build_manifest_preview · Manifest MCP: Risk & Policy

WHAT IT DOES

What build_manifest_preview does on Manifest MCP

AI agents invoke build_manifest_preview to trigger actions in Manifest MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why build_manifest_preview needs a policy

This is an Execute tool because it runs validation logic and computational operations (SHA-256 hashing, rule validation) whose outputs depend on complex input processing. It is not Destructive because it only previews/validates without modifying on-chain state. It is not Write because it doesn't commit changes—it's explicitly a pre-deployment check.

From the tool's definition Tool computes SHA-256 hashes and validates manifests against documented rules, which involves processing inputs to produce deterministic outputs.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

build_manifest_preview Rate-limited

build_manifest_preview stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "build_manifest_preview": {
      "limits": [
        {
          "counter": "build_manifest_preview_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about build_manifest_preview

What does the build_manifest_preview tool do? +

Build a deployment manifest, validate it against the documented Fred rules, and compute the SHA-256 meta_hash that would be recorded on-chain. Use this BEFORE deploy_app to catch invalid manifests without paying for a lease. Two modes: raw. It is categorised as a Execute tool in the Manifest MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on build_manifest_preview? +

Register the Manifest MCP server in PolicyLayer and add a rule for build_manifest_preview: 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 Manifest MCP. Nothing to install.

What risk level is build_manifest_preview? +

build_manifest_preview is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit build_manifest_preview? +

Yes. Add a rate_limit block to the build_manifest_preview 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 build_manifest_preview completely? +

Set action: deny in the PolicyLayer policy for build_manifest_preview. 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 build_manifest_preview? +

build_manifest_preview is provided by the Manifest MCP server (manifest-network/manifest-mcp-mono). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.