AI agents call codegraph_context to retrieve information from VibeServe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes code structure information (symbol analysis, call graphs, inheritance relationships) without creating, modifying, executing, or deleting anything. It is purely informational and has no side effects on the codebase or system. The blast radius if misused (e.g., to map out sensitive code paths) is limited to information disclosure.
From the tool's definition Tool description states 'Get 360-degree view' and lists retrieval operations: 'incoming/outgoing calls, inheritance, imports, and cluster membership' — all query/inspection actions with no modification.
Attacks that exploit this kind of access
Get 360-degree view of a symbol — all incoming/outgoing calls, inheritance, imports, and cluster membership. It is categorised as a Read tool in the VibeServe MCP Server, which means it retrieves data without modifying state.
Register the VibeServe MCP server in PolicyLayer and add a rule for codegraph_context: 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 VibeServe. Nothing to install.
codegraph_context 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_context 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_context. 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_context is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →