Pi MCP Tools
Universal MCP tools extension for pi coding agent — connect to filesystem, GitHub, databases, and more
What is Pi MCP Tools?
Pi MCP Tools is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to universal mcp tools extension for pi coding agent — connect to filesystem, github, databases, and more
Universal MCP tools extension for pi coding agent — connect to filesystem, GitHub, databases, and more
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Universal MCP tools extension for pi coding agent — connect
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx pi-mcp-toolsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Pi MCP Tools
pi-mcp-tools is a universal MCP tools extension for the Pi coding agent that simplifies connecting to external MCP servers including filesystem tools, GitHub integrations, databases, and any other MCP-compatible service. It provides Pi slash commands to manage server connections, toggle tools, and debug connectivity without editing config files manually.
Prerequisites
- Pi coding agent installed and configured (https://github.com/pi-agent/pi)
- Node.js 16+ and npx for running npm-based MCP servers
- GitHub personal access token if connecting to GitHub MCP servers
- Access credentials for any database MCP servers you plan to connect
Install pi-mcp-tools via Pi
Install the extension directly through the Pi package manager using either the Git or npm source.
# Install from GitHub:
pi install git:github.com/tickernelz/pi-mcp-tools
# Or install from npm:
pi install npm:@zhafron/pi-mcp-toolsLocate your Pi settings file
MCP server configurations are added to the Pi settings file at ~/.pi/agent/settings.json under the 'mcp' key.
# View current settings:
cat ~/.pi/agent/settings.json
# The mcp section will look like:
# {
# "mcp": { ... }
# }Add a local MCP server
Edit settings.json to add a local MCP server using the 'local' type. Specify the command array and optional environment variables.
{
"mcp": {
"filesystem": {
"type": "local",
"command": ["npx", "-y", "@modelcontextprotocol/server-filesystem", "/home/user/projects"],
"enabled": true
},
"github": {
"type": "local",
"command": ["npx", "-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your-github-token"
},
"toolPrefix": "gh"
}
}
}Add a remote MCP server
For remote HTTP-based MCP servers, use the 'remote' type with a URL and optional authentication headers.
{
"mcp": {
"my-remote-server": {
"type": "remote",
"url": "https://my-mcp-server.example.com/mcp",
"headers": {
"Authorization": "Bearer your-token"
},
"enabled": true
}
}
}Check server status and list tools
Use Pi slash commands to verify server connectivity and browse available tools.
/mcp-status
/mcp-list
/mcp-toolsToggle and manage servers
Enable or disable individual servers without editing the config file, and reconnect if a server drops.
/mcp-toggle github
/mcp-reconnect
# For detailed connection logs:
# Start Pi with --mcp-debug flagPi MCP Tools Examples
Client configuration
Example ~/.pi/agent/settings.json with a local filesystem server and a remote MCP server configured.
{
"mcp": {
"filesystem": {
"type": "local",
"command": ["npx", "-y", "@modelcontextprotocol/server-filesystem", "/home/user"],
"enabled": true,
"toolPrefix": "fs"
},
"github": {
"type": "local",
"command": ["npx", "-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
},
"toolPrefix": "gh"
}
}
}Prompts to try
Pi agent commands and prompts to manage MCP server connections and use connected tools.
- "/mcp-status" — check which servers are connected
- "/mcp-list" — view all available tools from connected servers
- "/mcp-toggle filesystem" — enable or disable the filesystem server
- "Read the file /home/user/projects/README.md using the filesystem MCP server"
- "Search my GitHub repositories for issues labeled 'bug' using the github MCP tools"Troubleshooting Pi MCP Tools
/mcp-status shows a server as disconnected immediately after adding it
Check that the command in settings.json is correct and all arguments are valid. Run the command manually in a terminal to see error output. For npm-based servers, ensure Node.js and npx are on the PATH that Pi uses. Use --mcp-debug for detailed connection logs.
Tool calls fail with 'tool not found' even though /mcp-list shows the tool
Check if the tool name uses a toolPrefix. Tools are registered as '{toolPrefix}_{toolName}'. If you set toolPrefix='gh', a tool named 'list_issues' becomes 'gh_list_issues'. You can also use filterPatterns in settings.json to include or exclude specific tools.
Environment variables passed in 'env' are not picked up by the server
The 'env' field in settings.json is merged with the system environment. If the server reads variables at startup, restart Pi after changing env values. For sensitive secrets, ensure the settings.json file has restricted read permissions (chmod 600).
Frequently Asked Questions about Pi MCP Tools
What is Pi MCP Tools?
Pi MCP Tools is a Model Context Protocol (MCP) server that universal mcp tools extension for pi coding agent — connect to filesystem, github, databases, and more It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Pi MCP Tools?
Follow the installation instructions on the Pi MCP Tools GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Pi MCP Tools?
Pi MCP Tools works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Pi MCP Tools free to use?
Yes, Pi MCP Tools is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Pi MCP Tools Alternatives — Similar Developer Tools Servers
Looking for alternatives to Pi MCP Tools? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Pi MCP Tools in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Pi MCP Tools?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.