IGPT MCP Server

Context Intelligence API that returns structured, cited answers from email threads, attachments, and Google Drive docs in one API call.

Local serverstdioPython

What is the IGPT MCP server?

Context Intelligence API that returns structured, cited answers from email threads, attachments, and Google Drive docs in one API call. Exposed over MCP by the igpt mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

  1. Connect datasources (per user) 2. Retrieve answers using the connected context

Adding it to your client

The server ships on PyPI as igptai, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Its toolset

Everything the assistant can do here goes through one of these:

Configuration

You will need one environment variable: IGPT_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python >= 3.8

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch IGPT.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the igpt mcp server does with a few real requests.

When to reach for it

This sits in the team communication group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. IGPT's toolset — Website, Documentation, Playground and 11 more — is a fair guide to whether it matches your workflow.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
Websitehttps://www.igpt.ai
Documentationhttps://docs.igpt.ai
Playgroundhttps://igpt.ai/hub/playground/
HeaderAuthorization: Bearer <IGPT_API_KEY>
KeyType
typestring
seqnumber
timestampnumber
timestampStartnumber
durationnumber
contextobject
context.qualitystring
context.reasoning_effortstring
context.indexednumber

How to install the IGPT MCP server

{
  "mcpServers": {
    "docs-igpt-ai": {
      "command": "uvx",
      "args": ["igptai"],
      "env": {
        "IGPT_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python >= 3.8
VariableDescriptionRequired
IGPT_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use IGPT to Website.
  • Use IGPT to Documentation.
  • Use IGPT to Playground.

Frequently asked questions

It connects IGPT to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Website, Documentation, Playground, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with IGPT directly.