Get the FREE Ultimate OpenClaw Setup Guide →

mcp-reporter

mcp-reporter is a streamlined utility that generates comprehensive capability reports for Model Context Protocol servers, empowering developers to easily understand available functionality across their MCP servers ecosystem for both documentation and integration into other tools.

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio cyanheads-mcp-reporter node dist/index.js

How to use

MCP Reporter is a utility that analyzes MCP servers in your ecosystem and generates a comprehensive Markdown report describing each server's capabilities, tools, resources, and resource templates. It discovers enabled MCP servers, extracts their capabilities, and assembles this information into an organized document for documentation or tooling. You can use it to obtain a high-level view of your MCP landscape, understand what tooling is available across servers, and share consistent, up-to-date details with your team. The tool also supports programmatic usage so you can generate reports from custom configurations or integrate report generation into CI pipelines.

To use MCP Reporter, supply a configuration file that lists the MCP servers you want to analyze. Then run the CLI to produce a Markdown report. The report includes a summary, per-server metadata, available tools with descriptions and input schemas, resource descriptors, and resource templates. If you enable metadata and input schemas in the options, you’ll get richer output suitable for documentation or onboarding materials. You can also invoke the library programmatically from JavaScript/TypeScript to customize how reports are generated or where they’re written.

How to install

Prerequisites:

  • Node.js 16.x or higher
  • npm or yarn

Install from source (example workflow):

# Clone the repository
git clone https://github.com/cyanheads/mcp-reporter.git
cd mcp-reporter

# Install dependencies
npm install

# Build the project
npm run build

# Create a symlink (optional, for easier CLI usage)
npm link

Run the reporter with a configuration file that specifies the MCP servers to analyze. The repository includes an example configuration named mcp-servers.json.example which you can copy and customize to mcp-servers.json. Example:

cp mcp-servers.json.example mcp-servers.json

Then invoke the CLI (e.g., npm run start or the installed binary) to generate the report:

# Generate report with default settings
npm run start

# Or run the CLI directly if linked
mcp-reporter

For programmatic usage, install the package and instantiate the reporter in your code as shown in the documentation example, then call run() to produce the report.

Additional notes

Tips and notes:

  • Configuration is defined in mcp-servers.json and should include each MCP server with command, args, and optional env vars. See the example in the repository for reference.
  • If you’re running multiple MCP servers or integrating with CI, consider setting includeInputSchemas and includeServerMetadata to true for richer reports.
  • Ensure Node.js and npm are up to date to avoid build-time issues with TypeScript and dependencies.
  • If you encounter path issues, ensure the server entry points in args point to the correct built JavaScript files (e.g., dist/index.js) after a successful build.
  • The reporter itself may be extended or consumed programmatically via its API (e.g., new McpReporter(configPath, options)) to tailor report output paths and options.
  • If using Docker, uvx, or other environments, you can adapt the mcp_config to your deployment model by pointing command/args to the appropriate entry points and ensuring environment variables are set as needed.

Related MCP Servers

Sponsor this space

Reach thousands of developers