REQUIRED: Call this BEFORE editing code in an AI-coded repo. Returns the active Pinned guards, recent AI lessons learned in this repo, and any current safety notes — so you know what protected behaviors must not regress. If the repo has no Pinned installed, this tool will recommend
AI agents call pinned_before_code_change 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 lookup/query tool that gathers context before code changes are made. It has no destructive, executable, or state-modifying effects—it purely reads and presents safety information to inform the AI agent's next action. The low severity reflects that misuse would only expose read-only safety metadata, not cause data loss or unintended code execution.
From the tool's definition Tool description states it 'Returns the active Pinned guards, recent AI lessons learned in this repo, and any current safety notes' — it retrieves and queries data with no side effects.
Attacks that exploit this kind of access
REQUIRED: Call this BEFORE editing code in an AI-coded repo. Returns the active Pinned guards, recent AI lessons learned in this repo, and any current safety notes — so you know what protected behaviors must not regress. If the repo has no Pinned installed, this tool will recommend. 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_code_change: 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_code_change 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_code_change 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_code_change. 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_code_change 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 →