Skip to content

Keesan12/Martin-Loop

vmcp-v0.2.0 scope: mcp Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 14d AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-runtime ai-agent-runtime ai-coding-agents ai-control-plane ai-governance ai-safety
+13 more
audit-trail budget-enforcement claude-code codex coding-agents control-plane governed-runtime llmops mcp model-context-protocol observability policy-as-code rollback

ReleasePort's take

Light signal
editorial:auto 14d

Martin-Loop v0.2.0 adds run management APIs and prompts: list runs, fetch dossiers with attempts and verification results, and guided failure triage.

Why it matters: Operators gain structured access to loop execution history and failure investigation. Adopt the dossier and triage APIs in dev for better auditability and SRE workflows.

Summary

AI summary

Updates Upgrade Notes, Tools Existing tools, and Resource Templates across a mixed release.

Changes in this release

Feature Medium

`martin_list_runs` lists recent governed run summaries.

`martin_list_runs` lists recent governed run summaries.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin_get_run` returns a run dossier by `loopId` or `latest`.

`martin_get_run` returns a run dossier by `loopId` or `latest`.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin_get_attempt` returns one attempt record by `loopId` and `attemptIndex`.

`martin_get_attempt` returns one attempt record by `loopId` and `attemptIndex`.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin_get_verification_results` extracts verifier completion events.

`martin_get_verification_results` extracts verifier completion events.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin_run_dossier` assembles summary, task, budget, attempts, and verification evidence for review.

`martin_run_dossier` assembles summary, task, budget, attempts, and verification evidence for review.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin://runs/summary` resource provides run summaries.

`martin://runs/summary` resource provides run summaries.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin://runs/latest` resource accesses the latest run.

`martin://runs/latest` resource accesses the latest run.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin://runs/{loopId}` template retrieves a specific run.

`martin://runs/{loopId}` template retrieves a specific run.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin://runs/{loopId}/attempts/{attemptIndex}` template accesses an attempt record.

`martin://runs/{loopId}/attempts/{attemptIndex}` template accesses an attempt record.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin://runs/{loopId}/verification` template fetches verification results.

`martin://runs/{loopId}/verification` template fetches verification results.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin_review_run` prompt guides run review.

`martin_review_run` prompt guides run review.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Feature Medium

`martin_triage_failures` prompt assists in failure triage.

`martin_triage_failures` prompt assists in failure triage.

Source: granite4.1:8b-q6_K@2026-05-20

Confidence: high

 —
Full changelog

@martinloop/mcp v0.2.0

0.2.0 turns the Martin Loop MCP server from a governed execution lane into a small local cockpit for reviewing governed agent runs.

0.1.4 introduced the safe operator foundation: check the environment, preflight a contract, run a governed coding task, and inspect saved results. 0.2.0 keeps that contract intact and adds read-only review surfaces so MCP hosts can show what happened after a run: recent runs, one-run dossiers, individual attempts, verifier results, and guided review prompts.

The important safety boundary is unchanged: martin_run is still the only tool that can execute work. The new 0.2.0 additions are read-only inspection and review helpers.

What Changed From 0.1.4

| Area | 0.1.4 | 0.2.0 |
| --- | --- | --- |
| Environment checks | martin_doctor | unchanged |
| Run preflight | martin_preflight | unchanged |
| Governed execution | martin_run | unchanged write boundary |
| Basic run inspection | martin_inspect, martin_status | unchanged |
| Review cockpit | not included | run lists, dossiers, attempts, verifier results |
| MCP discovery | tools | tools, resources, resource templates, prompts |

Tools

Existing tools:

  • martin_doctor
  • martin_preflight
  • martin_run
  • martin_inspect
  • martin_status

New read-only cockpit tools:

  • martin_list_runs lists recent governed run summaries from the local run store.
  • martin_get_run returns a run dossier by loopId or latest.
  • martin_get_attempt returns one attempt record by loopId and attemptIndex.
  • martin_get_verification_results extracts verifier completion events.
  • martin_run_dossier assembles summary, task, budget, attempts, and verification evidence for review.

Resources

  • martin://runs/summary
  • martin://runs/latest

Resource Templates

  • martin://runs/{loopId}
  • martin://runs/{loopId}/attempts/{attemptIndex}
  • martin://runs/{loopId}/verification

Prompts

  • martin_review_run
  • martin_triage_failures

Upgrade Notes

  • Existing 0.1.4 tool callers do not need to change their current calls.
  • Hosts can opt into the new cockpit surface by listing tools, resources, resource templates, and prompts through normal MCP discovery.
  • The npm package remains @martinloop/mcp.
  • The MCP server name remains io.github.Keesan12/martin-loop.

Verification

The published package was verified from npm after release. The published smoke test confirmed:

  • package version @martinloop/[email protected]
  • all 10 tools are discoverable
  • both resources are discoverable
  • all 3 resource templates are discoverable
  • both prompts are discoverable
  • local run inspection, status, run listing, dossier generation, and governed stub execution work from the installed npm artifact
View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Keesan12/Martin-Loop

Get notified when new releases ship.

Sign up free

About Keesan12/Martin-Loop

All releases →

Related context

Earlier breaking changes

  • vmcp-v0.1.3 martin_status uses oneOf for selector exclusivity, latest as const.
  • vmcp-v0.1.3 maxIterations and maxTokens modeled as integers in tool schemas.
  • vmcp-v0.1.3 Tool schemas enforce additionalProperties: false on public contracts.
  • vmcp-v0.1.3 Packaged artifacts now require and ship server.json alongside package.json.

Beta — feedback welcome: [email protected]