get_commit
AI agents call get_commit to retrieve information from GitHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_commit' tool retrieves commit data from a repository without modifying, deleting, or executing any operations. This is consistent with Read category tools (search, list, get, fetch). The empty description lowers confidence slightly, but the clear 'get' verb in the name and the established pattern of sibling tools makes Read the appropriate classification.
From the tool's definition Tool name 'get_commit' indicates retrieval of commit information from GitHub API. Description is empty, but the name and context (sibling tools include write/execute operations like create_branch, create_commit_status, create_issue) strongly suggest this is a…
Attacks that exploit this kind of access
get_commit. It is categorised as a Read tool in the GitHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for get_commit: 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 MCP Server. Nothing to install.
get_commit 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 get_commit 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 get_commit. 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.
get_commit is provided by the GitHub MCP Server MCP server (software-engineer-mj/github-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 →