Code Pathfinder is an open-source static analysis engine that traces vulnerabilities across files and functions by building a graph of the codebase and performing taint analysis. It supports multiple languages and provides a server for AI coding assistants to access code analysis features.
From the registry: Code intelligence MCP server: call graphs, type inference, and symbol search for Python/Go.

$ brew install shivasurya/tap/pathfinderhttps://github.com/shivasurya/code-pathfinder/releasesPlease install the `pathfinder` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install pathfinder CLI** — Install via Homebrew, pip, or download pre-built binary Run: `brew install shivasurya/tap/pathfinder` (https://github.com/shivasurya/code-pathfinder/releases)
Canonical MCP server config (stdio transport):
- command: `pathfinder`
- args: ["serve","--project","."]
Note: Open-source SAST engine with cross-file taint analysis. MCP server mode exposes call graph queries and security analysis tools. 190 security rules for Python, Dockerfile, and Docker Compose. No API key required.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GITHUB_TOKENrequiredGitHub token required when posting comments or inline reviews on pull requests.Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.