Rebuild Dossier
NPM · REBUILD-DOSSIER
MCP server that reverse-engineers a locked rebuild spec from an existing app.
Available components
Last scanned (20 hours ago)
Scores higher than 97% of npm servers
Category Developer Tools
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 Security93
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known medium-severity CVE affects @hono/node-server 1.19.18, reached via @modelcontextprotocol/node > @hono/node-server. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 34 of 118 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Parker-Fawcett/rebuild-dossier). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 40 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability77
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 742 tokens (~123/item across 6 items; 6 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
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
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (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.
- 2 Nov 26 +1
- Stability: 0.97 → pass security
- 1 Nov 26 −1
- Stability: pass → 0.97 functional
- 31 Oct 26 0
- CVE-2026-118764 affects this package: medium ▼ security
- 29 Oct 26 −1
- CVE-2026-118663 affects this package: medium ▼ security
- Known CVEs: pass → fail ▼ security
- 26 Oct 26 0
- Stability: 0.97 → pass security
- 25 Oct 26 0
- Stability: pass → 0.97 functional
- 19 Oct 26 0
- Stability: 0.97 → pass security
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
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 4 Nov 2026 · Analysed npm/rebuild-dossier@0.2.6
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 | Parker-Fawcett/rebuild-dossier |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Parker-Fawcett/rebuild-dossier/.github/workflows/publish.yml@refs/tags/v0.2.6 |
| Rekor log index | 2706500965 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:a80becd3750063ecb109a6d453ce58bd72a458171f5dd6e19aaeaf7549e13204988dbc790802646367114938e0be4af8d5740b2dbf53ceb35892e89f7 |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 2 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-rmxm-3fg6-px4f | CVE-2026-118663 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N | yes |
| GHSA-g3hv-75wg-m249 | CVE-2026-118764 | medium | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 118 packages
| Packages resolved | 118 |
|---|---|
| Stale | 34 |
| 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 →
crawl_site Crawl site ~78
Playwright headless crawl of reachable routes. Emits periodic progress notifications.
| Name | Type | Req | Description |
|---|---|---|---|
| maxPages | integer | – | Optional cap on how many reachable pages to visit. Unset means no limit. |
| repoPath | string | yes | Repo path whose .dossier/ this crawl evidence should be saved under |
| url | string | yes | Base URL to crawl |
| Name | Type | Req | Description |
|---|---|---|---|
| openCases | integer | yes | – |
| routesVisited | integer | yes | – |
| routesWithConsoleErrors | integer | yes | – |
| savedTo | string | yes | – |
No examples provided.
flag_known_bug Flag known bug ~68
Record a known bug. Always overrides auto-resolve for any case it matches, regardless of other evidence.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | yes | Free-text description of a known bug, stored verbatim |
| repoPath | string | yes | Repo path whose .dossier/ this known bug belongs to |
| Name | Type | Req | Description |
|---|---|---|---|
| bug | object | yes | – |
| openCases | integer | yes | – |
No examples provided.
generate_spec Generate spec ~337
Write CLAUDE.md, .claude/, spec/, tests/, and kickoff-prompt.txt to <repo>-rebuild/. Only callable once the case queue is empty. Optional: if the target is a Next.js app with page routes, set GROQ_API_KEY and REBUILD_DOSSIER_ENABLE_VISION_CLASSIFICATION=1 before calling this tool to enable vision-assisted page-content classification (sends each captured page's screenshot and source code to Groq to judge static vs. dynamic content more accurately than plain regex matching) — ask the user for a Groq API key if they want more reliable generated page tests and this isn't already configured. Off by default; nothing changes if unset. Optional: pass authStorageStatePath to reach auth-gated pages during capture — see that field's own description for how to produce it.
| Name | Type | Req | Description |
|---|---|---|---|
| authStorageStatePath | string | – | Optional path to a Playwright storageState JSON file (cookies/localStorage from an already-authenticated session against the target app) — load it once with `npx playwright open <url> --save-storage=… |
| repoPath | string | yes | Repo path that was ingested; output is written to a sibling <repoPath>-rebuild/ directory |
| Name | Type | Req | Description |
|---|---|---|---|
| capturedPages | integer | yes | – |
| mutationsChecked | integer | yes | – |
| outputDir | string | yes | – |
| pageCaptureNote | string | – | – |
| pageVisionFallbackNote | string | – | – |
| pageVisionFallbacks | array | – | – |
| skippedPages | array | yes | – |
| unrunnableTests | array | yes | – |
| visionClassificationEnabled | boolean | yes | – |
| visionClassificationNote | string | – | – |
| warning | string | – | – |
| weakTests | array | yes | – |
No examples provided.
get_case_queue Get case queue ~57
Return unresolved ambiguity cases from reconciliation.
| Name | Type | Req | Description |
|---|---|---|---|
| interactive | boolean | – | When true, walk open cases via MCP elicitation instead of just listing them |
| repoPath | string | yes | Repo path whose .dossier/ case queue to read |
| Name | Type | Req | Description |
|---|---|---|---|
| cases | array | yes | – |
| open | integer | yes | – |
No examples provided.
ingest_repo Ingest repo ~86
Parse package.json, tailwind/vite config, route files, and existing tests via static analysis. No LLM call.
| Name | Type | Req | Description |
|---|---|---|---|
| interactive | boolean | – | When true and 0 routes are found at a monorepo-shaped path, ask via elicitation which candidate directory is the real app, then ingest that instead |
| path | string | yes | Absolute path to the repo to ingest |
| Name | Type | Req | Description |
|---|---|---|---|
| buildConfig | array | yes | – |
| existingTests | integer | yes | – |
| monorepoHint | object | – | – |
| openCases | integer | yes | – |
| resolvedMonorepoChoice | string | – | – |
| routes | integer | yes | – |
| savedTo | string | yes | – |
| signals | integer | yes | – |
No examples provided.
resolve_case Resolve case ~116
Resolve one open case with a human decision. Always available, no elicitation capability required.
| Name | Type | Req | Description |
|---|---|---|---|
| decision | string | yes | Free-text decision, e.g. "intentional" or "bug" — stored verbatim, not a fixed enum |
| id | string | yes | The case id to resolve, as returned by get_case_queue (e.g. "case:...") |
| note | string | – | Optional free-text note explaining the decision |
| repoPath | string | yes | Repo path whose .dossier/ this case belongs to |
| Name | Type | Req | Description |
|---|---|---|---|
| autoResolution | object | – | – |
| conflict | object | – | – |
| humanDecision | object | – | – |
| id | string | yes | – |
| matchedKnownBugs | array | yes | – |
| relatedCaseIds | array | – | – |
| signals | array | yes | – |
| status | string | yes | – |
| topicKey | string | yes | – |
No examples provided.
How do I install the Rebuild Dossier MCP server?
Rebuild Dossier runs locally as an npm package, launched with npx -y rebuild-dossier. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · rebuild-dossier
claude mcp add com-parkerfawcett-rebuild-dossier -- npx -y rebuild-dossier
What is the Rebuild Dossier MCP server?
Rebuild Dossier is an MCP server listed in the public MCP registry as com.parkerfawcett/rebuild-dossier. MCP server that reverse-engineers a locked rebuild spec from an existing app. This page covers its npm package (rebuild-dossier).
Is the Rebuild Dossier MCP server safe to use?
Rebuild Dossier scores 94 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 4 November 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 Rebuild Dossier MCP server expose?
Rebuild Dossier exposes 6 tools: ingest_repo, crawl_site, flag_known_bug, get_case_queue, resolve_case, generate_spec. Their descriptions and schemas cost roughly 742 tokens of context every time the server is loaded.
Is the Rebuild Dossier MCP server still maintained?
Rebuild Dossier is still listed as active in the MCP registry. We last reached this channel on 4 November 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 Rebuild Dossier MCP server under?
Rebuild Dossier declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.