AI agents call git_search to retrieve information from Git without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs searching operations (pickaxe and grep are standard Git search mechanisms) which retrieve and analyze data without creating, modifying, or deleting any repository state. This is a typical Read operation with minimal risk—misuse would result in information disclosure rather than corruption or unauthorized changes to the repository.
From the tool's definition Tool name 'git_search' combined with description 'Search code and history using pickaxe and grep' indicates read-only operations that query Git repository contents without modification.
Attacks that exploit this kind of access
Search code and history using pickaxe and grep. It is categorised as a Read tool in the Git MCP Server, which means it retrieves data without modifying state.
Register the Git MCP server in PolicyLayer and add a rule for git_search: 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 Git. Nothing to install.
git_search 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 git_search 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 git_search. 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.
git_search is provided by the Git MCP server (selfagency/git-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 →