REQUIRED: Call this BEFORE telling the user that a code change / feature / fix is complete. Runs the full Pinned check: scan-diff for unprotected risk surfaces, Guard Integrity check for any tests in tests/pinned/ that were weakened/skipped/deleted, and AI-lessons check. Returns PASS / REVIEW / B...
AI agents call pinned_before_done_check 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 tool performs scanning, guard integrity validation, and lesson-checking—all inspection and analysis activities with no side effects. It returns status information and findings but does not create, modify, delete, or execute external operations. The purpose is to validate and inform, not to alter state. Confidence is high due to clear read-only semantics in the description.
From the tool's definition The tool 'pinned_before_done_check' runs checks and 'Returns PASS / REVIEW / BLOCK plus a [report]'. The description indicates it performs scanning, validation, and analysis operations that retrieve and report information without modifying code, tests, or any…
Attacks that exploit this kind of access
REQUIRED: Call this BEFORE telling the user that a code change / feature / fix is complete. Runs the full Pinned check: scan-diff for unprotected risk surfaces, Guard Integrity check for any tests in tests/pinned/ that were weakened/skipped/deleted, and AI-lessons check. Returns PASS / REVIEW / BLOCK plus a. 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_before_done_check: 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_before_done_check 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_before_done_check 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_before_done_check. 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_before_done_check 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 →