Gpt MCP Server

A MCP server which can write report using gpt-researcher.

Local serverstdio

What is the Gpt MCP server?

If you already use Gpt, the gpt mcp server is the piece that lets your assistant work with it directly. A MCP server which can write report using gpt-researcher.

What the server does

This project, gpt-researcher-mcp, is a wrapper extension built on top of the open-source project gpt-researcher. The original gpt-researcher was developed by Assaf Elovic, and I am not the original author.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Token — --token or UV_PUBLISH_TOKEN
  • Debugging — Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the [MCP

Installation

Installation goes through your MCP client rather than a global install: point it at @modelcontextprotocol/inspector on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Credentials and setup notes

Configuration is passed through the environment: GOOGLE_API_KEY, FAST_LLM, SMART_LLM, STRATEGIC_LLM, EMBEDDING, TAVILY_API_KEY, UV_PUBLISH_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Gpt's toolset — Token, Debugging — is a fair guide to whether it matches your workflow. It is maintained by markchiang; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

  • 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.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Token--token or UV_PUBLISH_TOKEN
DebuggingSince MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector).

How to install the Gpt MCP server

{
  "mcpServers": {
    "gpt-researcher": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/inspector"],
      "env": {
        "GOOGLE_API_KEY": "your-value",
        "FAST_LLM": "your-value",
        "SMART_LLM": "your-value",
        "STRATEGIC_LLM": "your-value",
        "EMBEDDING": "your-value",
        "TAVILY_API_KEY": "your-value",
        "UV_PUBLISH_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
GOOGLE_API_KEYCredential the server authenticates with.Yes
FAST_LLMConfiguration value read at startup.Optional
SMART_LLMConfiguration value read at startup.Optional
STRATEGIC_LLMConfiguration value read at startup.Optional
EMBEDDINGConfiguration value read at startup.Optional
TAVILY_API_KEYCredential the server authenticates with.Yes
UV_PUBLISH_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Gpt to Token.
  • Use Gpt to Debugging.

Frequently asked questions

It connects Gpt to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Token, Debugging) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Gpt directly.