How do I install MCP-Grep?
Use `pip install mcp-grep` for manual installation, or run `npx -y @smithery/cli install @erniebrodeur/mcp-grep --client claude` to install via Smithery for Claude Desktop.
@erniebrodeur
Basic information
simple mcp server to wrap the local instance of grep.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-grep": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@erniebrodeur/mcp-grep",
"--client",
"claude"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
MCP-Grep exposes system grep functionality through the Model Context Protocol (MCP), allowing MCP-compatible clients to search file contents using regular expressions. It is designed for developers and LLM-based tools that need to inspect local files efficiently.
Install via pip install mcp-grep or automatically through Smithery. Start the server with the command mcp-grep-server, or use mcp-grep-inspector for an interactive web UI. Connect any MCP-compatible client to access the grep tool and the grep://info resource.
grep://info resource.Use `pip install mcp-grep` for manual installation, or run `npx -y @smithery/cli install @erniebrodeur/mcp-grep --client claude` to install via Smithery for Claude Desktop.
Run `mcp-grep-server` to start the MCP server, or `mcp-grep-inspector` to launch the interactive web‑based inspector.
It supports case‑insensitive matching, context lines before/after matches, maximum match count, fixed string matching, and recursive directory searching.
MCP-Grep accepts plain‑English requests like “Find ‘error’ in log.txt” or “Show 3 lines of context around ‘exception’.” The server interprets the intent and sets the correct grep parameters.
It uses the system’s `grep` binary and the `mcp-grep` Python package. No additional runtime or cloud service is needed.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
🚀 The fast, Pythonic way to build MCP servers and clients.
Hindsight: Agent Memory That Learns
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Model Context Protocol Servers
Comments