@getmarrow/mcp
ai.getmarrow/marrow · version 3.9.110 · 4,223 weekly npm downloads · audited 2026-11-03
Notes
Findings
No hidden-instruction or invisible-character findings in any tool, prompt, or resource description.
Claude Connectors Directory readiness
- ❌ Every tool has a title Missing on 17 of 17: marrow_think, marrow_commit, marrow_model_usage, marrow_agent_status and 13 more
- ❌ Every tool declares readOnlyHint or destructiveHint Missing on 17 of 17: marrow_think, marrow_commit, marrow_model_usage, marrow_agent_status and 13 more
- ✅ Tool names are 64 characters or fewer All within limit
- ❌ Descriptions avoid instructions about model behavior or other tools 2 of 17 descriptions reference other tools or tell the model what it must do: marrow_commit, marrow_agent_runtime
- ✅ No hidden instructions or invisible characters in tool metadata None found
Checks the directory's published tool requirements that are visible from tools/list. Passing them does not guarantee acceptance.
Supply chain
- Install scripts: none
- npm provenance: yes
- Source repository linked: yes
- License: MIT
- Direct dependencies: 1
Tools (17)
| Name | Title | Hint | Description |
|---|---|---|---|
marrow_think | none | Record intent and retrieve authorized governance intelligence before acting. Returns a decision_id for outcome closure plus relevant patterns, prior outcomes, and recommendedNext. Pass previous_outcome to auto-commit the… | |
marrow_commit | none | Close a recorded action with success/failure, a specific outcome, and required proof. decision_id comes from marrow_think, marrow_auto, or a runtime that actually created a decision. Use the gate receipt from marrow_agen… | |
marrow_model_usage | none | Record compact model token usage for value proof. Use when the harness exposes provider/model token counts. Do not send raw prompts, completions, tool logs, secrets, or customer content. | |
marrow_agent_status | none | Check whether Marrow is passively active for this agent or fleet. Returns connected state, signal quality, non-sensitive proof, and next actions. Use at session start or before owner reporting to prove Marrow is working … | |
marrow_value_report | none | Get owner-ready proof of Marrow value for this agent or fleet. Returns summary, decision metrics, saves, active agents, top risks, recommendations, and improvement data without raw decision text. | |
marrow_decision_brief | none | One pre-action call before meaningful or risky work. Returns risk level, workflow/playbook steps, handoff requirements, freshness/source-of-truth checks, minimum verification checks, proof-pack fields, and next actions. … | |
marrow_agent_runtime | none | One-call agent-native Marrow loop. Returns passive status, decision brief, risk gate, relevant lessons, template suggestion, required proof pack, before-you-act instruction, and exact next action. Its runtime_authorizati… | |
marrow_arbitrate | none | Resolve conflicting next-step proposals from two or more tenant agents before execution. Uses the existing Marrow runtime gate and returns a durable arbitration receipt with the selected, synthesized, review-required, or… | |
marrow_coordinate | none | Coordinate tenant agents without sharing transcripts. Acquire or release a bounded resource lease, list current leases, or create/list compact evidence-backed child proof packets for a parent agent. | |
marrow_replay_compare | none | Compare two already-recorded outcomes for the same tenant task using durable proof. This does not run a model or replay customer content; it returns complete or insufficient_evidence. | |
marrow_completion_contracts | none | List Marrow completion contracts for deploy, merge, publish, database migration, security change, support response, and Hermes goal workflows. | |
marrow_evaluate_completion_contract | none | Evaluate whether an agent has enough proof to mark work complete. Returns complete, missing_proof, review_required, or blocked with missing proof fields. | |
marrow_governance_timeline | none | Return the recent fleet governance timeline across decisions, risk gates, and proof-pack events. | |
marrow_decision_trace | none | Inspect the tenant-scoped path behind one governed decision and return its owner-readable intervention receipt with gate, required workflow, permit follow-through, proof, and observed outcome. | |
marrow_buyer_proof | none | Return buyer-grade value proof: failures avoided, risky actions reviewed, proofs completed, measured provider-reported token usage when available, failure classes, agent leaderboard, and reliability score. | |
marrow_workflow_gate | none | Pre-action risk gate for deploys, publishes, merges, DB migrations, key rotation, destructive commands, and production work. Returns allow, warn, review_required, or block plus prior lessons/playbooks. | |
marrow_fleet_lessons | none | Retrieve ranked reusable fleet lessons before similar work. Use before deploys, handoffs, migrations, audits, and repeated task types. |
Check your own setup
npx mcpvetter scan --liveBadge
Add this to a README:
[](https://mcpvetter.com/servers/getmarrow-mcp)Publish this server?
Get the MCPVetter verified badge, a re-audit within 24 hours of every npm release, and an email whenever tools, findings, or Claude directory readiness change. $29 per server per month. You prove ownership first, free.