Summary
You'd reach for this when you need structured oversight across multiple AI agents with different roles and risk profiles. It enforces behavioral boundaries through manifest files that define permissions, escalation rules, and reliability controls per agent. The thirteen included manifests cover everything from public-facing coaching (lily) to strict financial workflows (harry) to legal guidance with compliance boundaries (aram). The drift detection catches when agents deviate from their defined parameters. If you're orchestrating specialized agents that need different trust levels and operating constraints, this gives you a governance layer instead of hoping prompt engineering holds up under load.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Nervous System
Deterministic governance lint for MCP server configurations, plus reference tooling for the 7 rules.
What each tool actually does
| Tool | Does real work? |
|---|---|
audit_mcp_config | Yes. Deterministic lint, zero dependencies, fully offline, never throws. Checks inline secrets in env, shell wrappers, unpinned packages, auto-install flags, broad filesystem scopes, non-TLS remote transports, unpinned docker tags. Returns findings with severities and a 0-100 score. |
check_preflight | Yes, when configured. Reads protected_files_list from nervous-system.config.json or NERVOUS_SYSTEM_PROTECTED_LIST. With no list it says so rather than guessing. If the list is unreadable it FAILS CLOSED. |
get_* (everything else) | No. They return text: the framework, templates, instructions. That is why they are named get_. |
Install
npx mcp-nervous-system
Free local tool: audit_mcp_config
Pass your config as config (object) or config_json (string), e.g. the contents of
claude_desktop_config.json. Returns findings with severities and a 0-100 score.
Hosted API (pay-per-call, x402, USDC on Base)
The write-capable toolset runs server-side and is not in this package.
POST https://api.100levelup.com/x402/audit-mcp- governance lint ($0.05 USDC)GET https://api.100levelup.com/x402/verify-audit- audit-chain verification ($0.005 USDC)
Discovery: /openapi.json and /llms.txt.
2.0.0 breaking changes
emergency_kill_switch->get_kill_switch_instructions. It never stopped anything.verify_audit_chain->get_audit_verification_instructions. It never verified a chain.dispatch_to_llm->get_dispatch_command. It never dispatched.check_preflightno longer matches hardcoded filenames from the author's own server. It reads your list.- Hardcoded fleet counts and violation totals removed from
get_origin_story. A number baked into a package is a fossil the moment it ships.
License
MIT
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Categories
Registryactive
Packagemcp-nervous-system
TransportSTDIO
UpdatedMar 9, 2026
