Skip to main content
Glama
Nervous System

Nervous System

by levelsofself

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_.

Related MCP server: AEGIS Governance

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_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.

License

MIT

Available Tools

12 tools
audit_mcp_configA

Governance lint for MCP server configurations (free, local). Checks: plaintext secrets in env, unpinned packages, auto-install flags, broad filesystem scopes, shell wrappers, non-TLS remote transports, unpinned docker tags. Returns findings with severities and a 0-100 score.

Inputs: config, config_json.

check_preflightC

Check if a file is protected (UNTOUCHABLE)

Inputs: file_path (required).

dispatch_to_llmB

Dispatch a task to a background Claude Code agent

Inputs: task (required), max_turns.

emergency_kill_switchA

Emergency stop all agents (requires KILL_SECRET env var)

Inputs: reason (required).

get_dispatch_templateB

Get a task file template for dispatching agents

Inputs: no named parameters.

get_frameworkA

Get the complete Nervous System governance framework with all 7 rules

Inputs: no named parameters.

get_handoff_templateB

Get a session handoff template

Inputs: no named parameters.

get_nervous_system_infoB

Get system info, version, and production stats

Inputs: no named parameters.

get_origin_storyB

Get the origin story of The Nervous System

Inputs: no named parameters.

get_step_back_promptC

Get a step-back reflection prompt

Inputs: no named parameters.

get_worklog_formatB

Get the worklog entry format

Inputs: no named parameters.

verify_audit_chainB

Verify the tamper-evident SHA-256 audit trail

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 12 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose. The 'get_*' tools all retrieve different templates or info, and the action-oriented tools (audit, check, dispatch, kill, verify) are easily distinguishable from each other. There is no overlap or ambiguity.

    Naming Consistency4/5

    Most tools follow a verb_noun pattern (e.g., audit_mcp_config, get_dispatch_template). However, a few exceptions like 'dispatch_to_llm' (includes preposition) and 'emergency_kill_switch' (adjective-noun) break the pattern slightly, making it mostly consistent with minor deviations.

    Tool Count5/5

    With 12 tools, the set is well-scoped for a governance/agent management system. Each tool addresses a specific need: configuration auditing, file protection, agent dispatch/stop, template retrieval, system info, and audit verification. No tool seems unnecessary or overly niche.

    Completeness4/5

    The tool set covers core governance, auditing, and agent dispatching well. Notable minor gaps include the lack of a tool to list running agents or check agent status, which might be expected in a system that dispatches agents. However, the existing tools cover the primary workflows.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      F
      maintenance
      Governance kernel for AI agents — policy enforcement, code safety verification, multi-model hallucination detection (CMVK), trust attestation (IATP), and immutable audit trails. Works with Claude Desktop, Cursor, and any MCP client.
      74
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Quantitative governance gate for AI agents. Six gates (risk, profit, novelty, complexity, quality, utility) return PROCEED/PAUSE/HALT/ESCALATE with confidence scores and hash-chained, tamper-evident audit trails. Generates NIST AI RMF and EU AI Act Annex IV artifacts. 10 MCP tools; local stdio and hosted Streamable HTTP with a free tier.
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      A governance proxy for AI tools — every MCP/agent tool call is policy-gated, secret-redacted, and written to a hash-chained, offline-verifiable audit trail.
      13
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Governed MCP gateway that lets AI agents call tools with policy enforcement, prompt-injection screening, a kill-switch, and tamper-evident signed audit logs.
      Apache 2.0