CodeGraph
About
Generates and queries a graph representation of a codebase.
Details
- Author
- cartographai
- Categories
- Developer Tools, Knowledge Base, Other
- Tags
- #data-analysis
Jump to
Setup
Install CodeGraph in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/cartographai/mcp-server-codegraph
Follow the installation instructions in the repository README, then restart your MCP client.
- 📊 Creates a graph representation of your codebase
- 🔍 Identifies entities (functions, classes, imports) and their relationships
- 🔗 Tracks relationships like function calls, inheritance, and implementations
- 🌐 Supports multiple programming languages (Python, JavaScript, Rust)
- index
- Indexes the codebase to create a graph of entities and relationships.
- Provides a list of all entities within a specified file.
- path(string): relative path of the file
- List the relationships of a specific entity
- Inputs
- path(string): relative path of the file
- name(string): name of entity
npx @cartographai/mcp-server-codegraph /path/to/directory
Add this to yourclaude_desktop_config.json
{ "mcpServers": { "codegraph": { "command": "npx", "args": [ "-y", "@cartographai/mcp-server-codegraph", "/path/to/directory", ] } } }
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.
Knowledge graph for token-efficient code reviews with Tree-sitter parsing, dual-mode embedding (ONNX + LiteLLM), and blast-radius analysis via MCP tools.
Code Rag with Graph - local only installation
A blazingly fast codebase graphRAG implementation in 100% Rust
MCP server that gives coding agents program-analysis primitives — data flow, call graphs, taint analysis — so they reason from ground truth instead of grep-and-guess. (same as the GitHub About — keeps your messaging consistent across the web).
An interactive graph analysis toolkit with web visualizations and AI-powered analysis capabilities.
Multi-language code-graph MCP server with 18 tools (find_symbol, callers, callees, blast_radius, dataflow_trace) for AI assistants — local-first, no API key required, ~3× fewer tokens than Claude+grep at the same correctness.
See how OSS libs in your stack are really used: source, tests, callers. C#, Java, TS, Python, Rust, PHP+.
Cross-language code graph extraction and visualization — symbols, call graphs, and cross-repo relationships across 34+ languages with incremental caching and federation support.
Recon indexes your codebase into a knowledge graph and exposes it via 14 MCP tools. AI agents get dependency mapping, blast radius analysis, safe multi-file rename, execution flow tracing, Cypher queries, semantic search, and PR review — without reading every file. Supports 13 languages, live re-index in ~50ms, and zero config setup.
MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
