
DeepContext
DeepContext MCP provides symbol-aware semantic search capabilities for large codebases by indexing Typescript and Python code and enabling agents to find relevant code chunks through natural language queries rather than text matching. The server offers two primary tools: `index_codebase` to create a searchable index of the codebase and `search_codebase` to perform semantic searches that return precise results based on code meaning and relationships. This solves the problem of context window overflow and hallucinations in coding agents by replacing grep-based exact matching with intelligent semantic search that reduces token usage and improves completion accuracy.
- GitHub stars
- 276
- tools
- 4
- last updated
- Dec 15, 2025
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
index_codebaseCreates a searchable index of your codebase for semantic search.
Creates a searchable index of your codebase for semantic search.
No parameter schema in public metadata yet.
search_codebaseFinds relevant code using natural language or keyword queries.
Finds relevant code using natural language or keyword queries.
No parameter schema in public metadata yet.
get_indexing_statusShows indexing status and file counts for your codebases.
Shows indexing status and file counts for your codebases.
No parameter schema in public metadata yet.
clear_indexRemoves all indexed data for a codebase.
Removes all indexed data for a codebase.
No parameter schema in public metadata yet.
Sponsors
Readme
Smarter Context for Large Codebases
DeepContext is an MCP server that adds symbol-aware semantic search to Codex CLI, Claude Code, and other agents, giving them more precise context of even the largest codebases. Currently supports Typescript and Python.
Details
- Repository
- github.com/wildcard-official/deepcontext-mcp
- Category
- Search & Web Crawling