15 tools. 13 can modify or destroy data without limits.
2 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (muse_batch, muse_template) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (muse_auto_tag, muse_collect_code_context, muse_create_session_log) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Intercept sits between your agent and Vibe Coding. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.
npx -y @policylayer/intercept scan -- npx -y @vibe-coding-mcp muse_batch:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
muse_auto_tag:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
muse_analyze_code:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Vibe Coding server exposes 2 destructive tools including muse_batch, muse_template. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Vibe Coding server has 11 write tools including muse_auto_tag, muse_collect_code_context, muse_create_session_log. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
15 tools across 3 categories: Destructive, Read, Write. 2 are read-only. 13 can modify, create, or delete data.
One line change. Instead of running the Vibe Coding server directly, prefix it with Intercept: intercept -c io-github-muse-code-space-vibe-coding.yaml -- npx -y @vibe-coding-mcp. Download a pre-built policy from policylayer.com/policies/io-github-muse-code-space-vibe-coding and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
npx -y @policylayer/intercept init