Given a unified diff, compute changed files and 1-hop impacted neighbors
AI agents call graph.impact_from_diff to retrieve information from CodeGraph MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool takes a diff as input and analyzes the code graph to determine what is impacted. It performs read/query operations only — computing relationships and reporting results without modifying any data, executing code, or causing side effects.
From the tool's definition 'compute changed files and 1-hop impacted neighbors' from a unified diff — purely analytical/query operation on the code graph
Attacks that exploit this kind of access
Given a unified diff, compute changed files and 1-hop impacted neighbors. It is categorised as a Read tool in the CodeGraph MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CodeGraph MCP Server MCP server in PolicyLayer and add a rule for graph.impact_from_diff: 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 CodeGraph MCP Server. Nothing to install.
graph.impact_from_diff 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 graph.impact_from_diff 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 graph.impact_from_diff. 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.
graph.impact_from_diff is provided by the CodeGraph MCP Server MCP server (nabiatech/codegraph-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 →