semantic-search-mcp by Parado-xy - MCP Server

Seroost Search MCP Server

A Model Context Protocol (MCP) server that provides AI agents with powerful codebase search capabilities using the Seroost semantic search engine.

Features

Semantic Code Search: Find functions, classes, and code patterns using natural language queries
Ranked Results: Get relevance-scored search results with line numbers and file paths
Fast Indexing: Quick indexing of entire codebases including dependencies
MCP Integration: Works with any MCP-compatible AI system (Claude, VS Code Copilot, etc.)
JSON API: Structured responses perfect for programmatic use

Prerequisites

Node.js 18+
Seroost installed and built in release mode
TypeScript (for development)

Installation

Install Seroost (if not already installed):

# Clone and build Seroost
git clone https://github.com/Parado-xy/seroost
cd seroost
cargo build --release
# Make sure the binary is in your PATH

Clone this repository:

git clone https://github.com/Parado-xy/semantic-search-mcp
cd search-mcp

Install dependencies:
```
npm install
```
Build the project:
```
npm run build
```

Usage

As an MCP Server

Configure your MCP client to use this server:

{
  "mcpServers": {
    "seroost-search": {
      "command": "node",
      "args": ["/path/to/search-mcp/build/index.js"]
    }
  }
}

Available Tools

`seroost_set_index`

Configure the target directory for indexing.

Parameters:

path (string): Absolute path to the directory to index

Example:

{
  "name": "seroost_set_index",
  "arguments": {
    "path": "/home/user/my-project"
  }
}

`seroost_index`

Build the search index for the configured directory.

Parameters: None (uses path set by seroost_set_index)

Example:

{
  "name": "seroost_index",
  "arguments": {}
}

`seroost_search`

Search through the indexed codebase.

Parameters:

query (string): Search term, function name, or natural language description

Example:

{
  "name": "seroost_search",
  "arguments": {
    "query": "user authentication functions"
  }
}

Response:

{
  "query": "user authentication functions",
  "results": [
    {
      "rank": 1,
      "path": "/home/user/project/src/auth.js",
      "score": 0.8543,
      "line_matches": [
        {
          "line": 42,
          "content": "function authenticateUser(credentials) {"
        }
      ]
    }
  ]
}

Workflow

Set Index Path: Use seroost_set_index to configure which directory to search
Build Index: Run seroost_index to process and index all files
Search: Use seroost_search to find relevant code with natural language queries

Example Searches

"function createUser" - Find user creation functions
"error handling" - Find error handling patterns
"database connection" - Find database-related code
"React components" - Find React component definitions
"API endpoints" - Find REST API route definitions

Development

Building

npm run build

Project Structure

src/
├── index.ts        # MCP server setup and tool definitions
├── commands.ts     # Seroost command wrappers
build/              # Compiled JavaScript output

How It Works

This MCP server acts as a bridge between AI agents and the Seroost search engine:

Indexing: Seroost processes your codebase and creates a searchable index
Querying: AI agents send search queries through the MCP protocol
Results: Seroost returns ranked, relevant code snippets with metadata
Integration: AI agents can use these results to understand and work with your code

Benefits for AI Agents

Faster Code Discovery: Find relevant code without reading entire files
Semantic Understanding: Search by intent, not just exact text matches
Contextual Results: Get ranked results with relevance scores
Large Codebase Support: Handle projects with thousands of files
Cross-File Analysis: Find usage patterns across the entire project

License

ISC

Contributing

Contributions welcome! Please feel free to submit issues and pull requests.

Related Projects

Seroost - The underlying search engine
Model Context Protocol - The protocol this server implements