AI agents call codegraph_report to retrieve information from Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays analysis metadata (god nodes, clusters, connections, questions) from an existing report. It performs no write, execute, or destructive operations—it simply reads and formats pre-computed knowledge graph analysis for display. No side effects or irreversible actions occur.
From the tool's definition Tool returns a pre-generated report file (CODEGRAPH_REPORT.md) containing analysis of code structure. Words like 'return' and 'report' indicate data retrieval with no modification, creation, or deletion of persistent state.
Attacks that exploit this kind of access
Return CODEGRAPH_REPORT.md — god nodes, clusters, surprising connections, suggested questions. It is categorised as a Read tool in the Context MCP Server, which means it retrieves data without modifying state.
Register the Context MCP server in PolicyLayer and add a rule for codegraph_report: 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 Context. Nothing to install.
codegraph_report 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 codegraph_report 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 codegraph_report. 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.
codegraph_report is provided by the Context MCP server (vibhasdutta/context-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 →