AI agents call graphify_query 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 performs read-only queries against a knowledge graph to retrieve information about code structure (functions, modules, connections). It has no side effects, does not execute code, does not modify data, and does not delete anything. The primary use case is information retrieval to reduce token usage when exploring a codebase, which is characteristic of Read category tools.
From the tool's definition Tool description states 'Query the knowledge graph' and 'Find functions, modules, and their connections' — both are retrieval/query operations with no mention of modification, deletion, or execution capabilities.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Query the knowledge graph instead of reading entire files. Find functions, modules, and their connections with minimal tokens. 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 graphify_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 VibeServe. Nothing to install.
graphify_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 graphify_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 graphify_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.
graphify_query 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 →