AI agents call github.commits to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves historical commit metadata from a GitHub repository with filtering and pagination capabilities. It has no side effects, cannot modify data, and is explicitly documented as read-only.
From the tool's definition Tool description explicitly states 'Read-only; no caller key needed' and retrieves 'Commit history for a repository: sha, message, author name + GitHub login, date, and URL.' with optional filtering and pagination.
Attacks that exploit this kind of access
Commit history for a repository: sha, message, author name + GitHub login, date, and URL. Optionally filter by branch/tag (sha), file path, or author. Paginate. Read-only; no caller key needed. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for github.commits: 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 Mcp. Nothing to install.
github.commits 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 github.commits 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 github.commits. 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.
github.commits is provided by the MCP server (@2sio/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 →