Show commits and merged PRs from the last N days.
AI agents call recent_changes to retrieve information from GitHub Repo Explainer MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries historical repository data—commits and merged pull requests—without side effects. It is a read-only operation that retrieves information from GitHub's repository history. The blast radius of misuse is minimal since it only exposes already-public repository metadata that would be accessible through normal GitHub browsing or API queries.
From the tool's definition Tool retrieves commit and PR history ('Show commits and merged PRs from the last N days'); no modification or deletion of data, no code execution, no financial operations.
Attacks that exploit this kind of access
Show commits and merged PRs from the last N days. It is categorised as a Read tool in the GitHub Repo Explainer MCP MCP Server, which means it retrieves data without modifying state.
Register the GitHub Repo Explainer MCP server in PolicyLayer and add a rule for recent_changes: 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 Repo Explainer MCP. Nothing to install.
recent_changes 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 recent_changes 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 recent_changes. 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.
recent_changes is provided by the GitHub Repo Explainer MCP server (pranavvr/repo_explainer_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 →