MCP Servers
Connect external tools to your AI agents. Filesystem. Search. Databases. GitHub. Slack.
What is an MCP Server?
An MCP server is a tool connector that lets AI agents interact with files, databases, APIs, developer tools, and other systems. AgentNode helps you discover, install, and run them.
Your First MCP in 3 Steps
Install AgentNode
pip install agentnode-sdkPython 3.10+ required. No account needed.
Install an MCP Server
agentnode install mcp-filesystemConnects your agent to the local filesystem. No API key needed.
Check & Run
agentnode mcp doctor mcp-filesystem
agentnode run mcp-filesystem --input '{"path": "."}'Doctor confirms your setup works. Run executes the MCP server and returns results.
Expected output
{"content": [{"text": "README.md\nsrc/\ntests/"}]}That's it. Your first MCP server is running.
Next: Add an API-powered MCP
Now try an MCP that connects to an external service. This one searches the web via Brave Search.
agentnode install mcp-brave-searchagentnode mcp doctor mcp-brave-search
agentnode run mcp-brave-search --input '{"query": "latest AI news"}'Available MCP Servers
View allBrave Search MCP
MCP server for Brave Search API web and local search.
Filesystem MCP
MCP server for secure local filesystem operations.
GitHub MCP
MCP server for GitHub API repository operations.
Memory MCP
MCP server for persistent knowledge graph memory.
PostgreSQL MCP
MCP server for read-only PostgreSQL database access.
Puppeteer MCP
MCP server for browser automation via Puppeteer.
Sequential Thinking MCP
MCP server for structured sequential thinking and reasoning.
Slack MCP
MCP server for Slack workspace interaction via Bot API.
SQLite MCP
MCP server for SQLite database interaction and analysis.