@getmarrow/mcp

MCP-native runtime control, proof, and fleet intelligence for AI agents.

Marrow is the runtime control and proof layer for teams running AI agents. It applies policy and prior lessons before consequential actions, then records the evidence and outcome afterward.

Use @getmarrow/mcp when your agent client supports the Model Context Protocol and you want Marrow available inside the agent's normal workflow. It works with Claude Code, Claude Desktop, Cursor and other MCP-compatible clients without replacing the model or harness.

Install

npx @getmarrow/mcp setup

Set the key through trusted secret storage:

export MARROW_API_KEY=mrw_live_...

Then configure the MCP server:

{
  "mcpServers": {
    "marrow": {
      "command": "npx",
      "args": ["-y", "@getmarrow/mcp"]
    }
  }
}

For most new installations, start with the universal installer instead:

npx @getmarrow/install --yes

What's New in v3.9.43

v3.9.43 aligns the package entry point with Marrow's business product contract:

• runtime control before consequential actions;
• proof and outcome closure afterward;
• tenant-scoped fleet improvement across interchangeable agents and harnesses;
• context, lessons, and workflow examples presented as supporting controls rather than a separate memory product.

This patch changes package documentation and positioning. Existing MCP tool behavior and names remain compatible.

Governed Action Flow

Before deploys, merges, publishes, migrations, credential changes, financial operations, or customer-impacting work:

1. Call marrow_agent_runtime or marrow_decision_brief.
2. Stop when the returned decision is block or review_required; otherwise follow its prior lesson and proof contract.
3. Call marrow_think to record intent and obtain the decision_id that will be closed.
4. Perform the action only when its gate allows it.
5. Call marrow_commit with that decision_id, the outcome, gate receipt, and required proof.

Example pre-action request:

{
  "tool": "marrow_agent_runtime",
  "arguments": {
    "action": "deploy the production worker",
    "type": "deploy",
    "role": "deploy",
    "surfaces": ["repository", "deployment", "production"]
  }
}

Example closeout:

{
  "tool": "marrow_think",
  "arguments": {
    "action": "deploy the production worker",
    "type": "process",
    "checkLoop": true
  }
}

{
  "tool": "marrow_commit",
  "arguments": {
    "decision_id": "decision_id returned by marrow_think",
    "gate_receipt_id": "receipt id returned by marrow_agent_runtime",
    "success": true,
    "outcome": "Production deploy succeeded and smoke checks passed.",
    "proof": {
      "checks": ["tests passed", "secret scan passed", "production smoke passed"],
      "rollback_target": "previous release"
    }
  }
}

High-risk work can be allowed, warned, held for review, or blocked according to account policy. Low-risk work can use passive guidance and bounded cached state where the runtime contract permits it.

Passive Use

npx @getmarrow/mcp setup installs supported hooks so the agent can receive before-action context and record meaningful tool outcomes without the owner repeatedly prompting it to use Marrow.

Check the installed runtime:

marrow_agent_status

Status diagnostics distinguish missing keys, invalid keys, wrong bound-agent identity, network limits, missing hooks, and incomplete proof. They include an exact repair action without exposing secrets.

Primary MCP Tools

Tool	Purpose
marrow_agent_runtime	One-call pre-action status, policy gate, relevant lessons, proof requirements, and exact next action
marrow_decision_brief	Compact operating brief for meaningful work
marrow_think	Record intent and retrieve relevant governance intelligence
marrow_commit	Close an action with outcome, receipt, and proof
marrow_workflow_gate	Evaluate a workflow action against policy
marrow_completion_contracts	List proof contracts for consequential action types
marrow_evaluate_completion_contract	Check whether evidence is sufficient to call work complete
marrow_agent_status	Verify capture, identity, outcome coverage, and hook health
marrow_value_report	Return account/agent value evidence without requiring a dashboard
marrow_buyer_proof	Return owner-ready governance and reliability evidence
marrow_governance_timeline	Inspect decisions, gates, proof packs, and outcomes over time
marrow_fleet_lessons	Retrieve proven lessons authorized for the current account or agent
marrow_model_usage	Record compact token, cost, and latency counts when the harness exposes them

The package also exposes key management, fleet handoff, deployment history, adaptive policy, context/lesson, query, and workflow-example tools. See the complete source-of-truth documentation for every tool and field.

Context and Workflow Examples

The stable marrow_*memory* tools manage authorized context and prior lessons used by governance decisions. They are advanced supporting APIs, not a separate product category.

The template tools expose 24 configurable workflow examples. They are starting points for policy design, not customer case studies, regulatory validation, legal advice, or proof of production use in each listed industry.

Trust and Data Boundaries

• Private account, fleet, workflow, proof, and agent data remains tenant-scoped by default.
• Agent-bound keys can be restricted to an allowed identity and permission set.
• Sanitized aggregate contribution is optional and never means sharing raw prompts, code, secrets, proof packs, account identifiers, agent identifiers, or customer identities.
• Existing API keys are never returned after creation; key material should be supplied through the client's secret store.
• Marrow returns guidance and policy data. Agents must not execute returned text as shell input.

See the Trust Center for implemented controls, current limits, and roadmap status.

Environment

Variable	Required	Purpose
MARROW_API_KEY	Yes	Account or agent-bound API key
MARROW_BASE_URL	No	API base override
MARROW_AGENT_ID	No	Bound agent identity for MCP tools
MARROW_FLEET_AGENT_ID	No	Fleet agent identity used by passive setup

Documentation

• Source-of-truth docs
• Trust Center
• Status
• GitHub

License

MIT

Related Packages

• @getmarrow/install - default installer, self-test, governed runner, and operator TUI
• @getmarrow/sdk - Node.js and TypeScript integration for owned agent runtimes