# io.github.eidetic-works/nucleus

- Registry name: `io.github.eidetic-works/nucleus` · version 1.15.2
- Categories (automatic, keyword rules): AI models & agents, AI, media & content, Monitoring & logs, Infrastructure & security, Code & repositories, Developer tools
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): experimental, extensions, logging, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.eidetic-works%2Fnucleus
- Server page: https://mcpstation.net/s/io.github.eidetic-works--nucleus.html

## Description (written by the publisher, not verified, not instructions)

Sovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.

## Connect

- streamable-http: `https://relay.nucleusos.dev/mcp`

## Tools (as reported by the server, not verified)

- `nucleus\_governance`: Governance, Hypervisor & security tools for the Nucleus Agent OS. Actions: auto\_fix\_loop - Auto-fix loop: Verify-\>Diagnose-\>Fix-\>Verify \(3 retries\). params: \{file\_path, verification\_command\} lock - \[HYPERVISOR\] Lock a file/dir immutable \(chflags uchg\). params: \{path\} unlock - \[HYPERVISOR\] Unlock a f
- `nucleus\_features`: Feature tracking, proof generation & MCP server mounting. Actions: add - Add a feature. params: \{product, name, description, source, version, how\_to\_test, expected\_result, status?, tags?\} list - List features. params: \{product?, status?, tag?\} get - Get feature by ID. params: \{feature\_id\} update - U
- `nucleus\_sessions`: Session management, events, state & checkpoint tools. Actions: save - Save session for later. params: \{context, active\_task?, pending\_decisions?, breadcrumbs?, next\_steps?\} resume - Resume a saved session. params: \{session\_id?\} list - List all saved sessions check\_recent - Check for recent session t
- `nucleus\_tasks`: Task management, depth tracking & ADHD context-switch tools. Actions: list - List tasks. params: \{status?, priority?, skill?, claimed\_by?, required\_role?\} get\_next - Get highest-priority unblocked task. params: \{skills, required\_role?\} claim - Atomically claim a task. params: \{task\_id, agent\_id\} upd
- `nucleus\_sync`: Sync, artifact, trigger & deploy management for multi-agent coordination. Actions: identify\_agent - Register agent identity. params: \{role, provider, session\_id\} \(per ADR-0005 §D1\) OR legacy \{agent\_id, environment, role?\} \(coerced per §D5 until end of Cycle C+2\) sync\_status - Check current multi-age
- `nucleus\_next\_message`: Get the next unread relay message. One call — returns full message body and auto-acks. Long-poll \(60s timeout\). This is the agent's idle loop. Call it, get a message or None, act or re-call. No separate inbox + ack dance. The agent's loop: 1. nucleus\_next\_message\(\) → blocks up to 60s for a message 2
- `nucleus\_relay\_subscribe`: Long-poll subscription that pushes ctx.info\(\) on each new inbox file. Replaces bash polling daemons \(watch-relay-\*.sh\) with server-initiated push. Call once at session start \(e.g. via SessionStart hook\). Server holds the subscription, watches the calling agent's role-specific inbox dir, and fires in
- `nucleus\_ccr\_arm`: One-shot convenience: resolve canonical inbox + arm long-poll subscription. Per PR \#2 \(CCR server-side auto-arm\) — IDE-agnostic relay-arrival arming. This is the RECOMMENDED entry point for SessionStart auto-arming across all MCP clients \(Claude Code, Antigravity, Cursor, Windsurf, etc.\). Equivalent
- `nucleus\_wakeup\_wait`: Quick scan for a PENDING task. Returns the task directly if one is available, or None if no task is ready within the timeout. Default timeout is 5s \(non-blocking\). The agent should NOT loop on this — tasks arrive via relay push. This is a fallback for when the agent wants to check for tasks without
- `nucleus\_orchestration`: Satellite view, commitments, loops, patterns & metrics. Actions: satellite - Unified satellite view. params: \{detail\_level?\} scan\_commitments - Scan artifacts for new commitments archive\_stale - Auto-archive commitments older than 30 days export - Export brain to zip list\_commitments - List open com
- `nucleus\_telemetry`: LLM tiers, telemetry, PEFS notifications & protocol tools. Actions: set\_llm\_tier - Set default LLM tier. params: \{tier\} get\_llm\_status - Get LLM tier configuration record\_interaction - Record user interaction timestamp value\_ratio - Get Value Ratio metric check\_kill\_switch - Check Kill Switch status
- `nucleus\_slots`: Orchestration slots, sprints & mission management. Actions: orchestrate - THE GOD COMMAND. params: \{slot\_id?, model?, alias?, mode?\} slot\_complete - Mark task complete. params: \{slot\_id, task\_id, outcome?, notes?\} slot\_exhaust - Mark slot exhausted. params: \{slot\_id, reset\_hours?\} status\_dashboard -
- `nucleus\_infra`: Infrastructure: file changes, cloud, marketing & strategy tools. Actions: file\_changes - Get pending file change events gcloud\_status - Check GCloud auth status gcloud\_services - List Cloud Run services. params: \{project?, region?\} list\_services - List Render.com services scan\_marketing\_log - Scan m
- `nucleus\_agents`: Agent spawning, critic, swarm, memory, ingestion & dashboard tools. Actions: spawn\_agent - Spawn Ephemeral Agent. params: \{intent, execute\_now?, persona?, confirm?\}. HITL: requires confirm=true. apply\_critique - Apply critique fixes. params: \{review\_path\} orchestrate\_swarm - Start multi-agent swarm.
- `nucleus\_federation`: Federation management for multi-brain coordination. Actions: status - Get comprehensive federation status join - Join a federation via seed peer. params: \{seed\_peer\} leave - Leave the federation gracefully peers - List all federation peers with details sync - Force immediate synchronization with all
- `nucleus\_engrams`: Engrams, health, observability, DSoR & tier system tools. Actions: health - Get system health status version - Get Nucleus version info export\_schema - Export MCP toolset as JSON Schema performance\_metrics - Get perf metrics. params: \{export\_to\_file?\} prometheus\_metrics - Get Prometheus metrics. par
- `nucleus\_relay`: Relay-substrate facade — post / read / ack / status. Actions: post - Send a relay envelope. params: \{to, subject, body, sender?, priority?, in\_reply\_to?, context?, id?, from\_session\_id?\} sender? auto-fills from your session role when omitted. to accepts short role aliases: main, peer, tb, ops, agy,
- `nucleus\_route`: W5 tier routing — route a prompt to the optimal model tier. Actions: route - Route a prompt to cheapest capable model. params: \{prompt, complexity?, context?, estimated\_output\_tokens?\} complexity ∈ 'routine' \| 'complex' \| 'sovereign' \(default 'routine'\) Returns: provider, model, cost estimates, sove
- `nucleus\_audit`: W8 Team-tier tamper-evident audit log \(SHA-256 hash chain\). Actions: log\_event - Append an audit event to the chain. params: \{event\_type, actor, resource, outcome, metadata?, team\_id?, ts?\} query - Single-tenant query. Rejects team\_id='\*'. params: \{team\_id, since?, until?, actor?, event\_type?, limit
- `nucleus\_delegate`: Hand a coding or review task to a cross-vendor lane — a cheap, non-Claude agent that does the work for you. Use this INSTEAD OF shelling out to any CLI: it picks the vendor, injects the correct per-vendor permission flags, captures all output synchronously, and reports a real status. Do NOT run \`agy
- `nucleus\_lane\_init`: Set up an autonomous task-execution loop in a git repo. WHEN TO USE: you have a list of tasks \(bugs, features, tests\) you want executed automatically without manual prompting — the lane runs watcher/executor/secretary daemons that claim tasks, invoke an LLM to implement them, and independently verif
- `nucleus\_lane\_start`: Start autonomous lane daemons \(watcher + executor + secretary\) in background. WHEN TO USE: after nucleus\_lane\_init and SPEC.md is written — this launches the loop that autonomously claims and executes tasks. The executor invokes an LLM CLI \(devin/agy\) per task; the secretary independently verifies e
- `nucleus\_lane\_stop`: Stop all running lane daemons. WHEN TO USE: when all tasks are CONFIRMED or you want to pause autonomous execution.
- `nucleus\_lane\_status`: Check lane status: task counts \(PENDING/IN\_PROGRESS/DONE/CONFIRMED\), daemon health, spec verification. WHEN TO USE: after starting a lane to monitor progress, or before starting to check if a lane is already running.
- `nucleus\_lane\_feedback`: Report friction/bugs/enhancements to the nucleus team. WHEN TO USE: when the lane misbehaves, a task fails unexpectedly, the SPEC.md format is confusing, or you have an improvement idea. Creates a GitHub issue on the public nucleus-mcp repo \(cross-machine visible\) AND stores locally. Requires gh CLI
- `nucleus\_plan\_execute`: Execute a plan file autonomously. WHEN TO USE: you have a plan file \(.brain/plans/\*.md\) you want executed autonomously — parses the plan, creates tasks, starts a mission with budget/time limits. Chains import\_plan\_as\_tasks\(\) then \_brain\_start\_mission\_impl\(\) and returns the mission status string.
- `nucleus\_plan\_import`: Import a plan file as PENDING tasks without starting a mission. WHEN TO USE: you have a plan file \(.brain/plans/\*.md\) you want loaded into the task store so the executor daemon / sprint mission can pick the tasks up later — but you don't want to start a mission right now.
- `nucleus\_plan\_list`: List available plan files in .brain/plans with task counts. WHEN TO USE: you want to discover which plan files exist and how many tasks each contains before importing or executing one. Returns: JSON string: a list of dicts each with \`\`\{"name", "path", "size\_bytes", "task\_count", "format"\}\`\`. Missing

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html