This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+13 more
Summary
AI summaryUpdates Hardening and polish, Release Verification Gates, and Execution visibility across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Added martin_list_runs command. Added martin_list_runs command. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Feature | Medium |
Added martin_get_run command. Added martin_get_run command. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Feature | Medium |
Added martin_get_attempt command. Added martin_get_attempt command. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Feature | Medium |
Added martin_get_verification_results command. Added martin_get_verification_results command. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Feature | Medium |
Added martin_run_dossier command. Added martin_run_dossier command. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Feature | Medium |
Upgraded martin_run to return richer inspection, verification, and artifact rollups. Upgraded martin_run to return richer inspection, verification, and artifact rollups. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Feature | Medium |
Added static resources for server health, recent runs, MCP usage, and publish readiness. Added static resources for server health, recent runs, MCP usage, and publish readiness. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Feature | Medium |
Added resource templates for runs, attempts, and verification. Added resource templates for runs, attempts, and verification. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Feature | Medium |
Added prompts for governed kickoff, failed-run debugging, and publish‑readiness review. Added prompts for governed kickoff, failed-run debugging, and publish‑readiness review. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Feature | Low |
Added martin://runs/triage resource URI. Added martin://runs/triage resource URI. Source: granite4.1:30b@2026-05-26-audit Confidence: low |
— |
| Feature | Low |
Added martin_triage_run_store tool for store inspection and recovery. Added martin_triage_run_store tool for store inspection and recovery. Source: granite4.1:30b@2026-05-26-audit Confidence: low |
— |
| Performance | Medium |
Cached repeated doctor and run‑store inspection work per process. Cached repeated doctor and run‑store inspection work per process. Source: llm_adapter@2026-05-26 Confidence: high |
— |
| Bugfix | Medium |
Run‑store scans now skip unreadable loop records and continue with warnings instead of failing entirely. Run‑store scans now skip unreadable loop records and continue with warnings instead of failing entirely. Source: granite4.1:30b@2026-05-26-audit Confidence: low |
— |
| Refactor | Low |
Tightened error taxonomy and selector validation logic. Tightened error taxonomy and selector validation logic. Source: granite4.1:30b@2026-05-26-audit Confidence: low |
— |
Full changelog
@martinloop/mcp v0.2.5
@martinloop/[email protected] is the stable cockpit line for the public MartinLoop MCP package. It follows the 0.1.4 operator foundation and 0.2.0 cockpit expansion releases, then extends that surface with run triage, degraded-store hardening, and release-proof polish while keeping martin_run as the single execution entrypoint.
What Shipped
Execution visibility
- added
martin_list_runs - added
martin_get_run - added
martin_get_attempt - added
martin_get_verification_results - added
martin_run_dossier - upgraded
martin_runto return richer inspection, verification, and artifact rollups
Context and discovery
- added static resources for server health, recent runs, MCP usage, and publish readiness
- added resource templates for runs, attempts, and verification
- added prompts for governed kickoff, failed-run debugging, and publish-readiness review
Hardening and polish
- cached repeated doctor and run-store inspection work per process
- tightened error taxonomy and selector validation
- added
martin_triage_runs - added
martin://runs/triage - added
martin_triage_run_store - run-store scans now skip unreadable loop records and continue with warnings instead of taking down the whole inspection lane
- kept
martin_run,martin_inspect,martin_status,martin_doctor, andmartin_preflightbackward-compatible - aligned docs, manifests, and release checks to the full shipped surface
Release Verification Gates
pnpm --filter @martinloop/mcp lintpnpm --filter @martinloop/mcp testpnpm --filter @martinloop/mcp buildpnpm --filter @martinloop/mcp smoke:packpnpm --filter @martinloop/mcp smoke:published:packpnpm --filter @martinloop/mcp verify:releasepnpm --filter @martinloop/mcp smoke:published
Compatibility Statement
- existing five-tool callers remain supported
- all newly added MCP surfaces are read-only except
martin_run - verification evidence is derived only from persisted Martin run data
- no new write-capable MCP tools are introduced in
0.2.5 0.1.4,0.2.0, and0.2.5are the public MCP deliveries in the current release lineage
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
About Keesan12/Martin-Loop
All releases →Related context
Related tools
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]