AI agents call codegraph_arch 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 queries the codebase knowledge graph to extract and return architectural information (module exports and imports). It performs analysis and retrieval only, with no capability to modify, delete, or execute code. The operation is purely informational and has no blast radius if called with any arguments.
From the tool's definition Tool description states 'Return a module map' with exported functions/classes and imports — a retrieval/query operation with no side effects. The verb 'Return' and focus on mapping/analyzing existing code structure confirms read-only semantics.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Return a module map: every file with its exported functions/classes and what it imports. 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_arch: 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_arch 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_arch 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_arch. 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_arch 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 →