Connect PostHog to Claude. For your whole team.
The official PostHog MCP runs on a personal API key, and the key preset its docs point to grants write access on nearly everything: feature flags, persons, recordings. Loopthink holds one read-only key pinned to one project, gives every Claude user in your team their own login, and lets Product, Engineering and Management ask the questions their role allows.
Free for your own server · Team from €99 · EU-hosted
PostHog in a chat client, today.
Today a team that wants PostHog in an AI client either invites everyone to the project or passes one personal API key around. Person profiles carry emails and distinct IDs, so a shared key sends them to the model with every question. And the MCP server can create, enable and disable feature flags, so a typo in a chat becomes a change in production.
One matrix for PostHog. Roles across, tools down.
| Tool | Product | Engineering | Management |
|---|---|---|---|
| Insights & trends | Product may use Insights & trends | Engineering may use Insights & trends | Management may use Insights & trends |
| Events & persons | Product may use Events & persons | Engineering may not use Events & persons | Management may not use Events & persons |
| Feature flags | Product may use Feature flags | Engineering may use Feature flags | Management may not use Feature flags |
| Session recordings | Product may use Session recordings | Engineering may not use Session recordings | Management may not use Session recordings |
| Error tracking | Product may use Error tracking | Engineering may use Error tracking | Management may not use Error tracking |
| Write actions off by default | Product may not use Write actions | Engineering may not use Write actions | Management may not use Write actions |
Masked for every role: person emails and distinct IDs, IP addresses, session recording links.
You set this once. Every Claude user in your team gets exactly this.
Once on the PostHog side, once in Claude.
On the PostHog side
Personal API key, read scopes, one project
- 1
PostHog → Settings → Personal API keys → Create personal API key. Skip the MCP Server preset; it grants write scopes.
- 2
Hand-pick read scopes: insight:read, query:read, feature_flag:read, error_tracking:read, session_recording:read, project:read. Organisation and project access: the one project your team uses.
- 3
Copy the key once and paste it into Loopthink. It stays on our side; the team only ever sees tools.
In Claude
Custom connector, OAuth
- 1
An Owner opens Organization settings → Connectors → Add and pastes your Loopthink connector URL. On Free, Pro and Max: Customize → Connectors → + → Add custom connector.
- 2
Each team member opens Customize → Connectors, clicks Connect on Loopthink and signs in once with their own account.
- 3
In a chat, the + menu lists the connector. Toggle it on, ask away. No key, no config file.
Custom connectors are available on Free, Pro, Max, Team and Enterprise. On Team and Enterprise only Owners can add one; every member still connects individually, which is exactly what gives each call its own identity.
Steps checked against the vendor documentation on 17 September 2026: PostHog MCP server · MCP tools · Personal API keys · Get started with custom connectors using remote MCP · Use connectors to extend Claude's capabilities
Loopthink sits in between: it holds the key, shows Claude a normal login, and applies your roles on every call.
Four checks between Claude and PostHog.
- 01
Identify
OIDC/SSO against your own IdP, including Microsoft Entra. The call runs as the person who made it, never as a shared service account.
- 02
Authorize
Per-role, per-tool, read or write. Anything not explicitly granted never shows up in the tool list in the first place.
- 03
Mask
Field-level masking and pseudonymization applied on your side, before the result travels. The model never sees the raw field. Composio, AnythingMCP and both provider tunnels have no field-level masking at all.
- 04
Log
Who asked, which tool, which records, which fields were masked. One audit trail across every AI client, exportable for review.
What people actually ask Claude about PostHog.
- Product
“Which feature flags are rolled out to more than half of users right now?”
- Engineering
“How many errors of type TypeError since yesterday's release, and on which page?”
- Management
“Weekly active users this month versus last month?”
Each question runs as the person who asked it, with that person's role. A Engineering colleague asking the Product question gets the tools their own role allows, not an error, not more.
Four ways to put PostHog into Claude.
| Native PostHog connector | Build it yourself | Enterprise gateways1 | Loopthink | |
|---|---|---|---|---|
| Per-user identity | One personal login, all its rights | Only if you build it | Yes | Yes, every call runs as the person who asked |
| Tool-level roles | No | Your code | Yes | Yes, write off by default |
| Field masking | No | Your code | Not documented | Yes, before the model sees the data |
| Published price | Included in your PostHog plan | Your engineers' time | Contact sales | Free, Team from €99 |
| EU company | No | Whatever you are | Mostly US | Yes, Germany |
Native PostHog connector: Official PostHog MCP with OAuth or a personal API key. One person's key, write on flags, persons and recordings unless you add the read-only switch yourself.
1 MintMCP, MCP Manager, Pomerium
Coming from one of them? Composio alternative · MintMCP alternative · MCP Manager alternative · AnythingMCP alternative
Also for
Connect another system to Claude
Before you connect.
- Does every team member need their own PostHog account?
- No. Loopthink holds one key or token for PostHog. Your people sign in to Loopthink with their own identity, and every call to PostHog is logged under their name. Seats in PostHog stay where they are today.
- Who has to add the connector in Claude?
- One person with the right to add connectors in your Claude workspace, once. After that every team member enables it for themselves. Nobody pastes a key, nobody edits a config file.
- Where does the PostHog key live?
- In Loopthink, encrypted, in the EU. It never reaches Claude and never reaches the people using the connector. Rotate it in PostHog whenever you like and paste the new one once.
- Can somebody write to PostHog from the chat?
- Not unless you switch it on. Write actions are a separate row in the permission matrix and are off for every role by default. If a role needs one write tool, you grant that one tool to that one role.
- What does the model see?
- The result of the tool call, after masking. Fields you mark as personal, such as emails, names or card details, are masked before the answer travels to Claude. The model gets the numbers, not the people.
- Is there an audit trail?
- Yes. Who asked, which tool, which parameters, which fields were masked, when. One log across every client your team uses, exportable for review.
- What does it cost?
- Free for one person and your own MCP server, forever. Team starts at €99 per month and covers the built connector, per-person identity, roles, masking and audit for the whole team. Prices are on the pricing page, no call needed.
- We already run our own MCP server for PostHog. Does it still work?
- Yes. Point it at Loopthink and it inherits the same login, roles, masking and audit. Nothing on the server has to change.
PostHog in Claude, with rules.
One key in Loopthink, one login per person, one matrix that decides who may do what.
Free for your own server · Team from €99 · EU-hosted