Categorize the recent git commit history into types: feature, bugfix, docs, refactor, etc.
AI agents call classify_commit_history to retrieve information from GitHub PR Template Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes existing git commit history to classify commits by type. It retrieves historical data without modifying any state, making it a pure read/query operation with minimal blast radius.
From the tool's definition Categorize the recent git commit history into types: feature, bugfix, docs, refactor, etc.
Attacks that exploit this kind of access
Categorize the recent git commit history into types: feature, bugfix, docs, refactor, etc. It is categorised as a Read tool in the GitHub PR Template Tools MCP Server, which means it retrieves data without modifying state.
Register the GitHub PR Template Tools MCP server in PolicyLayer and add a rule for classify_commit_history: 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 GitHub PR Template Tools. Nothing to install.
classify_commit_history 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 classify_commit_history 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 classify_commit_history. 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.
classify_commit_history is provided by the GitHub PR Template Tools MCP server (sawantudayan/github-mcp-server). 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 →