graphlit-mcp-server

Overview

The Graphlit MCP Server enables integration between MCP clients and the Graphlit service, creating a searchable, RAG-ready knowledge base across developer and product management tools. It supports ingesting content from numerous sources including Slack, Discord, websites, Google Drive, email, Jira, Linear, and GitHub. The server provides comprehensive tools for retrieval, RAG, extraction, publishing, ingestion, data connectors, web operations, notifications, and enumerations. Documents are extracted to markdown, audio and video files are transcribed, and web crawling/search are built-in without requiring separate integrations.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• query_contents

  Search through ingested contents in your Graphlit project

  Try:Find documents about project timelinesTry:Search for information about user feedback
• query_collections

  Query across collections of content in your Graphlit project

  Try:Retrieve documents from the engineering collectionTry:Find information from all product-related collections
• web_search

  Search the web for information using built-in web search

  Try:Search for latest AI trendsTry:Find articles about React best practices
• web_crawling

  Crawl websites to extract their content

  Try:Crawl https://example.com/docsTry:Extract content from my company's knowledge base
• prompt_llm_conversation

  Start a conversation with an LLM using your Graphlit data as context

  Try:Summarize key findings from recent researchTry:Answer questions based on my project documentation
• extract_structured_json_from_text

  Extract structured JSON data from unstructured text

  Try:Extract key information from this meeting transcriptTry:Parse this customer feedback into structured format
• publish_as_audio

  Convert text to audio using ElevenLabs

  Try:Convert this summary to audio fileTry:Generate voiceover from this script
• publish_as_image

  Generate images using OpenAI's image generation

  Try:Create an illustration of a conceptTry:Generate a diagram showing our system architecture
• retrieve_similar_images

  Find images similar to a provided query or image

  Try:Find images similar to this product screenshotTry:Search for design patterns like this one
• visually_describe_image

  Generate a textual description of an image

  Try:Describe what's in this chartTry:Explain the contents of this screenshot
• configure_project

  Configure your Graphlit project settings

  Try:Update project settingsTry:Configure ingestion options
• create_collection

  Create a new collection to organize your content

  Try:Create a collection for research papersTry:Make a new collection for customer feedback

Comparable tools

Installation

npx -y graphlit-mcp-server

{
  "mcpServers": {
    "graphlit": {
      "command": "npx",
      "args": ["-y", "graphlit-mcp-server"],
      "env": {
        "GRAPHLIT_ORGANIZATION_ID": "your-organization-id",
        "GRAPHLIT_ENVIRONMENT_ID": "your-environment-id",
        "GRAPHLIT_JWT_SECRET": "your-jwt-secret"
      }
    }
  }
}

FAQ

What data sources does the Graphlit MCP Server support?

The server supports numerous sources including Slack, Discord, websites, Google Drive, email, Jira, Linear, GitHub, Microsoft Teams, Twitter/X, and many more through its data connectors.

Is there support for different content types?

Yes, it handles various content types including PDFs, DOCX, PPTX (extracted to Markdown), audio and video files (transcribed), web pages, and structured data extraction.

Compare graphlit-mcp-server with