MCP Servers

knowledge-mcp

An MCP server that allows Claude to export knowledge and experience into a personal knowledge corpus of markdown files with YAML frontmatter, organized by category, with tools for saving, reading, searching, and listing entries.

README

knowledge-mcp

A personal MCP server that lets Claude (Claude Code, Claude Desktop, etc.) export knowledge and experience into a personal knowledge corpus — a folder of markdown files that acts as your knowledge base.

Entries are markdown files with YAML frontmatter (created/updated timestamps, tags, source), organized into category folders. Every write regenerates an index.md at the corpus root listing all entries by category.

Tools

Tool	Purpose
`save_knowledge`	Write an entry to `<category>/<slug>.md`. Modes: `create` (default, fails on collision), `overwrite`, `append` (adds a dated section).
`list_knowledge`	List all entries grouped by category.
`search_knowledge`	Case-insensitive text search with line snippets — use before saving to avoid duplicates.
`read_knowledge`	Read one entry by relative path, e.g. `projects/my-project.md`.
`reindex_knowledge`	Regenerate `index.md` manually.

Writes are confined to the knowledge base root — path traversal outside it is rejected. Only markdown files directly inside category folders (and the root) are indexed.

Setup

Requires uv. Install dependencies once:

cd /path/to/knowledge-mcp
uv sync

Claude Code

claude mcp add --scope user knowledge \
  --env KNOWLEDGE_MCP_ROOT=/path/to/your/Knowledge -- \
  uv run --directory /path/to/knowledge-mcp knowledge-mcp

(--scope user makes it available in every project; drop it for project-only.)

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on your platform:

{
  "mcpServers": {
    "knowledge": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/knowledge-mcp",
        "knowledge-mcp"
      ],
      "env": {
        "KNOWLEDGE_MCP_ROOT": "/path/to/your/Knowledge"
      }
    }
  }
}

Then restart Claude Desktop.

Configuration

Env var	Default	Purpose
`KNOWLEDGE_MCP_ROOT`	`~/Documents/Personal/Notes/Knowledge`	Knowledge base root directory. Must already exist.
`KNOWLEDGE_MCP_TITLE`	`Knowledge Base`	Heading used for the generated `index.md`.

Manual run / smoke test

uv run knowledge-mcp   # starts the stdio server (Ctrl-C to stop)

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured