Given changed files or a unified diff, compute full blast radius with risk scores (HIGH/MEDIUM/LOW), test coverage gaps, and top files to review.
AI agents call pr_impact to retrieve information from code-intel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
pr_impact performs static analysis on provided code changes to generate insights (blast radius analysis, risk scoring, coverage recommendations). It reads and analyzes data without creating side effects, modifying codebases, or executing arbitrary operations. The analysis is informational for review purposes, placing it firmly in the Read category.
From the tool's definition The tool 'compute[s] full blast radius with risk scores' and identifies 'test coverage gaps' and 'top files to review' from 'changed files or a unified diff'. These are analytical outputs derived from code analysis—no code is executed, modified, or deleted.
Attacks that exploit this kind of access
Given changed files or a unified diff, compute full blast radius with risk scores (HIGH/MEDIUM/LOW), test coverage gaps, and top files to review. It is categorised as a Read tool in the code-intel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the code-intel MCP Server MCP server in PolicyLayer and add a rule for pr_impact: 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-intel MCP Server. Nothing to install.
pr_impact 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 pr_impact 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 pr_impact. 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.
pr_impact is provided by the code-intel MCP Server MCP server (vohongtho/code-intel-platform). 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 →