AI agents call codegraph_impact 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 existing code structure and dependency information to inform decision-making. It has no side effects—it does not execute code, modify files, delete anything, or trigger external operations. It is purely informational, helping developers understand impact before they make changes themselves. This is a classic Read operation (search/query with analysis).
From the tool's definition The tool performs 'blast radius analysis' and groups results by dependency depth (WILL BREAK, LIKELY AFFECTED, MIGHT AFFECT).
Attacks that exploit this kind of access
Blast radius analysis — what depends on this symbol? Groups results by depth (WILL BREAK, LIKELY AFFECTED, MIGHT AFFECT). Use before refactoring. 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_impact: 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_impact 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_impact 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_impact. 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_impact 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 →