FileMCP
Minimal MCP file server for safe file operations under a local AgentFiles directory.
README
FileMCP
FileMCP is a small Model Context Protocol (MCP) file server for AI Agents.
The server exposes simple file operations under an AgentFiles folder.
What It Does
FileMCP exposes these MCP tools:
createFileTool: creates a new file underAgentFilesand refuses to silently overwrite an existing file.overwriteFileTool: writes or replaces a file underAgentFiles.createDirectoryTool: creates a directory underAgentFiles.readFileTool: reads a UTF-8 text file fromAgentFiles.listDirectoryTool: lists files and folders underAgentFiles.
The read and list tools include path traversal checks so requests cannot escape the AgentFiles directory.
Requirements
- Node.js 18+
- npm
Install FileMCP
From your root directory:
npm install --save https://github.com/devcheyannagraham/FileMCP.git
Use With An Agent
In your import the server and pass it into your agent config:
import { filemcp } from "filemcp/server.ts";
import { agent } from "<your-agent-sdk>";
const myAgent = agent({
mcpServer: filemcp,
});
File Operations
File operations are relative to an AgentFiles folder in the working directory.
Asking the agent to read file.txt actually reads AgentFiles/file.txt.
Same with writes.
Ensure there is a folder called 'Agent Directory' in the root directory for the agent to read.
The code is simple and you can change this locally if you want. :)
Project Files
server.ts: creates the MCP server, registers tools, and starts stdio transport.tools.ts: implements the filesystem tools.toolSchemas.ts: defines tool descriptions and Zod schemas.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.