Mixpanel MCP server for Claude, ChatGPT, Claude Code and Cursor

How to connect Mixpanel

1. 1
   Click Connect Mixpanel free and paste your Mixpanel API key.
2. 2
   Add ContextGate to your AI app:

   ClaudeChatGPTClaude CodeCursorGitHub CopilotCodexGemini CLIOther

   1. 1

      In Claude, open Settings → Connectors and click Add custom connector.

   2. 2

      Name it ContextGate and paste this URL:

      https://api.contextgate.ai/mcp

   3. 3

      Click Add, then Connect, and sign in to ContextGate.

   4. 4

      In a chat, turn ContextGate on from the + menu → Connectors. Cowork and the desktop app use the same connectors.

   The full Claude guide

   1. 1

      In ChatGPT settings, open Apps & Connectors (or Connectors) → Advanced and turn on Developer mode.

   2. 2

      Create a connector, choose OAuth, and paste this URL:

      https://api.contextgate.ai/mcp

   3. 3

      Sign in to ContextGate when ChatGPT redirects you, then pick the connector in a chat.

   The full ChatGPT guide

   1. 1

      Run this in a terminal:

      claude mcp add --transport http contextgate https://api.contextgate.ai/mcp

   2. 2

      Start Claude Code, run /mcp, choose contextgate and sign in to ContextGate.

   The full Claude Code guide

   Add to Cursor

   1. 1

      Click Add to Cursor, or add this to ~/.cursor/mcp.json:

      {
        "mcpServers": {
          "contextgate": {
            "url": "https://api.contextgate.ai/mcp"
          }
        }
      }

   2. 2

      In Cursor Settings → MCP, sign in to ContextGate when Cursor asks.

   The full Cursor guide

   Add to VS Code

   1. 1

      Click Add to VS Code, or add this to .vscode/mcp.json:

      {
        "servers": {
          "contextgate": {
            "type": "http",
            "url": "https://api.contextgate.ai/mcp"
          }
        }
      }

   2. 2

      Start the server when VS Code asks, sign in to ContextGate, and use it from Copilot Chat in Agent mode.

   The full GitHub Copilot guide

   1. 1

      Run this in a terminal:

      codex mcp add contextgate --url https://api.contextgate.ai/mcp

   2. 2

      Then sign in to ContextGate:

      codex mcp login contextgate

   The full Codex guide

   1. 1

      Run this in a terminal:

      gemini mcp add --transport http contextgate https://api.contextgate.ai/mcp

   2. 2

      In Gemini CLI, run /mcp auth contextgate and sign in to ContextGate.

   The full Gemini CLI guide

   1. 1

      Add a remote (HTTP) MCP server with this URL:

      https://api.contextgate.ai/mcp

   2. 2

      Apps that support MCP sign-in ask you to sign in to ContextGate the first time they connect.

   3. 3

      An app that can't sign in can use a workspace API key instead: create one under API keys and add ?api_key=<your key> to the URL.

   More on adding it to any MCP app
3. 3
   Ask your AI app to use Mixpanel, then open Activity to see the call.

What you get with Mixpanel and ContextGate

• Your AI apps can use MixpanelClaude, Cursor, ChatGPT and other AI apps reach Mixpanel through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Mixpanel tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Mixpanel tools

Examples of what your AI apps can do in Mixpanel. You'll see the exact list of tools after you connect it.

• aggregate_event_countsGet aggregate event counts over time. supports different types of aggregation: general, unique, average, sum.
• get_all_projectsGet all projects associated with the authenticated mixpanel account. returns project details including name, permissions, role, domain, and other configuration details.
• jql_queryExecute a custom jql (javascript query language) query against mixpanel's query api. key constraints: - 60 queries/hour, max 5 concurrent queries. - 2-minute execution timeout. - 5 gb data processing limit, 2 gb output limit. - no remote network requests (xmlhttprequest) are allowed inside the jql script.
• list_cohortsGet list of all cohorts in a mixpanel project. returns cohort details including name, id, count, description, creation date, and visibility. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• list_funnelsGet the names and funnel ids of your funnels. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• profile_event_activityGet event activity feed for specified users from mixpanel query api. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• query_funnelGet data for a funnel. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• query_insightGet data from your insights reports. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• query_profilesQuery user or group profile data from mixpanel. returns list of profiles that match specified parameters. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• query_retention_reportGet cohort analysis data. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• query_segmentationGet data for an event, segmented and filtered by properties. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• aggregated_event_property_valuesGet unique, total, or average data for a single event and property over days, weeks, or months. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• aggregate_eventsGet aggregate event counts over time. supports different types of aggregation: general, unique, average, sum.
• query_frequency_reportGet data about how frequently users are performing events. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. example response with unit="day" and addiction unit="hour": { "2012-01-01": [305, 107, 60, 41, ...], # users who did event in 1+ hours, 2+ hours, etc. "2012-01-02": [495, 204, 117, 77, ...], "2012-01-03": [671, 324, 176, 122, ...] }
• query_numeric_averageAverages an expression for events per unit time. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. example response: { "status": "ok", "results": { "2024-01-01": 25.5, "2024-01-02": 32.75, "2024-01-03": 28.25 } }
• query_numeric_segmentationGet data for an event, segmented and filtered by properties, with values placed into numeric buckets. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• query_numeric_sumSums an expression for events per unit time. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. example response: { "status": "ok", "computed at": "2024-01-20t12:00:00", "results": { "2024-01-01": 150.5, "2024-01-02": 245.75, "2024-01-03": 198.25 } }
• todays_top_eventsGet the top events for today, with their counts and the normalized percent change from yesterday. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• top_event_propertiesGet the top property names for an event. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• top_event_property_valuesGet the top values for a property. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.
• top_eventsGet a list of the most common events over the last 31 days. the query api has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries.