code_nav MCP
Deterministic code navigation MCP server for Codex/CodeCLI that provides compact repo context using git-aware deterministic search tools without semantic search or embeddings.
README
code_nav MCP
AI-native deterministic code navigation MCP server for Codex / CodeCLI.
code_nav gives coding agents compact, structured repo context without making
them dump files into chat. It works in any git repo by detecting the repo root
and using git-visible files.
There is no semantic search, no embeddings, no vector database, no graph index, no Qdrant, no CocoIndex, and no Zoekt.
Repository:
https://github.com/ARQAWA/code-nav-mcp
Install Prompt
Use INSTALL_AGENT_PROMPT.md with Codex / CodeCLI on the target machine.
The prompt installs one shared user-level code_nav MCP:
$HOME/.local/share/code-nav-mcp/app
$HOME/.local/bin/code-nav-mcp
It also installs/checks Probe, ast-grep, ripgrep, and RTK, configures Codex MCP globally, installs Code Navigation Rules, and verifies the MCP tools.
Tools
| Tool | Purpose |
|---|---|
code_nav.health |
Check repo detection and dependency health. |
code_nav.search |
Main deterministic code discovery workflow. |
code_nav.find_file |
File/path discovery. |
code_nav.exact_search |
Ranked exact text search, not proof. |
code_nav.extract_context |
Compact code context extraction. |
code_nav.structural_search |
AST search with ast-grep. |
code_nav.exact_audit |
Exhaustive proof using raw rg/git grep. |
code_nav.coverage |
File coverage and no-semantic-index status. |
Local Development
npm install
npm run build
npm test
npm run doctor
npm run self-test
Run the MCP server locally:
node dist/cli.js mcp
Optional Repo Config
No per-repo config is required. Rare overrides can use .code-navrc.json:
{
"max_file_bytes": 2097152,
"extra_exclude": [],
"extra_include": [],
"markdown": "normal",
"result_limit": 12
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.