graphlit-mcp-server

MCP.Pizza Chef: graphlit

Files, web pages, messages and issues from Slack, Discord, Google Drive, Notion, Outlook, Gmail, Jira, Linear, GitHub, Dropbox and more get pulled into a Graphlit project, where documents become readable text and audio or video files are transcribed. Your assistant then searches across all of it at once, and can browse the web without a separate tool. A Graphlit account is required, along with three setup values from its dashboard. The code has been quiet since January 2026.

Files/PDF
Notes
Web/Research

Use This MCP server To

Search my Slack, Drive and Notion in one question Ask what was decided in a meeting recording Pull the key points out of a long PDF I uploaded Find every message about a customer across our tools Turn a folder of documents into something I can question Collect research from web pages into one place

README

npm version smithery badge

Model Context Protocol (MCP) Server for Graphlit Platform

Overview

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. This document outlines the setup process and provides a basic example of using the client.

Ingest anything from Slack, Discord, websites, Google Drive, email, Jira, Linear or GitHub into a Graphlit project - and then search and retrieve relevant knowledge within an MCP client like Cursor, Windsurf, Goose or Cline.

Your Graphlit project acts as a searchable, and RAG-ready knowledge base across all your developer and product management tools.

Documents (PDF, DOCX, PPTX, etc.) and HTML web pages will be extracted to Markdown upon ingestion. Audio and video files will be transcribed upon ingestion.

Web crawling and web search are built-in as MCP tools, with no need to integrate other tools like Firecrawl, Exa, etc. separately.

You can read more about the MCP Server use cases and features on our blog.

Watch our latest YouTube video on using the Graphlit MCP Server with the Goose MCP client.

For any questions on using the MCP Server, please join our Discord community and post on the #mcp channel.

graphlit-mcp-server MCP server

Tools

Retrieval

  • Query Contents
  • Query Collections
  • Query Feeds
  • Query Conversations
  • Retrieve Relevant Sources
  • Retrieve Similar Images
  • Visually Describe Image

RAG

  • Prompt LLM Conversation

graphlit-mcp-server FAQ

Is this project still being updated?
The code has been quiet since January 2026. It remains a commercial product from Graphlit with a support community, and no replacement is named.
Do I need an account?
Yes — a Graphlit account. You copy three values from its settings dashboard into your config file.
Which apps does it work in?
Claude Desktop, Cursor, VS Code, Cline, Goose, and Windsurf, along with other apps that support MCP servers.
Can I use this to search my documents and chats together?
Yes — that is the main point. Anything you add becomes searchable from one place.
What kinds of files does it handle?
PDFs, Word and PowerPoint files and web pages are converted to readable text, while audio and video are transcribed.
How hard is setup?
Easy to moderate. Install with one command or paste a config block, then add three values from your Graphlit dashboard.
Do I need a separate web-search tool alongside it?
No. Web search, crawling, page mapping and screenshots are all built in.