count
Counts pattern matches per file using ripgrep. Returns per-file match counts and totals.
This record as markdown: /tools/io-github-dave-london-http/count.md
What count does on Http
AI agents call count to retrieve information from Http without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why count is rated Low
The tool performs a read-only search operation across files using ripgrep (a file searching utility). It only returns counts of pattern matches without modifying data, executing code, or causing side effects. This is a classic Read category operation similar to grep or file querying.
From the tool's definition Tool 'count' uses ripgrep to count pattern matches per file, returning match counts and totals. This is a search/grep operation with no modification of files or execution of arbitrary code.
Attacks that exploit this kind of access
The rule that runs count safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Http, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For count, this is the rule to start with:
count is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Http, apply this rule, and every count call is checked against it from then on.
Questions about count
Counts pattern matches per file using ripgrep. Returns per-file match counts and totals. It is categorised as a Read tool in the Http MCP Server, which means it retrieves data without modifying state.
Register the Http MCP server in PolicyLayer and add a rule for count: 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 Http. Nothing to install.
count 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 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. 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 is provided by the Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Http, and thousands of servers like it.
This server
Across the catalogue