Skip to main content
Glama
Markdown Sidecar MCP Server

Markdown Sidecar MCP Server

by lwsinclair

Markdown Sidecar MCP Server

This provides a structured way to serve and access markdown documentation from an MCP server for NPM packages, Go Modules, or PyPi packages. It enables informed code generation by exposing these markdown files as resources or tools.

NOTE


Note: Many PyPi packages do not have markdown docs exposed, so this library will also mount python help root docs by default.

This is designed to be executed from within a project directory where the requested packages are already installed locally. Access always stays within your local environments working directory.

Installation

npx -y markdown-sidecar-mcp

Related MCP server: docubridge

Arguments

  • workingDir: The working directory of your repo.

  • packageName: The name of the package or module to request

  • registry: Registry the package will be found in (npm, gomodules, or pypi)

  • docsSubDir: [OPTIONAL] The specific subdirectory to look for markdown docs in. Defaults to package root.

  • mcpPrimitive: [OPTIONAL] The MCP primitive to expose from the server (tool or resource). This defaults to tool, some clients do not currently support resources.

Cursor Installation Steps

Add the following server definition to your .cursor/mcp.json file:

{
  "mcpServers": {
    "sidecar": {
      "command": "npx",
      "args": [
        "-y", "--package", "markdown-sidecar-mcp",
        "--",
        "mcp", "start",
        "--workingDir", "{REPO_WORKING_DIR}",
        "--packageName", "{PACKAGE_NAME}",
        "--registry", "npm"
      ]
    }
  }
}

Development

# Install dependencies
npm i

# Build
npm run build

# Run with Bun
npm run build:mcp

Contributing

  1. Fork the repository

  2. Create your feature branch

  3. Commit your changes and push them up

  4. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides direct access to local documentation files through simple search and overview tools, enabling LLMs to query project-specific markdown documentation without requiring vector databases or RAG pipelines.
    MIT
  • A
    license
    B
    quality
    A
    maintenance
    Enables AI agents to discover, read, search, and install Markdown-based knowledge (rules, skills, workflows) from a local directory via MCP tools.
    14
    1,505 npm
    1
    MIT
  • F
    license
    A
    quality
    C
    maintenance
    Enables MCP-compatible clients to search and read local markdown documentation, allowing agents to retrieve relevant doc snippets or full files by path.
    2
    -