Codecov

Provides Codecov coverage totals and test-prompt generation for MCP-based workflows, enabling quick coverage checks and actionable test suggestions.
  • typescript

5

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "stedwick-codecov-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "codecov-mcp-server",
        "--api-key",
        "XXX",
        "--git-url",
        "XXX"
      ],
      "env": {
        "GIT_URL": "XXX",
        "CODECOV_API_KEY": "XXX"
      }
    }
  }
}

You can run a Codecov MCP Server to work with your AI agent for assessing test coverage and getting prompts to write new tests. It provides a lightweight, configurable bridge that exposes a couple of tools to analyze coverage data and suggest tests based on Codecov reports, helping you focus your testing effort where it matters.

How to use

Launch the MCP server in your environment, then connect your MCP client to it. You will access two core capabilities: retrieve commit coverage totals and get suggested tests based on Codecov reports. Use these tools to quickly identify gaps in your codebase and receive actionable prompts for new tests.

How to install

Prerequisites you need before starting are Node.js and npm (or npx). Install Node.js from the official source and ensure npm is available in your shell.

Install dependencies for the project and build if needed, then run the server with the MCP command shown below.

Configuration and usage notes

To configure how the MCP server is invoked by your AI agent, use the example MCP configuration block. This defines the stdio-based MCP server using npx and passes the required environment variables for authentication and repository URL.

Development

You can develop and test locally by installing dependencies, building, and running in watch mode for auto-rebuilds. Use the following commands in sequence to set up, build, and run the server during development.

Code example for MCP configuration

{
  "mcpServers": {
    "codecov-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "codecov-mcp-server",
      ],
      "env": {
        "CODECOV_API_KEY": "XXX",
        "GIT_URL": "XXX"
      }
    }
  }
}

Troubleshooting and debugging

MCP servers communicate over stdio. If you encounter issues, use the MCP Inspector tool to debug and obtain a browser-based debugging interface. Run the inspector script to start debugging helpers.

Development commands

npm install
npm run build
npm run watch

Available tools

get_commit_coverage_totals

Returns the coverage totals for a given commit and the coverage totals broken down by file, using the designated API.

suggest_tests

Suggests tests to write based on the Codecov report.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational