AI agents call codegraph_query 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 information from a knowledge graph about code structure. It does not create, modify, delete, or execute operations—it only queries existing data. The blast radius of misuse is minimal; worst case, an agent learns incorrect information about the codebase, but no systems are altered.
From the tool's definition Tool description states 'Ask a structural question about the codebase OR look up a specific node by name', which are query/lookup operations. The verb 'look up' and the framing as asking questions indicate data retrieval with no modification capabilities.
Attacks that exploit this kind of access
Ask a structural question about the codebase OR look up a specific node by name — or both in one call. 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_query: 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_query 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_query 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_query. 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_query 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 →