Search Tools MCP Server
About
An MCP server that enhances code analysis with advanced search and dependency mapping capabilities.
Details
- Author
- voxmenthe
- Categories
- Developer Tools, Search, Knowledge Base
Jump to
Setup
Install Search Tools MCP Server in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/voxmenthe/search-tools-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
⚡ An intelligent Model Context Protocol (MCP) server that supercharges code analysis with advanced search capabilities and dependency mapping
TheSearch Tools MCP Serveris a powerful toolkit that combines traditional code search with intelligent analysis algorithms. It leverages theCodeRankalgorithm (inspired by PageRank) to identify the most critical modules in your codebase and provides sophisticated search capabilities that go beyond simple text matching.
- Contextual Keyword Search: Ripgrep-powered search with configurable context lines
- Symbol Discovery: Extract and analyze functions, classes, methods, and modules
- Usage Tracking: Find where symbols are used across your codebase
- Priority-Ranked Results: Search results ranked by code importance
- CodeRank Algorithm: Identify the most critical modules using network analysis
- Dependency Mapping: Trace complex dependency chains and impact analysis
- Hotspot Detection: Find code areas that are both highly connected and frequently used
- Refactoring Impact: Analyze the potential impact of code changes
- Symbol type filtering (functions, methods, classes)
- File inclusion/exclusion patterns
- External module dependency tracking
- Markdown documentation analysis
- Python 3.13+
- uvpackage manager
- kitCLI tool (for symbol analysis)
- ripgrep(for fast text search)
# Clone the repository git clone <repository-url> cd search-tools # Install dependencies uv sync
Add the following configuration to yourmcp.jsonfile:
{ "mcpServers": { "search-tools": { "command": "/path/to/uv", "args": [ "run", "--directory", "/path/to/search-tools", "main.py" ] } } }
{ "mcpServers": { "search-tools": { "command": "/Users/yourusername/.local/bin/uv", "args": [ "run", "--directory", "/path/to/your/search-tools/directory", "main.py" ] } } }
claude mcp add-json search-tools '{"type":"stdio","command":"/Users/yourusername/.local/bin/uv","args":[ "run", "--directory", "/path/to/your/search-tools/directory", "main.py"]}'
To find the correct paths for your system:
# Find uv location which uv # Get absolute path to search-tools directory pwd # (run this from the search-tools directory)
Search for keywords with configurable context lines around matches.
- keyword: Search term (case insensitive)
- working_directory: Absolute path to search directory
- num_context_lines: Lines of context (default: 2)
Extract symbols (functions, classes, methods) from your codebase.
- repo: Repository path
- working_directory: Command execution directory
- keep_types: Filter by symbol types
- file_must_contain/file_must_not_contain: File filtering
Find where specific symbols are used throughout your codebase.
- repo: Repository path
- symbol_name_or_substring: Symbol to search for
- working_directory: Command execution directory
- symbol_type: Optional type filter
Analyze repository importance using the CodeRank algorithm.
- repo_path: Repository to analyze
- external_modules: Comma-separated external dependencies
- top_n: Number of top modules to return (default: 10)
- analyze_markdown: Include markdown files
- output_format: "summary", "detailed", or "json"
Identify critical code areas combining connectivity and usage frequency.
- repo_path: Repository path
- working_directory: Command execution directory
- min_connections: Minimum import connections (default: 5)
- include_external: Include external dependencies
- top_n: Number of hotspots to return (default: 20)
Trace dependency chains and analyze refactoring impact.
- repo_path: Repository path
- target_module: Module to analyze
- working_directory: Command execution directory
- analysis_type: "dependency", "refactoring", or "both"
- max_depth: Maximum trace depth (default: 3)
- change_type: "modify", "split", "merge", or "remove"
Enhanced search combining ripgrep with CodeRank prioritization.
- keyword: Search term (supports regex)
- repo_path: Repository path
- working_directory: Command execution directory
- rank_results: Sort by module importance
- context_lines: Context lines around matches (default: 3)
- max_results: Maximum results to return (default: 20)
# Development mode uv run mcp dev main.py # Testing with MCP Inspector npx @modelcontextprotocol/inspector python main.py
- mcp[cli]: Model Context Protocol framework
- cased-kit: Symbol analysis toolkit
- networkx: Graph analysis for CodeRank algorithm
The CodeRank algorithm treats your codebase as a directed graph where:
- Nodes: Python modules, classes, functions, methods
- Edges: Import relationships and dependencies
- Weights: Different weights for internal vs external dependencies
This creates a ranking system that identifies the most "central" and important parts of your codebase, similar to how PageRank identifies important web pages.
- 🔍 Code Exploration: Quickly understand large codebases
- 🏗️ Refactoring Planning: Identify high-impact areas before changes
- 📚 Documentation: Find the most important modules to document first
- 🐛 Bug Investigation: Focus on critical code paths
- 👥 Code Review: Prioritize review efforts on important modules
Contributions are welcome! Please feel free to submit issues, feature requests, or pull requests.
This project is open source. Please check the license file for details.
🔮 Powered by the CodeRank Algorithm & Model Context Protocol
Making code search intelligent, one repository at a time
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Semantic code search for AI agents without indexing your codebase or storing any data. Fast and accurate.
Create and read feature flags, review experiments, generate flag types, search docs, and interact with GrowthBook's feature flagging and experimentation platform.
Word search, crossword, and sudoku generator MCP server with printable PDF worksheets, themed word banks, and verifiable LLM evals. Local-first, from the makers of puzzletide.com.
Official MCP server for Stimulsoft Reports & Dashboards documentation. Semantic search across FAQ, Programming Manual, Server/User Manual, and Server/Cloud API for .NET, WPF, Avalonia, WEB, Blazor, Angular, React, JS, PHP, Java, and Python platforms.
Searching and access your AI coding sessions from Claude Code, Gemini CLI, opencode, and OpenAI Codex.
Search Apple's Developer Documentation with smart search and wildcard support.
MCP server that exposes ast-grep (sg) as two tools for structural code search.
Search everything your terminal ever printed. Local MCP server over per-command recorded output: full-text search, exit codes, diffs, secret redaction. Built and maintained by an AI agent (Soren Achebe).
Let AI agents search, register, and manage domains via API
Search, compare, and get docs for 210+ APIs ranked by CLI and agent relevance
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




