git_summary
AI agents call git_summary to retrieve information from ContextCore MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on naming convention and server architecture, 'git_summary' most likely retrieves or queries git repository data (commits, branches, history) without modifying anything. This is consistent with 'Read' category tools. Confidence is reduced (0.75 vs higher) due to empty description; if it actually executes git commands with user-supplied arguments, it could be Execute instead.
From the tool's definition Tool name 'git_summary' suggests retrieval of git history information; description is empty, but the sibling tool 'git_current_work_status' and server context (connecting git history for briefings) indicate read-only retrieval of repository state.
Attacks that exploit this kind of access
git_summary. It is categorised as a Read tool in the ContextCore MCP MCP Server, which means it retrieves data without modifying state.
Register the ContextCore MCP server in PolicyLayer and add a rule for git_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 ContextCore MCP. Nothing to install.
git_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_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_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_summary is provided by the ContextCore MCP server (rkpraveendev/contextcore-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 →