Provides comprehensive file system exploration capabilities including directory listing, file reading, metadata retrieval, and file searching with wildcard pattern support
Mentioned as an advanced exercise for implementing git integration with status, log, and diff functionality
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@File System Explorer MCP Server list the files in my current project directory"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A beginner-friendly MCP (Model Context Protocol) server that demonstrates core MCP concepts through practical file system exploration tools. This project is perfect for learning MCP development while building something immediately useful.
This project teaches you essential MCP concepts:
Tools: Interactive functions that AI can call (like listing directories or reading files)
Resources: Static data sources that provide context (like current directory info)
Prompts: Reusable templates that help users accomplish specific tasks
Server Architecture: How to structure and implement a proper MCP server
Error Handling: Best practices for robust MCP server development
Related MCP server: local-tools-mcp-server
list_directory - List contents of any directory with file sizes and modification dates
read_file - Read text files with safety limits and error handling
get_file_info - Get detailed metadata about files and directories
search_files - Search for files using wildcard patterns (supports * and ?)
Current Directory - Provides information about the working directory
explore_project - Guided project exploration and analysis
file_analysis - Analyze files in a directory for patterns and structure
MCPServer/
├── src/
│ └── index.ts # Main server implementation
├── build/ # Compiled JavaScript output
├── .vscode/
│ └── mcp.json # MCP server configuration
├── .github/
│ └── copilot-instructions.md
├── package.json # Node.js project configuration
├── tsconfig.json # TypeScript configuration
└── README.md # This fileBefore you begin, ensure you have:
Node.js 18+ installed (download here)
TypeScript knowledge (basic understanding)
VS Code (recommended for debugging)
# Navigate to the project directory
cd MCPServer
# Install dependencies
npm install
# Build the project
npm run buildYou can test your server using the MCP Inspector:
# Install and run MCP Inspector
npx @modelcontextprotocol/inspector node build/index.jsThis opens a web interface where you can:
Test all available tools
View resources
Try out prompts
Debug server responses
Once connected to an MCP client (like Claude Desktop), you can:
Can you list the contents of my Desktop folder?Please read the README.md file in my project directoryFind all JavaScript files in my project using the pattern "*.js"What can you tell me about the package.json file?The server includes helpful prompts:
Use the explore_project prompt with my code directoryAnalyze my src directory focusing on TypeScript filesMake sure you have the MCP extension installed in VS Code
The server is already configured in .vscode/mcp.json
Restart VS Code to load the configuration
You should see the MCP server available in the sidebar
Edit the source code in src/index.ts
Rebuild the project:
npm run buildTest your changes using the MCP Inspector or restart your MCP client
For faster development, use watch mode:
npm run devThis automatically recompiles when you make changes.
const server = new Server(
{ name: "filesystem-explorer", version: "1.0.0" },
{ capabilities: { tools: {}, resources: {}, prompts: {} } }
);server.setRequestHandler(CallToolRequestSchema, async (request) => {
const { name, arguments: args } = request.params;
switch (name) {
case "your_tool_name": {
// Your tool logic here
return {
content: [{ type: "text", text: "Tool response" }]
};
}
}
});The server includes several security measures:
Path validation to prevent directory traversal
File size limits to prevent reading huge files
Recursion limits in directory search
Error handling for permission issues
Add a new tool that counts lines in a text file
Modify the file size limit for reading files
Add a new resource that shows system information
Add file writing capabilities (create_file, write_file tools)
Implement a simple backup tool that copies files
Add support for binary files with proper handling
Add file watching capabilities using Node.js file system events
Implement a simple git integration (status, log, diff)
Add compression/decompression tools for zip files
Server not starting:
Check that Node.js is installed: node --version
Ensure dependencies are installed: npm install
Verify build completed: ls build/ (should contain index.js)
Permission errors:
Make sure the server has read access to directories
On Windows, avoid system directories that require admin access
Build errors:
Clear and reinstall dependencies: rm -rf node_modules && npm install
Check TypeScript configuration in tsconfig.json
Once you've mastered this server:
Explore other MCP servers in the official repository
Build your own specialized server for your domain (database, API, etc.)
Contribute to the MCP community with your own implementations
Learn about remote MCP servers for cloud-based tools
Want to improve this learning resource?
Fork the repository
Make your improvements
Add tests if applicable
Submit a pull request
Ideas for contributions:
Additional example tools
Better error messages
More comprehensive prompts
Performance improvements
Additional security features
MIT License - feel free to use this code for learning and building your own MCP servers!
You've successfully set up your first MCP server! This foundation will help you understand the Model Context Protocol and build more sophisticated integrations. The concepts you've learned here - tools, resources, prompts, and proper error handling - apply to all MCP server development.
Happy coding! 🚀
Get detailed information about a file or directory
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | The file or directory path to get info about |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Get detailed information') but doesn't specify what information is returned (e.g., metadata, permissions, size), whether it's read-only (implied but not stated), or any constraints like rate limits or authentication needs. This leaves significant gaps for a tool with no structured safety hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose without unnecessary words. It could be slightly more structured by hinting at return values, but it earns its place by being direct and clear, with no wasted verbiage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (1 parameter, no nested objects) and high schema coverage, the description is minimally adequate. However, with no output schema and no annotations, it should ideally explain what 'detailed information' includes to compensate. It meets the basic threshold but lacks depth for full contextual understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'path' parameter clearly documented. The description adds no additional parameter details beyond what the schema provides, such as path format examples or constraints. Since the schema does the heavy lifting, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Get') and resource ('detailed information about a file or directory'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'list_directory' (which might list contents) or 'search_files' (which might search across files), so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'list_directory' or 'search_files'. It doesn't mention prerequisites, such as needing a valid path, or clarify if it works for both files and directories, leaving usage context implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the contents of a directory
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | The directory path to list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the basic action but doesn't cover critical aspects like permissions needed, error handling (e.g., for invalid paths), output format, or whether it's read-only or has side effects. This is inadequate for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's front-loaded with the core purpose, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the output looks like (e.g., list of filenames, metadata), error conditions, or behavioral nuances. This leaves significant gaps for an agent to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'path' parameter clearly documented. The description adds no additional semantic context beyond what the schema provides, such as path format examples or constraints. Given the high schema coverage, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('List') and resource ('contents of a directory'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'search_files' or 'get_file_info' which might also involve directory operations, so it lacks sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'search_files' or 'get_file_info'. There's no mention of prerequisites, context, or exclusions, leaving the agent to infer usage based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the contents of a text file
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | The file path to read |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only states the basic action. It doesn't disclose important behavioral traits like error handling (e.g., what happens if the file doesn't exist), encoding assumptions, or size limitations, leaving significant gaps for a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words. It's appropriately sized for a simple tool and front-loads the core action, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description is too minimal. It doesn't explain what the return value looks like (e.g., raw text, structured data) or address potential constraints, making it incomplete for effective agent use despite the simple parameter schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'path' parameter clearly documented. The description doesn't add any parameter details beyond what the schema provides, so it meets the baseline for high schema coverage without adding extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Read') and resource ('contents of a text file'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'get_file_info' which might also read file metadata, so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'get_file_info' for metadata or 'search_files' for finding files. The description only states what it does, not when it's appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for files by name pattern in a directory
| Name | Required | Description | Default |
|---|---|---|---|
| directory | Yes | The directory to search in | |
| pattern | Yes | The filename pattern to search for (supports * wildcards) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action ('search for files') but doesn't describe key behaviors such as whether the search is recursive, case-sensitive, or supports regex beyond wildcards, nor does it mention performance aspects like timeouts or result limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It is appropriately sized and front-loaded, making it easy to understand quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., a list of file paths, metadata), error conditions, or behavioral nuances, leaving significant gaps for a search operation with two required parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting both parameters. The description adds minimal value beyond the schema by implying the search is based on filename patterns, but it doesn't provide additional context like examples of valid patterns or directory path formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('search') and resource ('files'), specifying the search criteria ('by name pattern') and scope ('in a directory'). However, it doesn't explicitly differentiate from sibling tools like 'list_directory' or 'get_file_info', which might also involve file operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'list_directory' (which might list all files) or 'get_file_info' (which might retrieve metadata), leaving the agent to infer usage context without explicit direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose with no overlap: get_file_info retrieves metadata, list_directory shows directory contents, read_file accesses file data, and search_files performs pattern matching. An agent can easily distinguish between these operations.
All tools follow a consistent verb_noun pattern with snake_case naming (get_file_info, list_directory, read_file, search_files). The naming is predictable and readable throughout the set.
Four tools is reasonable for a file system explorer, covering core operations like inspection, listing, reading, and searching. It feels slightly minimal but well-scoped for basic file system interactions.
The tools cover read-only operations well but lack write capabilities (e.g., create, update, delete files/directories) and advanced features like file watching or permissions management. This is a notable gap for a full file system explorer.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Browse and manage files in your Moxt AI workspace from any MCP client.
Create guides as MCP servers to instruct coding agents to use your software (library, API, etc).
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/akshat12000/FileSystem-MCPServer'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
