Nucleus

eidetic-works/nucleus-mcp

This is a file-based memory and governance layer that sits between your AI tools and your codebase. It exposes 114 MCP tools across memory (engrams that persist cross-session), execution verification (5-tier GROUND checks from syntax to runtime), human-in-the-loop corrections (ALIGN), and compliance configs for EU DORA, Singapore MAS TRM, and SOC2. The core workflow is machine verifies, human corrects, system learns. Each correction automatically generates a training pair and audit event. No embeddings, no vendor lock-in, just JSON and markdown in a `.brain` folder. Use it when you're tired of re-explaining the same context every session or when you need audit trails for regulated environments.

GitHub stars: 5
tools: 28
transport: STDIO, HTTP
env var: 1
last updated: Nov 2, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://relay.nucleusos.dev/mcp --name nucleus

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http nucleus https://relay.nucleusos.dev/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 28 tools

Verified live against the running server on Nov 6, 2026.

nucleus_governanceGovernance, 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 -...2 params

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 -...

Parameters* required

action*string

paramsobject

nucleus_featuresFeature 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:...2 params

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:...

Parameters* required

action*string

paramsobject

nucleus_sessionsSession 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 - Che...2 params

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 - Che...

Parameters* required

action*string

paramsobject

nucleus_tasksTask 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:...2 params

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:...

Parameters* required

action*string

paramsobject

nucleus_syncSync, 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 -...2 params

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 -...

Parameters* required

action*string

paramsobject

nucleus_next_messageGet 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...1 params

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...

Parameters* required

recipientstring

default:

nucleus_relay_subscribeLong-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...3 params

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...

Parameters* required

inbox_filterstring

explicit inbox dir NAME (e.g., "cc_tb", "claude_code_main"). When provided, BYPASSES role detection entirely. Recommended for SessionStart hook deterministic arming. Resolve...default:

rolestring

override calling agent's role (default: env-detected from CC_SESSION_ROLE or detect_session_role())default:

timeout_secondsinteger

max subscription duration (60..1800, default 270 = under FastMCP context-cache TTL so re-subscribe doesn't burn cache)default: 270

nucleus_ccr_armOne-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, Wind...2 params

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, Wind...

Parameters* required

rolestring

explicit role override (e.g., "antigravity", "cc_tb"). If omitted, server detects via env vars / registry ancestry / provider heuristics (per detect_session_role).default:

timeout_secondsinteger

max subscription duration (60..1800, default 270 under FastMCP context-cache TTL).default: 270

nucleus_wakeup_waitQuick 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 c...5 params

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 c...

Parameters* required

agent_idstring

identifier for claiming (auto-detected if empty).default:

auto_claimboolean

if True, atomically claim the task before returning.default: true

required_rolestring

role scope filter. Auto-detected from posture if empty.default:

skillsstring

comma-separated skill filter (optional).default:

timeout_secondsinteger

max wait (default 5s, 0 = instant burst, max 1800).default: 5

nucleus_orchestrationSatellite 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_comm...2 params

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_comm...

Parameters* required

action*string

paramsobject

nucleus_telemetryLLM 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 - C...2 params

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 - C...

Parameters* required

action*string

paramsobject

nucleus_slotsOrchestration 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_hou...2 params

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_hou...

Parameters* required

action*string

paramsobject

nucleus_infraInfrastructure: 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...2 params

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...

Parameters* required

action*string

paramsobject

nucleus_agentsAgent 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 - S...2 params

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 - S...

Parameters* required

action*string

paramsobject

nucleus_federationFederation 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 s...2 params

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 s...

Parameters* required

action*string

paramsobject

nucleus_engramsEngrams, 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...2 params

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...

Parameters* required

action*string

paramsobject

nucleus_relayRelay-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: mai...2 params

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: mai...

Parameters* required

action*string

paramsobject

nucleus_routeW5 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, mode...2 params

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, mode...

Parameters* required

action*string

paramsobject

nucleus_auditW8 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?, act...2 params

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?, act...

Parameters* required

action*string

paramsobject

nucleus_delegateHand 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...2 params

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...

Parameters* required

action*string

paramsobject

nucleus_lane_initSet 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,...6 params

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,...

Parameters* required

forceboolean

Skip isolation guards (for testing only).default: false

repo_pathstring

Path to the git repo (default: current directory).default:

rolestring

Lane role name (default: lane-g1).default: lane-g1

spec_pathstring

Path to the spec file (default: SPEC.md).default: SPEC.md

tagstring

Git tag for spec pinning (default: <role>-v1).default:

vendorstring

Default vendor — devin (GLM) or agy (Gemini).default: devin

nucleus_lane_startStart 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 i...4 params

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 i...

Parameters* required

executorsvalue

List of executor lane names (default: ["lane_devin"]).

no_secretaryboolean

Skip secretary daemon (NOT recommended — disables verification).default: false

no_watcherboolean

Skip control watcher.default: false

repo_pathstring

Path to the git repo (default: current directory).default:

nucleus_lane_stopStop all running lane daemons. WHEN TO USE: when all tasks are CONFIRMED or you want to pause autonomous execution.1 params

Stop all running lane daemons. WHEN TO USE: when all tasks are CONFIRMED or you want to pause autonomous execution.

Parameters* required

repo_pathstring

Path to the git repo (default: current directory).default:

nucleus_lane_statusCheck 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.1 params

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.

Parameters* required

repo_pathstring

Path to the git repo (default: current directory).default:

nucleus_lane_feedbackReport 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 l...5 params

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 l...

Parameters* required

body*string

Detailed description.

feedback_type*string

"bug", "enhancement", "observation", or "question".

repo_pathstring

Path to the repo where the feedback was observed.default:

reporterstring

Your name/project (default: anonymous).default:

subject*string

Short summary.

nucleus_plan_executeExecute 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 mis...4 params

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 mis...

Parameters* required

budget_limitnumber

Mission spend cap in USD (default $10.00).default: 10

goalstring

Optional mission goal text. Defaults to empty.default:

plan_path*string

Path to the plan markdown file (.brain/plans/*.md).

time_limit_hoursnumber

Mission time cap in hours (default 4.0).default: 4

nucleus_plan_importImport 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.1 params

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.

Parameters* required

plan_path*string

Path to the plan markdown file.

nucleus_plan_listList 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...

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...

No parameters. Call it with no arguments.

Configuration

NUCLEUS_BRAIN_PATH

Path to .brain/ directory (defaults to .brain in current directory)

Readme

`.brain` — the portable decision log

The portable decision log your AI tools all read. One MCP server. Any AI tool. Plain files.

Every AI coding session starts by re-explaining context the last session already knew. .brain is a folder in your repo that Claude Code, Cursor, and Codex all read via one MCP server. Decisions, policies, plans — written once, remembered across every session and every tool.

MIT licensed. File-based (plain JSON + markdown). No embeddings. No vendor lock-in.

Also included: nucleus-rabbithole

View the full README on GitHub

Details

Repository: github.com/eidetic-works/nucleus-mcp
Website: nucleusos.dev
Category: AI & LLM Tools
Package: nucleus-mcp
Transport: STDIO, HTTP
Registry: MCP registry, active
Resources: 19
Prompts: 8
Tools verified: Nov 6, 2026

Related AI & LLM Tools MCP servers

View all

Ragalgokokogo100/ragalgo-mcp-serverDynamic RAG Engine preventing AI hallucinations in Korean Finance and Crypto markets.5stars

Clarifypromptlumabyteco/clarifyprompt-mcpAI prompt optimization for 58+ platforms across 7 categories with custom platforms5stars

Image Recognition Mcpmcp-s-ai/image-recognition-mcpMCP server for AI-powered image recognition and description using OpenAI vision models.5stars

Image Recongnition Mcpmcp-s-ai/image-recongnition-mcpMCP server for AI-powered image recognition and description using OpenAI vision models.5stars

Skill Historypineapple-farm/skill-historyTrack download history for 70,000+ agent skills. Search and get daily snapshots.5stars

Moltbridgesagemindai/moltbridgeAgent network intelligence for AI agents. Trust scoring, broker discovery, and Ed25519 identity.5stars

Nucleus

Install

Tools

Configuration

Readme

.brain — the portable decision log

Also included: nucleus-rabbithole

Details

Related AI & LLM Tools MCP servers

`.brain` — the portable decision log