adhikasp/mcp-git-ingest
MCP server to read and analyze GitHub repositories with an LLM.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for adhikasp/mcp-git-ingest, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
MCP Git Ingest lets an LLM read and analyze GitHub repositories, fetching file trees and file contents for analysis. It gives agents lightweight repo comprehension without cloning locally. Ingested repository content (including untrusted repos) is a prompt-injection surface.
Key features and capabilities
- Read GitHub repo structure
- Fetch file contents
- Repo analysis for LLMs
- Lightweight, no clone
Use cases
- Analyzing GitHub repos via agents
- Code comprehension workflows