github_list_commits
AI agents call github_list_commits to retrieve information from Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Listing commits is a retrieval operation that queries repository data without modifying, deleting, or executing anything. It falls squarely into the Read category. Severity is low because commit history is typically public or otherwise accessible information with no blast radius from unauthorized queries.
From the tool's definition Tool name 'github_list_commits' indicates a list/query operation (list, get, fetch pattern) that retrieves commit history from GitHub. The 'list_' prefix is a strong signal of a read-only operation with no side effects.
Attacks that exploit this kind of access
github_list_commits. It is categorised as a Read tool in the Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Integrations MCP server in PolicyLayer and add a rule for github_list_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 Integrations MCP. Nothing to install.
github_list_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_list_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_list_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_list_commits is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →