AI agents call git_context_summary to retrieve information from Git without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and summarizes repository metadata and context information to assist LLM workflows. It performs no write operations, does not execute arbitrary code, and does not delete or modify data. The blast radius of misuse is minimal—an agent could only read sensitive code or commit history that should already be access-controlled at the repository level.
From the tool's definition Tool name 'git_context_summary' and description 'High-signal repository context for LLM-assisted workflows' indicate data retrieval. The word 'summary' and 'context' suggest querying repository state (commits, branches, file structure) without modification.
Attacks that exploit this kind of access
High-signal repository context for LLM-assisted workflows. It is categorised as a Read tool in the Git MCP Server, which means it retrieves data without modifying state.
Register the Git MCP server in PolicyLayer and add a rule for git_context_summary: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Git. Nothing to install.
git_context_summary is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the git_context_summary rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for git_context_summary. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
git_context_summary is provided by the Git MCP server (selfagency/git-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →