PostHog MCP server
Inspect saved insight metadata and feature-flag state with Arc0’s PostHog tools. Flag activation is an explicit write that can immediately affect targeted users. Connect through Arc0 to use the actions your identity is allowed to call.
Working with PostHog
For a rollout check, posthog.list_feature_flags finds non-archived flags in the configured project. posthog.get_feature_flag reads one flag by numeric ID so the agent can report its current active state. This is configuration inspection, not an evaluation of what a particular user sees.
posthog.update_feature_flag_active changes whether that flag is active. The effect reaches targeted users immediately, so confirm the flag and intended state before executing it. Read the flag afterward, particularly when the response is lost. Repeating a toggle without checking the current value can make incident handling more confusing.
posthog.list_insights and posthog.get_insight inspect saved insight metadata rather than calculating or returning analysis results. For a specific support investigation, posthog.list_persons accepts one exact distinct ID and returns structural identifiers. posthog.list_events is limited to that subject, a window within seven days, and at most ten events. Its underlying endpoint is deprecated, so it is not a basis for a new bulk export workflow. The current tools do not run arbitrary analytics queries or capture product events.
Official MCP reference: PostHog documentation.
Agent workflows for PostHog.
Find a saved insight
Use posthog.list_insights and posthog.get_insight to inspect saved metadata without recalculating analytics.
Review a flag’s state
Use posthog.list_feature_flags and posthog.get_feature_flag to check active settings in the connected project.
Toggle an approved flag
Use posthog.update_feature_flag_active only after confirming the exact flag and intended production effect.
Check one known subject
Use posthog.list_persons for an exact distinct ID and posthog.list_events for bounded structural event metadata.
7 PostHog actions, graded by risk.
These actions come from the Arc0 registry. Your identity, provider permissions and Arc0 policies determine which actions can run.
read
6Look things up, subject to your permissions.
- posthog.list_insightsList insights
Use when locating saved insight metadata without recalculating analytics. Not for retrieving results; basic metadata pages contain at most 20 insights.
- posthog.get_insightGet insight
Use when checking one saved insight’s metadata, not its results. A large cached result can exceed the 1 MiB response cap (502 provider_response_too_large); use list_insights for metadata pages.
- posthog.list_feature_flagsList feature flags
Use when inspecting flag metadata and active states in the connected project. Not for evaluating a user; archived flags are excluded.
- posthog.get_feature_flagGet feature flag
Use when checking a flag by numeric ID or reading back an uncertain update. Not for evaluating what a particular user sees.
- posthog.list_personsList persons
Use when looking up one exact distinct ID: returns at most one person’s structural identifiers and timestamps. Not a people search; no names or profile properties.
- posthog.list_eventsList events
Use when checking event IDs and timestamps for one exact subject within seven days. At most 10 events. Not for exports or new integrations: this endpoint is deprecated; use vendor batch exports for bulk data.
write
1Create and change things. Allow, or ask the user first.
- posthog.update_feature_flag_activeUpdate feature flag active
Use when the user confirms the exact flag to toggle: it immediately changes what every targeted user sees in production. Not for testing or archived flags. If the outcome is unknown, read the flag before retrying.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Control access to PostHog.
Connect the intended PostHog account, authorize your AI client and set policies for its tools.
Provider permissions and Arc0 policy both apply. Allow reads, require approval for selected writes, or deny destructive actions. The audit log records execution decisions.
Configure policies and approvalsExample policy choices
- Read actions: allow where authorized
- posthog.update_feature_flag_active: require approval
Arc0 MCP endpoint: https://api.arc0.ai/mcp
How PostHog connects.
Connect PostHog using API key or OAuth. OAuth grants the provider scopes shown during consent; API keys and other credentials retain the permissions configured at the provider. Arc0 stores credentials in its encrypted vault and does not pass them to the model. Disconnect to remove access through Arc0; revoke a key at the provider to invalidate it there. Token refresh and provider-side revocation depend on the authentication lane and provider.
The connection serves authorized calls through Arc0 MCP and REST. How Arc0 handles credentials →
- AUTH
- API key · OAuth
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use PostHog with your AI client.
Sign in to Arc0 and connect PostHog in My apps. Then authorize your AI client separately. It only receives tools and accounts allowed for that identity.
PostHog with Claude
Claude Desktop + Claude Code
- In Claude Desktop, add Arc0 through the remote MCP settings and use OAuth. Follow the generic remote-client steps if your account’s interface differs.
- For Claude Code, run the command below. Open /mcp, select Arc0, and authenticate in your browser. Select your workspace and review access.
- Check the connection with claude mcp get arc0.
claude mcp add --transport http --scope user arc0 https://api.arc0.ai/mcpFull MCP setup and troubleshootingPostHog with ChatGPT
ChatGPT on the web
- Open Plugins in ChatGPT, select the plus button, then Add custom MCP server.
- Name it Arc0, enter the server URL below, and choose OAuth. Use dynamic client registration if asked; no Arc0 API key is needed.
- Review the notice and select Create as a plugin. Complete Arc0 sign-in, workspace selection and consent, then install and select the plugin in your conversation. Labels and access vary by account; managed workspaces may require administrator approval.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingPostHog with OpenAI Codex
Codex app + CLI
- Run the registration command below. The app and CLI share ~/.codex/config.toml.
- Complete browser OAuth, choose your Arc0 workspace, and review access. If authentication does not start, run codex mcp login arc0.
- Check codex mcp list, then open a new Codex chat. Inspect an existing arc0 entry before changing it.
codex mcp add arc0 --url https://api.arc0.ai/mcpFull MCP setup and troubleshootingPostHog with Cursor
Remote MCP setup
- Add Arc0 in your client’s remote MCP settings using the server URL below.
- Choose OAuth, sign in to Arc0, select the intended workspace and review access.
- Confirm the server is connected and start with an allowed read. These are generic remote-MCP steps; consult your client’s settings for its current interface.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingPostHog with VS Code
Remote MCP setup
- Add a remote HTTP MCP server named Arc0 using the URL below.
- Use OAuth and finish Arc0 sign-in, workspace selection and consent.
- Confirm discovery succeeds before requesting a read. These are generic remote-MCP steps; client UI and availability may differ.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingPostHog with Any MCP client
Streamable HTTP
- Use a client that supports remote MCP over Streamable HTTP. Add the server URL below and choose OAuth.
- For a client without OAuth, use a self-bound API key with execute permission in the X-API-Key header. Store it in secret storage or an environment variable, outside source control. Never send both an API key and an OAuth bearer token.
- Use the MCP clients guide for the SDK transport example and Embedded identity for business-managed end users.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingAfter setup, ask your agent to find an allowed read action, load its schema, and execute it on the intended account. Check Activity for the receipt. A connected MCP client alone does not confirm a successful provider call.
PostHog and Arc0, answered.
Is there an official PostHog MCP server, and how does Arc0 differ?
Yes. PostHog hosts an official MCP server. Arc0’s current REST tools are narrower: saved metadata, flag state and activation, and tightly bounded subject checks.
Which permissions does Arc0 need for PostHog?
OAuth or a personal API key uses user:read, insight:read, feature_flag:read, feature_flag:write, person:read and query:read. Use the selected US or EU cloud project; project capture tokens and self-hosted origins are not supported by this version.
Does this work with Claude, ChatGPT, Codex and Cursor?
Yes, through Arc0 MCP when your Claude, ChatGPT, Codex, or Cursor client supports remote MCP and your account permits it. Connect the app in Arc0 and configure your client using the Arc0 setup guide. App permissions still apply.
How are credentials stored, refreshed and revoked?
Credentials are encrypted in Arc0’s vault. Arc0 stores the personal key or OAuth credentials. OAuth access can refresh; personal keys cannot. Disconnect removes local access; remove the authorization or key in PostHog for provider-side revocation, especially where a grant is shared.
What happens with rate limits or errors?
PostHog limits API calls, and a large cached insight can exceed Arc0’s response cap. Use insight listing for small metadata pages. Arc0 reports errors; after an uncertain flag update, read the flag before trying again.
What is the availability of these PostHog tools?
These tools are available. Connect the app in Arc0 and authorize your AI client. The action list describes the current implementation.
Plug PostHog into your agent.
PostHog MCP server: 7 actions including list insights, get insight, list feature flags. Connect through Arc0.
Free to build · MCP + REST · Audit log on every plan
PostHog and its logo are trademarks of their respective owners. Arc0 is not affiliated with or endorsed by PostHog.