Dunstan
NPM · DUNSTAN
Checks a coding agent's handback against the pull request's GitHub record. No model decides.
Available components
Last scanned (3 hours ago)
Scores higher than 65% of npm servers
Category Version Control
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to BargLabs/dunstan). View diagnostics → Pass
- Clear OSI-approved license (AGPL-3.0-only).Pass
- Actively maintained (last published 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability60
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 577 tokens (~288/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management10
- Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Oct 26 +11
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → pass ▲ functional
- 15 Oct 26 +30
- Injection markers: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Stability: unverified → 0.03 ▲ functional
- Dependency health: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- Package version: 0.1.10 → 0.1.12 functional
- Package version: 0.1.10 → 0.1.11 functional
- 14 Oct 26 −11
- Known CVEs: pass → unverified ▼ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Dependency health: pass → unverified ▼ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- Package version: 0.1.8 → 0.1.10 functional
- Package version: 0.1.8 → 0.1.9 functional
- 13 Oct 26 0
- Security disclosure: unverified → fail ▼ functional
- Package version: 0.1.6 → 0.1.8 functional
- Package version: 0.1.6 → 0.1.7 functional
- 12 Oct 26 49
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 17 Oct 2026 · Analysed npm/dunstan@0.1.12
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | BargLabs/dunstan |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/BargLabs/dunstan/.github/workflows/release.yml@refs/tags/v0.1.12 |
| Rekor log index | 3264259039 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:58621b9b7e8f46235ef46ad8acc245e0e274495959f28b912d7e929aa812005c687a583c52b980489e2f78539977c7eaa6d2797b3ae4a04f762402eff |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
dunstan_check_handback Check a handback against the record ~332
Check a completion handback against the repository's own record, before you say done. Give the subject (repository owner/name and pull request number) and exactly one of: block, the dunstan-handback block as a JSON object; or report, the report text that carries exactly one ```dunstan-handback fence. Of the checks claims, checks.allSucceeded is true only if every counted check run concluded success, so a skipped or neutral run makes it false; checks.noneFailed is true if none concluded other than success, skipped or neutral and at least one succeeded. Returns the verdict (pass, fail or unverifiable), the claims table, and the full record as JSON. Same checker and same verdict as `dunstan check` on the same evidence; no model decides. Reads GitHub metadata with GITHUB_TOKEN and writes nothing to GitHub or the repository; the record is written to a file only when you pass outPath. If the verdict is not pass, report the rows as they are; change the work, not the block.
| Name | Type | Req | Description |
|---|---|---|---|
| block | object | – | The dunstan-handback block as a JSON object. Give this or report, not both. |
| outPath | string | – | Write the record to this path (must not exist). Without it nothing is written. |
| pullRequest | integer | yes | The pull request number the handback is about. |
| report | string | – | The report text, carrying exactly one ```dunstan-handback fence. Give this or block, not both. |
| repository | string | yes | The GitHub repository, owner/name. |
No output schema declared.
No examples provided.
dunstan_suggest_declarations Suggest declarations from the prose ~131
List the sentences in your report's prose that look like claims your dunstan-handback block does not declare, before you say done. Give report, the report text. For each, declare it in the block, or reword it if it is not a claim about this PR. Offline: needs no pull request, reads nothing and writes nothing. Never a verdict: nothing passes or fails, and nothing is written to a record. The same text as `dunstan suggest`.
| Name | Type | Req | Description |
|---|---|---|---|
| report | string | yes | The report text: the prose and its ```dunstan-handback fence. |
No output schema declared.
No examples provided.
How do I install the Dunstan MCP server?
Dunstan runs locally as an npm package, launched with npx -y dunstan. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · dunstan
claude mcp add barglabs-dunstan -- npx -y dunstan
What is the Dunstan MCP server?
Dunstan is an MCP server listed in the public MCP registry as io.github.BargLabs/dunstan. Checks a coding agent's handback against the pull request's GitHub record. No model decides. This page covers its npm package (dunstan).
Is the Dunstan MCP server safe to use?
Dunstan scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Dunstan MCP server expose?
Dunstan exposes 2 tools: dunstan_check_handback, dunstan_suggest_declarations. Their descriptions and schemas cost roughly 463 tokens of context every time the server is loaded.
Is the Dunstan MCP server still maintained?
Dunstan is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Dunstan MCP server under?
Dunstan declares the AGPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.