Extract related PR/MR links from description text
AI agents call extract_related_prs to retrieve information from Code Review without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and parses existing pull request description text to identify and extract related PR/MR links. It has no side effects—it does not create, modify, delete, or execute operations. It is purely a data retrieval and analysis function, making it a Read category tool with low severity as it poses minimal risk if misused by an AI agent (worst case: incorrect link identification).
From the tool's definition Tool performs text extraction and analysis of PR/MR descriptions without modifying data, pull requests, or their state. The verb 'extract' indicates information retrieval.
Attacks that exploit this kind of access
Extract related PR/MR links from description text. It is categorised as a Read tool in the Code Review MCP Server, which means it retrieves data without modifying state.
Register the Code Review MCP server in PolicyLayer and add a rule for extract_related_prs: 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 Code Review. Nothing to install.
extract_related_prs 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 extract_related_prs 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 extract_related_prs. 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.
extract_related_prs is provided by the Code Review MCP server (oldjii/code-review-mcp). 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 →