The Nervous System server provides governance tooling and coordination for multi-agent AI systems. Here's what you can do:
Tools That Do Real Work
audit_mcp_config – Governance lint on MCP server configs (checks plaintext secrets, unpinned packages, broad filesystem scopes, auto-install flags, non-TLS transports, etc.). Returns findings with severities and a 0–100 score. Fully offline.
check_preflight – Check whether a file path is protected (UNTOUCHABLE) before modification. Fails closed if the protected list is unreadable.
Informational / Template Retrieval (get_*)
get_framework – Retrieve the full Nervous System governance framework (all 7 rules).
get_nervous_system_info – Get system info, version, and production stats.
get_origin_story – Get the origin story of The Nervous System.
get_handoff_template – Get a session handoff template for agent transitions.
get_worklog_format – Get the standard worklog entry format.
get_step_back_prompt – Get a step-back reflection prompt for agent reasoning.
get_dispatch_template – Get a task file template for dispatching agents.
⚠️ Legacy Tools (return instructions/templates, do NOT perform the implied action)
emergency_kill_switch – Returns kill-switch instructions; does not actually stop agents. (Renamed get_kill_switch_instructions in v2.0.0.)
verify_audit_chain – Returns audit verification instructions; does not actually verify a SHA-256 chain. (Renamed get_audit_verification_instructions in v2.0.0.)
dispatch_to_llm – Returns a dispatch command/template; does not actually dispatch to a background agent. (Renamed get_dispatch_command in v2.0.0.)
Hosted Pay-Per-Call API (separate from local server)
POST https://api.100levelup.com/x402/audit-mcp – Governance lint with audit-chain verification ($0.05 USDC)
GET https://api.100levelup.com/x402/verify-audit – Audit-chain verification ($0.005 USDC)
Deterministic governance lint for MCP server configurations, plus reference tooling for the 7 rules.
Tool | Does real work? |
| 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. |
| Yes, when configured. Reads |
| No. They return text: the framework, templates, instructions. That is why they are named |
Related MCP server: dingdawg-governance
npx mcp-nervous-systemPass 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.
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.
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_preflight no 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.
MIT
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Six-gate governance for AI agents: PROCEED/PAUSE/HALT decisions with hash-chained audit trails.
Hash-chained HMAC-signed audit log MCP for A2A (agent-to-agent) calls. Every tool-call, agent-ha...
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/levelsofself/mcp-nervous-system'
If you have feedback or need assistance with the MCP directory API, please join our Discord server