

Book a demo.
See it in action.

Tell us who you are, then pick a time for a 1:1 session with an expert from our team.

We use your details only to email you about Agent200. See the Privacy Policy.

Pick a time. We'll take it from there.

A 1:1 session with an expert from our team, about what you are building.

Open in Calendly (opens in a new tab)