Low Risk

search_git_history

Search indexed git history using natural language queries. Returns semantically relevant commits with metadata. Useful for finding past fixes, similar changes, or understanding how problems were solved before.

How to control search_git_history ↓

What search_git_history does on Qdrant MCP Server

AI agents call search_git_history to retrieve information from Qdrant MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why search_git_history needs a policy

This tool retrieves historical commit information via semantic search—a read-only operation with no side effects. It queries existing indexed data and presents results without altering the repository, commits, or any state. The natural language query interface does not grant code execution or write permissions.

From the tool's definition Tool performs 'search' and 'returns' data from indexed git history; described as querying and retrieving 'semantically relevant commits with metadata' with no mention of modifications, deletions, or execution capabilities.

Documented attack patterns abuse exactly the kind of access search_git_history gives an agent:

How to control search_git_history

PolicyLayer is an MCP gateway — it sits between your AI agents and Qdrant MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_git_history:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_git_history": {}
  }
}

search_git_history is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Qdrant MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about search_git_history

What does the search_git_history tool do? +

Search indexed git history using natural language queries. Returns semantically relevant commits with metadata. Useful for finding past fixes, similar changes, or understanding how problems were solved before. It is categorised as a Read tool in the Qdrant MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_git_history? +

Register the Qdrant MCP Server MCP server in PolicyLayer and add a rule for search_git_history: 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 Qdrant MCP Server. Nothing to install.

What risk level is search_git_history? +

search_git_history is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_git_history? +

Yes. Add a rate_limit block to the search_git_history 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.

How do I block search_git_history completely? +

Set action: deny in the PolicyLayer policy for search_git_history. 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.

What MCP server provides search_git_history? +

search_git_history is provided by the Qdrant MCP Server MCP server (mhalder/qdrant-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Qdrant MCP Server tool call.

Start from Qdrant MCP Server, 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.

20 Qdrant MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.