Count matches in files using ripgrep
AI agents call count-matches to retrieve information from Mcp Ripgrep without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation using ripgrep to count pattern matches across files. It retrieves information (match counts) without side effects like creating, modifying, or deleting data. Ripgrep is a file search tool, and counting matches is a passive analysis operation with no blast radius beyond information disclosure.
From the tool's definition Tool name 'count-matches' and description 'Count matches in files using ripgrep' indicate a query operation that retrieves aggregated data without modifying files or executing commands beyond search.
Attacks that exploit this kind of access
Count matches in files using ripgrep. It is categorised as a Read tool in the Mcp Ripgrep MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ripgrep MCP server in PolicyLayer and add a rule for count-matches: 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 Mcp Ripgrep. Nothing to install.
count-matches 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 count-matches 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 count-matches. 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.
count-matches is provided by the Mcp Ripgrep MCP server (mcp-ripgrep). 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 →