graphify_build · VibeServe MCP: Risk & Policy

WHAT IT DOES

What graphify_build does on VibeServe

AI agents use graphify_build to create or update resources in VibeServe — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VibeServe environment.

WHY IT NEEDS A POLICY

Why graphify_build needs a policy

The tool analyzes the codebase and produces new files as output. This is a Write operation since it creates new artifacts on disk. It is not Destructive (no deletion), not Execute (no code execution or shell commands beyond AST parsing), and not Read (it has persistent side effects in the form of created files).

From the tool's definition 'Creates graph.json + wiki articles + interactive HTML visualization' — the tool generates and writes multiple output files (graph.json, wiki articles, HTML) to the local filesystem.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

graphify_build Rate-limited

graphify_build stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "graphify_build": {
      "limits": [
        {
          "counter": "graphify_build_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches VibeServe, so you can run agents against it safely.

FAQ

Questions about graphify_build

What does the graphify_build tool do? +

Build a knowledge graph from the codebase using tree-sitter AST analysis. Creates graph.json + wiki articles + interactive HTML visualization. 100% local, zero API cost. Reduces codebase recall tokens by up to 71x. It is categorised as a Write tool in the VibeServe MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on graphify_build? +

Register the VibeServe MCP server in PolicyLayer and add a rule for graphify_build: 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.

What risk level is graphify_build? +

graphify_build is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit graphify_build? +

Yes. Add a rate_limit block to the graphify_build 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.

How do I block graphify_build completely? +

Set action: deny in the PolicyLayer policy for graphify_build. 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.

What MCP server provides graphify_build? +

graphify_build 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.