Parse a PR description / commit message / spec for behavioral claims (auth, rate-limits, webhook idempotency, permissions, URL preservation, status codes, etc.) and return the structured claim list. Call this when the user shows you a PR body or asks
AI agents call pinned_check_pr_description to retrieve information from Pinnedai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure read operation that analyzes text input and extracts information. It retrieves and structures data from existing PR descriptions without modifying, executing, or deleting anything. The blast radius of misuse is minimal—worst case, the agent extracts incorrect or irrelevant claims, which is caught by human review and does not alter systems or data.
From the tool's definition The tool 'pinned_check_pr_description' parses and returns a structured claim list from PR descriptions/commit messages/specs. The verbs used are 'parse' and 'return'—no side effects, no modifications, no execution.
Attacks that exploit this kind of access
Parse a PR description / commit message / spec for behavioral claims (auth, rate-limits, webhook idempotency, permissions, URL preservation, status codes, etc.) and return the structured claim list. Call this when the user shows you a PR body or asks. It is categorised as a Read tool in the Pinnedai MCP Server, which means it retrieves data without modifying state.
Register the Pinnedai MCP server in PolicyLayer and add a rule for pinned_check_pr_description: 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 Pinnedai. Nothing to install.
pinned_check_pr_description 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 pinned_check_pr_description 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 pinned_check_pr_description. 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.
pinned_check_pr_description is provided by the Pinnedai MCP server (pinnedai/pinnedai). 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 →