io.github.Evanciel/stellavault
NPM · STELLAVAULT
Local-first MCP server: Claude searches, asks & drafts from your Obsidian vault. 21 tools, no keys.
Available components
Last scanned (2 hours ago)
Scores higher than 58% of npm servers
Category Memory and Knowledge
Recent critical change
CVE-2026-41242 affects this package (3 Aug 2026). See the changelog before you install this server.
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 Security88
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known medium-severity CVE affects @anthropic-ai/sdk 0.82.0, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 125 of 359 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 72 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability80
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1126 tokens (~70/item across 16 items; 16 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
- Stability observed for 21 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 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 16 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.
- 5 Nov 26 +78
- CVE-2026-44288 affects this package: medium ▼ security
- CVE-2026-44290 affects this package: medium ▼ security
- CVE-2026-114113 affects this package: medium ▼ security
- CVE-2026-44291 affects this package: medium ▼ security
- CVE-2026-44292 affects this package: medium ▼ security
- CVE-2026-54269 affects this package: medium ▼ security
- CVE-2026-48712 affects this package: medium ▼ security
- CVE-2026-114111 affects this package: medium ▼ security
- CVE-2026-16633 affects this package: medium ▼ security
- CVE-2026-114112 affects this package: medium ▼ security
- CVE-2026-44289 affects this package: medium ▼ security
- CVE-2026-45740 affects this package: medium ▼ security
- CVE-2026-44294 affects this package: medium ▼ security
- CVE-2026-44293 affects this package: medium ▼ security
- CVE-2026-41686 affects this package: medium ▼ security
- CVE-2026-41242 no longer affects this package ▲ security
- Known CVEs: CVE check failed: a known medium-severity CVE affects @anthropic-ai/sdk 0.82.0, a direct dependency. A fixed version is available. security
- Score status: failed → scored ▲ functional
- 3 Nov 26 0
- Stability: pass → 0.63 functional
- 28 Oct 26 0
- Stability: 0.97 → pass security
- 27 Oct 26 0
- Stability: pass → 0.97 functional
- 21 Oct 26 0
- Stability: 0.97 → pass security
- 20 Oct 26 0
- Stability: pass → 0.97 functional
- 17 Oct 26 0
- Stability: 0.83 → pass security
- 15 Oct 26 0
- Injection markers: unverified → pass ▲ security
- Stability: unverified → 0.80 ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
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 5 Nov 2026 · Analysed npm/stellavault@0.9.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 17 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-p7fg-763f-g4gf | CVE-2026-41686 | medium | yes | |
| GHSA-hq66-cqwq-w95j | CVE-2026-16633 | high | yes | |
| GHSA-2pr8-phx7-x9h3 | CVE-2026-44294 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-66ff-xgx4-vchm | CVE-2026-44293 | high | yes | |
| GHSA-685m-2w69-288q | CVE-2026-44289 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-75px-5xx7-5xc7 | CVE-2026-44291 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-f38q-mgvj-vph7 | CVE-2026-54269 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-fx83-v9x8-x52w | CVE-2026-44292 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| GHSA-jggg-4jg4-v7c6 | CVE-2026-45740 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-jvwf-75h9-cwgg | CVE-2026-44290 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-q6x5-8v7m-xcrf | CVE-2026-44288 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| GHSA-wcpc-wj8m-hjx6 | CVE-2026-48712 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-f88m-g3jw-g9cj | CVE-2026-114113 | high | yes | |
| GHSA-rgj7-g3m4-5g8c | CVE-2026-114112 | high | yes | |
| GHSA-wq5f-xc86-pv6w | CVE-2026-114111 | high | yes | |
| GHSA-4r6h-8v6p-xvw6 | CVE-2023-30533 | high | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | no |
| GHSA-5pgg-2g8v-p4x9 | CVE-2024-22363 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | no |
Background: What a vulnerability scan can and cannot prove →
Dependencies 359 packages
| Packages resolved | 359 |
|---|---|
| Deprecated | 1 |
| Stale | 124 |
| 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 →
ask ~90
Ask a question about your knowledge base. Searches vault using hybrid AI search (BM25 + vector + RRF), returns structured results with sources. Use the results to compose your own AI-powered answer. Optionally saves as a new note.
| Name | Type | Req | Description |
|---|---|---|---|
| question | string | yes | The question to ask about your knowledge |
| save | boolean | – | Save the answer as a new note in the vault (default: false) |
No output schema declared.
No examples provided.
create-snapshot ~74
현재 프로젝트 관련 지식을 스냅샷으로 저장합니다. 나중에 load-snapshot으로 즉시 컨텍스트 복원.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | 스냅샷 이름 (예: my-project-v1) |
| queries | array | yes | 관련 지식 검색 쿼리들 |
No output schema declared.
No examples provided.
detect-gaps ~93
Detect knowledge gaps between topic clusters. Returns gap severity, isolated nodes, and suggested topics to bridge gaps. Result cached 6h (set forceRefresh=true to recompute).
| Name | Type | Req | Description |
|---|---|---|---|
| forceRefresh | boolean | – | Bypass cache and recompute (expensive: 30s+ on large vaults). Default false. |
| minSeverity | string | – | Minimum gap severity to include: high, medium, or low |
No output schema declared.
No examples provided.
export ~69
벡터 DB의 문서와 메타데이터를 JSON 파일로 내보냅니다. 다른 도구로 이전 가능.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | 출력 포맷 (기본: json) |
| outputPath | string | yes | 출력 파일 경로 (예: ./export.json) |
No output schema declared.
No examples provided.
find-decisions ~29
과거 기술 결정을 검색합니다.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | 검색 쿼리 |
No output schema declared.
No examples provided.
generate-claude-md ~86
프로젝트명을 기반으로 관련 지식(아키텍처, 패턴, 교훈, 결정사항)을 검색하여 CLAUDE.md 초안을 자동 생성합니다.
| Name | Type | Req | Description |
|---|---|---|---|
| projectName | string | yes | 프로젝트명 또는 주요 키워드 |
| topics | array | – | 추가 검색할 토픽 (예: ["인증", "배포", "성능"]) |
No output schema declared.
No examples provided.
generate-draft ~125
Gather knowledge from your vault to write a draft. Returns structured context (notes, concepts, excerpts) so you can compose a blog post, report, or outline. Use this when the user asks you to "write a draft", "blog post from my notes", or "summarize my knowledge about X".
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Desired output format (default: blog) |
| maxSources | number | – | Maximum number of source documents to include (default: 10) |
| topic | string | – | Topic or keyword to focus on. Leave empty for all knowledge. |
No output schema declared.
No examples provided.
get-document ~38
문서 ID 또는 파일 경로로 전체 문서 내용을 가져옵니다.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | 문서 ID 또는 파일 경로 |
No output schema declared.
No examples provided.
get-evolution ~62
Track semantic evolution of knowledge. Shows which topics have changed the most in meaning over time.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max results to return (default: 10) |
| topic | string | – | Optional topic/tag to filter. Omit for vault-wide analysis. |
No output schema declared.
No examples provided.
get-learning-path ~50
Generate a personalized learning path based on knowledge decay and gaps. Returns prioritized list of what to review, explore, or bridge.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max items to return (default: 10) |
No output schema declared.
No examples provided.
get-related ~56
특정 문서와 의미적으로 관련된 문서들을 반환합니다.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | 기준 문서 ID 또는 파일 경로 |
| limit | number | – | 반환할 관련 문서 수 (기본: 5) |
No output schema declared.
No examples provided.
link-code ~87
Find knowledge notes related to a code file. Extracts keywords from file path and content, then searches the knowledge base.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | – | Optional: code file content for deeper keyword extraction |
| filePath | string | yes | Path to the code file (e.g., src/auth/middleware.ts) |
| limit | number | – | Max related notes to return (default: 5) |
No output schema declared.
No examples provided.
list-topics ~29
지식 베이스의 전체 토픽/태그 목록과 문서 수를 반환합니다.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
load-snapshot ~44
저장된 스냅샷을 로드하여 프로젝트 컨텍스트를 즉시 복원합니다.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | 스냅샷 이름 |
No output schema declared.
No examples provided.
log-decision ~109
기술적 결정을 구조화하여 기록합니다. 나중에 "왜 이 선택을 했지?"에 답변할 수 있습니다.
| Name | Type | Req | Description |
|---|---|---|---|
| alternatives | array | – | 고려한 대안들 |
| context | string | – | 결정 배경/상황 |
| decision | string | yes | 선택한 내용 |
| project | string | – | 관련 프로젝트명 |
| reasoning | string | yes | 선택 이유 |
| title | string | yes | 결정 제목 (예: Zustand 대신 Jotai 선택) |
No output schema declared.
No examples provided.
search ~85
개인 지식 베이스에서 관련 문서/청크를 검색합니다. 자연어 쿼리와 키워드 모두 지원합니다.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | 반환할 결과 수 (기본: 5) |
| query | string | yes | 검색 쿼리 (자연어 또는 키워드) |
| tags | array | – | 태그 필터 |
No output schema declared.
No examples provided.
How do I install the io.github.Evanciel/stellavault MCP server?
io.github.Evanciel/stellavault runs locally as an npm package, launched with npx -y stellavault. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · stellavault
claude mcp add evanciel-stellavault -- npx -y stellavault
What is the io.github.Evanciel/stellavault MCP server?
io.github.Evanciel/stellavault is an MCP server listed in the public MCP registry as io.github.Evanciel/stellavault. Local-first MCP server: Claude searches, asks & drafts from your Obsidian vault. 21 tools, no keys. This page covers its npm package (stellavault).
Is the io.github.Evanciel/stellavault MCP server safe to use?
io.github.Evanciel/stellavault scores 78 out of 100 on VerifyMCP. We recorded 17 known advisories against it as of 5 November 2026. It declares no install or post-install scripts. 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 io.github.Evanciel/stellavault MCP server expose?
io.github.Evanciel/stellavault exposes 16 tools: search, get-document, list-topics, get-related, generate-claude-md, and 11 more. Their descriptions and schemas cost roughly 1,126 tokens of context every time the server is loaded.
Is the io.github.Evanciel/stellavault MCP server still maintained?
io.github.Evanciel/stellavault is still listed as active in the MCP registry. We last reached this channel on 5 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 io.github.Evanciel/stellavault MCP server under?
io.github.Evanciel/stellavault declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.