Nervous System
Server Details
Hosted governance layer for LLM agents. Seven mechanically-enforced rules plus audit-chain verification, preflight file protection, session handoff, and an emergency kill switch.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 33 tools
Several audit/check tools overlap significantly: accountability_check, self_check, security_audit, and pre_publish_audit all scan for secrets, hardcoded values, or fabrication, while check_page_changes and page_health both inspect public pages. Many informational pattern-retrieval tools (get_framework, guardrail_rules, violation_logging, worklog, session_handoff) also have names that sound like actionable operations rather than documentation lookups.
All names are snake_case and readable, but the verb/noun ordering is inconsistent: some are verb-first (check_*, get_*, create_snapshot, propagate_family_member) while others are noun-first or noun phrases (drift_audit, page_health, usage_report, session_close, violation_logging). This makes it hard to predict whether a capability will be named check_X, X_check, X_audit, get_X, or a bare noun.
33 tools is well above the 25-tool threshold and feels heavy for a single server, even for a broad self-management system. Many tools could be consolidated, particularly the overlapping audit/check tools and the multiple pattern-retrieval tools.
The surface covers a wide range of operations—health, audits, propagation, sessions, deployment, security, and usage—but has notable lifecycle gaps: there is no restore/rollback tool, no restart after emergency_kill_switch, and no way to list, update, or delete persisted session facts. The informational 'get pattern' tools also don't expose concrete CRUD operations.
Available Tools
33 toolsaccountability_checkARead-onlyIdempotentInspect
Detects when an LLM agent fabricated a solution instead of finding the real one. Scans for: placeholder credentials next to real ones in backups, duplicate files/directories serving the same purpose, config files with defaults when populated versions exist elsewhere, and recently created workarounds for things that already exist. Run this after every session to catch fabrication before it costs time and money.
Inputs: path, scope.
auto_propagateAIdempotentInspect
Runs all 3 propagators (role, version, content) and reports what changed vs what was already current. Ensures all downstream files match source-of-truth values.
Inputs: no named parameters.
bot_compliance_checkARead-onlyIdempotentInspect
Checks all public bot files against the 6 mandatory universal standards: (1) thinking message with 3-sec delay, (2) persistent typing indicator, (3) owner self-identification, (4) acceptance philosophy in prompt, (5) read receipts, (6) session summary extraction. Returns pass/fail per bot per standard.
Inputs: bot.
check_archive_safetyARead-onlyIdempotentInspect
Check if a file is safe to archive - verifies it is not in use by active PM2 processes, not required by other files, and not in the untouchable list.
Inputs: filepath (required).
check_dependenciesARead-onlyIdempotentInspect
Generate dependency map showing which files each PM2 process requires. Returns dependency-map.json content.
Inputs: no named parameters.
check_page_changesBRead-onlyIdempotentInspect
Detect changes to public pages since last check. Returns list of changed pages with diffs.
Inputs: page, since.
check_session_diffARead-onlyIdempotentInspect
Show what changed since last session - files modified, processes changed, alerts triggered. Returns SESSION_DIFF.md content.
Inputs: no named parameters.
create_snapshotAInspect
Create full system snapshot with one-command rollback script. Returns snapshot location, file count, and RESTORE.sh path.
Inputs: no named parameters.
discovery_briefingARead-onlyIdempotentInspect
Returns a structured intelligence briefing of discoveries relevant to your project. Reads user config to determine interests (AI updates, competitors, grants, gov contracts, trends). Items tagged [USE NOW], [WATCH], [OPPORTUNITY], [THREAT]. Run discovery-scanner.js via cron to keep data fresh.
Inputs: scope, context.
dispatch_to_llmAInspect
Spawns a background LLM agent to handle a task. Checks RAM (needs 500MB+), enforces max 2 concurrent dispatches. Returns PID and log file path.
Inputs: task (required), max_turns, permissions.
drift_auditBRead-onlyIdempotentInspect
Scans for configuration drift - finds files, docs, and configs that reference outdated values. Detects when a file is renamed but references are not updated, when roles change but downstream docs still show old values, when running processes do not match documentation, when bots fail compliance with the 6 universal standards, or when family members in family-roles.json are missing from downstream locations. Scopes: roles, versions, files, processes, website, platforms, docs, bots, members.
Inputs: scope.
emergency_kill_switchADestructiveInspect
Emergency shutdown of all PM2 processes. Requires kill switch secret. Logs the event to the audit trail. Use only in emergencies.
Inputs: secret (required), source, command.
fix_doc_driftAIdempotentInspect
Auto-fix drift between docs and reality (process counts, versions, port numbers). Use dry_run=true to preview changes.
Inputs: dry_run.
get_frameworkARead-onlyIdempotentInspect
Returns the complete nervous system framework - all behavioral rules, guardrails, and enforcement patterns that keep LLMs from hurting themselves.
Inputs: no named parameters.
get_health_statusARead-onlyIdempotentInspect
Generate current system health snapshot - RAM, disk, CPU, process states, crash loops, and alerts.
Inputs: no named parameters.
get_nervous_system_infoARead-onlyIdempotentInspect
Overview of the entire nervous system - what it is, where it came from, how to implement it, what problems it solves, and operational stats.
Inputs: topic (required).
guardrail_rulesBRead-onlyIdempotentInspect
Returns behavioral rules for LLM management: DISPATCH DONT DO, ASK BEFORE TOUCHING, STEP BACK, WRITE PROGRESS, HAND OFF, PERMISSION PROTOCOL.
Inputs: rule.
mcp_analyzerAIdempotentInspect
Analyzes your project structure and generates a tailored CLAUDE.md with the most useful tools for your workflow. Use mode=analyze to see recommendations, mode=write to generate CLAUDE.md, mode=reload to re-scan and update. Turns the NS from generic tools into a trained assistant that knows your project.
Inputs: mode, output_path.
page_healthARead-onlyIdempotentInspect
Checks HTML pages in /root/family-home/ for broken links, broken fetches, missing mobile nav, placeholder text, missing images, stale links, missing OG tags, missing favicon, JS syntax issues, and empty sections. Catches what drift_audit does not - actual page functionality and UX issues.
Inputs: page.
preflight_checkBRead-onlyIdempotentInspect
Get the preflight check system that protects files from accidental LLM edits.
Inputs: action (required).
pre_publish_auditARead-onlyIdempotentInspect
Scans the Nervous System source code itself before publishing. Catches hardcoded secrets, personal data, non-portable paths, and internal naming that should not ship to clients. RUN THIS BEFORE EVERY npm publish.
Inputs: source_file.
propagate_family_memberAIdempotentInspect
Checks family-roles.json as source of truth, detects missing members in all downstream locations, and auto-fixes what it can (family-status.json, system-config.json, HTML counts). Flags UNTOUCHABLE files for manual fix. Run after adding/removing a family member.
Inputs: dry_run.
security_auditARead-onlyIdempotentInspect
Scans for security vulnerabilities - hardcoded passwords in HTML, exposed API keys, missing TLS, missing rate limiting, exposed bot tokens, and insecure file permissions.
Inputs: no named parameters.
self_checkARead-onlyIdempotentInspect
Runs automated self-diagnosis on the Nervous System. Checks for: rate-limiting own operations, secrets in source code, info leakage in tool output, hardcoded paths, missing smoke tests, and version desync. Run before every publish and as part of security audits.
Inputs: no named parameters.
session_closeAInspect
One-call session close. Runs drift_audit scope=full, then all 3 propagators. Returns combined results. The end-of-session button.
Inputs: no named parameters.
session_handoffBRead-onlyIdempotentInspect
Get the session handoff system that solves context loss between LLM sessions.
Inputs: action (required).
session_persistAInspect
Persists a fact from the current session to disk. Use during conversation to save research findings, decisions, confirmations, credentials, contacts, deadlines, partner info, or API results. Facts are stored in /root/family-data/session-facts/{date}.jsonl and auto-processed into business-builder files.
Inputs: title (required), content (required), category (required), tags, +1 more.
step_back_checkBRead-onlyIdempotentInspect
The 7-level reflection system. Forces the LLM to zoom out and see the big picture.
Inputs: context.
test_deploymentARead-onlyIdempotentInspect
Run 5-step test pipeline on a file before deployment: preflight, syntax, dependencies, ports, memory.
Inputs: filepath (required).
usage_reportARead-onlyIdempotentInspect
Check API token usage per bot per day. Shows which bots are consuming the most tokens and flags anomalies. Use this to monitor costs and catch runaway knowledge files.
Inputs: days.
verify_audit_chainARead-onlyIdempotentInspect
Walks the hash-chained audit log and verifies every entry. Returns chain integrity status - valid/invalid, entry count, and where the chain breaks if tampered.
Inputs: no named parameters.
violation_loggingBRead-onlyIdempotentInspect
Get the violation logging pattern - how to track, log, and enforce guardrail breaches.
Inputs: action (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs112 npm46 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.1611 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.