Semantically search git commit history. Use this to find why code was changed, when decisions were made, or what an author worked on. Returns commits ranked by relevance to the query.
AI agents call search_commits to retrieve information from Local Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing git commit history data without side effects. It is informational and does not modify, execute, or delete anything. The blast radius of misuse is minimal—worst case an agent reads commit messages it shouldn't, a confidentiality concern rather than operational harm. Classified as Read with low severity.
From the tool's definition Tool performs semantic search on git commit history with results ranked by relevance. No modification, deletion, or execution capability—purely retrieval of historical commit data.
Documented attack patterns abuse exactly the kind of access search_commits gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Local Rag, and nothing reaches the server without passing your rules. This is the rule we recommend for search_commits:
{
"version": "1",
"default": "deny",
"tools": {
"search_commits": {}
}
}search_commits is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Semantically search git commit history. Use this to find why code was changed, when decisions were made, or what an author worked on. Returns commits ranked by relevance to the query. It is categorised as a Read tool in the Local Rag MCP Server, which means it retrieves data without modifying state.
Register the Local Rag MCP server in PolicyLayer and add a rule for search_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 Local Rag. Nothing to install.
search_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 search_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 search_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.
search_commits is provided by the Local Rag MCP server (thewinci/mimirs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Local Rag, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 Local Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.