Top Developer Productivity MCP servers

Ranked by the composite AgentRank score — a weighted blend of stars (15%), freshness (25%), issue health (25%), contributors (10%), and inbound dependents (25%). Average score across these 8 tools: 88.5.

See all code-assistant tools in the index →

Choosing by use case

Git operations

Read commit history, diff files, create branches, stage changes, and run git commands from your agent.

Code search & navigation

Semantic and symbol-level search across codebases — find where a function is defined, what calls it, and where it is tested.

Test runners

Execute tests from inside the agent loop and read results to iterate on failing tests automatically.

Terminal & shell execution

Run shell commands, build scripts, and CLI tools as part of agentic workflows.

Quick setup

Most MCP servers follow the same config pattern. Add this to your Claude Desktop, Cursor, or Windsurf MCP config file:

{
  "mcpServers": {
    "git": {
      "command": "uvx",
      "args": ["mcp-server-git", "--repository", "/path/to/your/repo"]
    }
  }
}

See the integrations page for platform-specific setup guides for Claude Code, Cursor, VS Code, Windsurf, and Cline.

Reading the AgentRank signals

Each tool in this guide is scored on five signals that predict long-term reliability:

Full scoring methodology →