Local-only Go static analysis engine with MCP server for AI coding agents.
gograph is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view ozgurcd/gograph --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Gograph builds a call graph of your Go code using static analysis. It gives AI agents tools to query symbols, call chains, and impact without reading raw files. It runs entirely locally and never executes your code.
Gograph is a static analysis tool for Go repositories that builds an AST-aware call graph and exposes over 50 query tools via CLI and MCP server. It enables AI coding agents to navigate packages, symbols, call chains, routes, SQL, environment variables, and tests without reading raw files. Key features include: token-saving composite commands (context, plan, explain), architecture enforcement (boundary rules, API drift detection, complexity gates), agent compliance auditing, and safe-by-design operation (no network, no code execution, no secrets read). It is benchmarked to reduce noise by up to 90% compared to grep-based workflows.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 2 days ago.
163 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
AI agents planning code changes with full structural context
Developers tracing call chains and impact analysis before refactoring
CI/CD pipeline enforcing architecture rules and detecting dead code
Auditing AI agent behavior for compliance with coding workflows
163
Stars
13
Forks
0
Issues
MIT
License
Local codebase intelligence CLI and MCP server for AI coding agents with change-safety gates and audit evidence.
An offline MCP server that indexes your codebase for semantic search, code search, and git history retrieval.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
0 security/trust notes recorded.
Setup difficulty is 2/5.