MCP-Grep MCP Server

What does “MCP-Grep” MCP Server do?

MCP-Grep is a Model Context Protocol (MCP) server that wraps the local instance of the Unix grep utility, making its powerful search functionality accessible to AI assistants and MCP-compatible clients. By exposing grep as both a resource and a tool, MCP-Grep allows AI systems and developers to perform advanced pattern searches, text analysis, and file exploration tasks via a standardized API. This enables workflows such as searching for patterns in codebases, logs, or documents, retrieving context around matches, and interacting with the system’s grep binary for information about its capabilities. MCP-Grep enhances development and debugging workflows by supporting natural language prompts, integration with LLMs, and interactive exploration through the MCP Inspector.

List of Prompts

• MCP-Grep supports natural language prompts for easier use with LLMs. Examples of supported prompt templates include:
  • Basic search: Search for ‘pattern’ in filename
  • Case-insensitive search: Find all instances of ‘PATTERN’ regardless of case in filename
  • Search with context lines: Search for ‘pattern’ in filename and show N lines before and after each match
  • Recursive directory search: Find all occurrences of ‘pattern’ in directory and subdirectories
  • Fixed string search: Search for the exact string ‘pattern’ in filename
  • Limited results: Show the first N occurrences of ‘pattern’ in filename
  • Multiple options combined: Find ‘pattern’ case-insensitively in all files matching criteria, show context, and limit results

List of Resources

• grep://info
  Returns information about the system grep binary, including its path, version, and supported features.

List of Tools

• grep
  Searches for patterns in files using the system grep binary. Supports options like case-insensitive matching, context lines, maximum match count, fixed string matching, and recursive directory searching.

Use Cases of this MCP Server

• Log Analysis:
  Quickly search for specific error messages or patterns in large log files, streamline debugging, and automate log monitoring.
• Codebase Exploration:
  Find function definitions, usage of variables, or deprecated code patterns within large source code repositories.
• Configuration File Search:
  Locate specific configuration parameters or settings in multiple config files across directories for audits or troubleshooting.
• Security Audits:
  Identify hardcoded secrets, passwords, or insecure patterns within codebases or files for security reviews.
• Documentation Search:
  Search through documentation files to quickly locate relevant sections, terms, or updates.

How to set it up

Windsurf

1. Ensure Python and mcp-grep are installed: pip install mcp-grep
2. Locate your Windsurf configuration file (e.g., windsurf.config.json)
3. Add the MCP-Grep server to the mcpServers section with the following JSON:

   {
     "mcpServers": {
       "mcp-grep": {
         "command": "mcp-grep-server",
         "args": []
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the server is accessible via Windsurf’s MCP interface.

Claude

1. Install with Smithery:

   npx -y @smithery/cli install @erniebrodeur/mcp-grep --client claude
   

2. Open Claude Desktop’s config file.
3. Add MCP-Grep as a server:

   {
     "mcpServers": {
       "mcp-grep": {
         "command": "mcp-grep-server",
         "args": []
       }
     }
   }
   

4. Save and restart Claude Desktop.
5. Confirm integration via the server panel.

Cursor

1. Install mcp-grep: pip install mcp-grep
2. Update Cursor’s MCP configuration file.
3. Add entry:

   {
     "mcpServers": {
       "mcp-grep": {
         "command": "mcp-grep-server",
         "args": []
       }
     }
   }
   

4. Save config and restart Cursor.
5. Check MCP tool availability within Cursor.

Cline

1. Install mcp-grep via pip: pip install mcp-grep
2. Locate your Cline MCP config file.
3. Insert:

   {
     "mcpServers": {
       "mcp-grep": {
         "command": "mcp-grep-server",
         "args": []
       }
     }
   }
   

4. Save and restart the application.
5. Verify that Cline recognizes the MCP server.

Securing API Keys

If you need to set environment variables (e.g., for advanced setups), use this pattern:

{
  "mcpServers": {
    "mcp-grep": {
      "command": "mcp-grep-server",
      "args": [],
      "env": {
        "MY_SECRET_API_KEY": "${MY_SECRET_API_KEY}"
      },
      "inputs": {
        "api_key": "${MY_SECRET_API_KEY}"
      }
    }
  }
}

Note: MCP-Grep does not require an API key by default, but this demonstrates the pattern for secure secrets.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mcp-grep": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “mcp-grep” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

MCP-Grep provides a focused, well-documented implementation of MCP for the popular grep utility. It offers clear resources, tool definitions, and setup instructions, but does not document support for Roots or Sampling. Its simplicity and documentation make it a solid choice for developers needing search capabilities, but advanced MCP features are not covered.

MCP Score

Rating: 7/10
MCP-Grep is robust in its core functionality and documentation but lacks explicit coverage of advanced MCP features like Roots and Sampling. It is a practical and well-scoped server for search tasks.