// SCAN REPORT

Vibe Stack MCP

9 tools. 3 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 4 Jul 2026

3 can modify or destroy data

6 read-only

9 tools total

Community server · catalogue entry verified 04/07/2026

How to control Vibe Stack MCP ↓

TOOL MAP

What Vibe Stack MCP exposes to your agents

Read (6) Write / Execute (2) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Vibe Stack MCP tools

Financial · Critical finalize_planning finalize_planning Execute · Medium collect_scale_timeline collect_scale_timeline Execute · Medium start_project_planning start_project_planning

3 of Vibe Stack MCP's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Vibe Stack MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Vibe Stack MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "finalize_planning": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Cap read operations

{
  "collect_features_data": {
    "limits": [
      {
        "counter": "collect_features_data_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Vibe Stack MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON VIBE STACK →

Instant setup, no code required.

FULL CATALOGUE

All 9 Vibe Stack MCP tools

FINANCIAL 1 tools

Financial finalize_planning finalize_planning

EXECUTE 2 tools

Execute collect_scale_timeline collect_scale_timeline Execute start_project_planning start_project_planning

READ 6 tools

Read collect_features_data collect_features_data Read collect_project_vision Collect your project vision and move to the next step of planning. Read collect_user_info collect_user_info Read explain_recommendation Get a detailed explanation of why specific technologies were recommended. Read get_deployment_guide Get step-by-step deployment instructions for your recommended stack. Read recommend_stack Get tech stack recommendations. If you haven't completed the planning process,

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Vibe Stack MCP

Can an AI agent move money through the Vibe Stack MCP server? +

Yes. The Vibe Stack MCP server exposes 1 financial tools including finalize_planning. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How many tools does the Vibe Stack MCP server expose? +

9 tools across 3 categories: Execute, Financial, Read. 6 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Vibe Stack MCP? +

Register the Vibe Stack MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Vibe Stack MCP tool call.

Deterministic rules across all 9 Vibe Stack MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON VIBE STACK →

Instant setup, no code required.

9 Vibe Stack MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.