FZF

You can run fuzzy search, list filtering, and content search through a self-contained MCP server that bundles the fzf binary. This server lets you connect your MCP client to quickly find files, filter lists, and search inside code without installing multiple dependencies on every machine.

How to use

Set up an MCP client to talk to the fzf MCP server. You’ll typically configure your client to point at a local or remote MCP entry that runs the fzf-capable server, then issue high-level tasks like fuzzy file search, list filtering, or content search. Use the server to perform operations non-interactively via your MCP client, and return the filtered results back to your UI or workflow.

How to install

Prerequisites: you need Git and Node.js installed on your system. No other prerequisites are required because the package bundles the fzf binary during installation.

Step 1: clone the project repository.

git clone https://github.com/danielsimonjr/fzf-mcp.git
cd fzf-mcp
npm install
chmod +x index.js

Configuration options

Configure how you run the fzf MCP server in your client configuration. The following examples show labeled configurations you can adapt for your environment.

{
  "mcpServers": {
    "fzf": {
      "command": "npx",
      "args": ["-y", "@danielsimonjr/fzf-mcp"]
    }
  }
}

If you prefer a global install, you can use the bundled command directly. The example below runs the fzf MCP server with the globally installed binary.

{
  "mcpServers": {
    "fzf": {
      "command": "fzf-mcp"
    }
  }
}

If fzf isn’t in your PATH, you can override its path with an environment variable in your MCP config.

{
  "mcpServers": {
    "fzf": {
      "command": "npx",
      "args": ["-y", "@danielsimonjr/fzf-mcp"],
      "env": {
        "FZF_PATH": "C:\\path\\to\\fzf.exe"
      }
    }
  }
}

Available tools

fuzzy_search_files

Search for files using fzf's fuzzy matching with parameters for query, directory, maxResults, caseSensitive, and exact.

fuzzy_filter

Filter a list of strings using fuzzy matching with parameters for items, query, maxResults, caseSensitive, and exact.

fuzzy_search_content

Search within file contents using fuzzy matching with parameters for query, directory, filePattern, maxResults, and caseSensitive.