pr-checks

SERVERHttp SOURCE@paretools/http

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-dave-london-http/pr-checks.md

WHAT IT DOES

What pr-checks does on Http

AI agents call pr-checks 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.

RISK

Why pr-checks is rated Low

This tool retrieves and queries status information about pull request checks without modifying any data, making side effects, or executing operations. It is a pure read operation that fetches metadata about CI/CD check results. The polling mechanism is still a read operation—it repeatedly queries the same endpoint until a condition is met, rather than triggering actions or modifications.

From the tool's definition Tool description states it 'Lists check/status results for a pull request' and 'Returns structured data with check names, states, URLs, and summary counts'. The polling behavior with watch=true is an internal query mechanism, not a side effect.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs pr-checks 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 pr-checks, this is the rule to start with:

pr-checks Allowed

pr-checks is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pr-checks": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Http, apply this rule, and every pr-checks call is checked against it from then on.

FAQ

Questions about pr-checks

What does the pr-checks tool do? +

Lists check/status results for a pull request. Returns structured data with check names, states, URLs, and summary counts (passed, failed, pending). When watch=true, polls internally until all checks complete (or timeout). It is categorised as a Read tool in the Http MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on pr-checks? +

Register the Http MCP server in PolicyLayer and add a rule for pr-checks: 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.

What risk level is pr-checks? +

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

Can I rate-limit pr-checks? +

Yes. Add a rate_limit block to the pr-checks 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 pr-checks completely? +

Set action: deny in the PolicyLayer policy for pr-checks. 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 pr-checks? +

pr-checks 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.

KEEP EXPLORING

More on Http, and thousands of servers like it.

This server

All 202 Http tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →