Skills Anywhere
NPM · DSH-SKILLS-ANYWHERE
Discover and load Agent Skills from configured local directories and Git sources over stdio MCP.
Available components
Last scanned (19 hours ago)
Scores higher than 93% 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 Security82
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects @modelcontextprotocol/server 2.0.0, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- Dependency health was assessed across the 56 of 57 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to noteflowai/dsh-skills-anywhere). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 25 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 461 tokens (~153/item across 3 items; 3 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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 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.
- 4 Nov 26 0
- Dependency health: 0.94 → partial functional
- 28 Oct 26 0
- GHSA-f897-62hf-6gxq affects this package: high ▼ security
- 21 Oct 26 −6
- CVE-2026-111771 affects this package: high ▼ security
- CVE-2026-111770 affects this package: high ▼ security
- CVE-2026-111768 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- 19 Oct 26 +1
- Security disclosure: unverified → pass ▲ functional
- 18 Oct 26 −1
- Security disclosure: pass → unverified ▼ functional
- 17 Oct 26 +2
- Stability: 0.90 → pass security
- 16 Oct 26 −2
- Stability: pass → 0.90 functional
- 14 Oct 26 +46
- Injection markers: unverified → pass ▲ security
- Stability: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Package version: 0.18.0 → 0.19.0 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 4 Nov 2026 · Analysed npm/dsh-skills-anywhere@0.19.0
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 | noteflowai/dsh-skills-anywhere |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/noteflowai/dsh-skills-anywhere/.github/workflows/release.yml@refs/tags/v0.19.0 |
| Rekor log index | 3179591590 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:86a09fb4d9401d2901bf3ce6cfced209f3ab12583773e50109b829aedd77ba48a5217709fbd238e74fcf0571a0ff75ccb0d529e49f5c4ebc0f112d1ca |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 4 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-46jr-4wx8-v453 | CVE-2026-111768 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-f897-62hf-6gxq | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes | |
| GHSA-jm63-cq47-j5jp | CVE-2026-111770 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:L/A:H | yes |
| GHSA-rvq5-wwqv-78pq | CVE-2026-111771 | medium | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:N | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 56 packages
| Packages resolved | 56 |
|---|---|
| Stale | 7 |
| Tree resolution | Partial |
The dependency tree was only partially resolved, so these counts may be incomplete.
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 →
find_skills Find skills ~76
Search installed Agent Skills by keyword across names, descriptions and origins. Returns the best matches; load one with open_skill.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum matches to return (default 10). |
| query | string | yes | Keywords describing the task or skill, e.g. "pdf forms", "react testing", "docx". |
| Name | Type | Req | Description |
|---|---|---|---|
| matches | array | yes | – |
| total | number | yes | Skills searched. |
No examples provided.
list_skills List skills ~69
List installed Agent Skills (name, description, origin) available through this server. Use find_skills to search a large pool instead of paging through it.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum skills to return (default 200). |
| offset | integer | – | Skip this many skills (for paging). |
| Name | Type | Req | Description |
|---|---|---|---|
| skills | array | yes | – |
| total | number | yes | Model-invocable skills available. |
No examples provided.
open_skill Open skill ~228
Load the full instructions of an installed Agent Skill by exact name, together with the directory its scripts and references live in.
| Name | Type | Req | Description |
|---|---|---|---|
| expected_bundle_sha256 | string | – | Require the reviewed directory digest from bundle --json. Includes its scripts, references, assets and hidden files; excludes external dependencies. Implies include_bundle. |
| expected_sha256 | string | – | Require these exact SKILL.md bytes, using a hash from check --json or an earlier open_skill. Excludes referenced files. |
| expected_source_commit | string | – | Require this exact Git source commit, the receipt.source_commit of an earlier open_skill, with no local changes below the skill directory (tracked edits, deletions, untracked or ignored files, or fil… |
| include_bundle | boolean | – | Also fingerprint all regular files below this skill directory; bounded reads, no execution. |
| name | string | yes | Exact skill name as returned by find_skills or list_skills. |
| Name | Type | Req | Description |
|---|---|---|---|
| bundle | object | – | Directory inventory at inspection time. Does not freeze files for later execution or authenticate an author. |
| content | string | yes | The skill instructions (Markdown body without frontmatter). |
| declared_tools | array | – | Tools the author declared this skill needs, from allowed-tools. Reported, not enforced: this server cannot restrict your tools. Absent when the author declared none, which is not a statement that the… |
| description | string | yes | – |
| directory | string | yes | Absolute directory; resolve relative paths in the instructions against it. |
| name | string | yes | – |
| path | string | yes | Absolute path of the SKILL.md file. |
| receipt | object | yes | Identity of this instruction delivery. Attach to your own tool span; does not assert execution, permission enforcement or task success. Omits source path fields and instruction text; preserves author… |
| sha256 | string | yes | SHA-256 of original SKILL.md bytes, including frontmatter; not a security or resource verification. |
| source | string | yes | – |
No examples provided.
How do I install the Skills Anywhere MCP server?
Skills Anywhere runs locally as an npm package, launched with npx -y dsh-skills-anywhere. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · dsh-skills-anywhere
claude mcp add noteflowai-dsh-skills-anywhere -- npx -y dsh-skills-anywhere
What is the Skills Anywhere MCP server?
Skills Anywhere is an MCP server listed in the public MCP registry as io.github.noteflowai/dsh-skills-anywhere. Discover and load Agent Skills from configured local directories and Git sources over stdio MCP. This page covers its npm package (dsh-skills-anywhere).
Is the Skills Anywhere MCP server safe to use?
Skills Anywhere scores 90 out of 100 on VerifyMCP. We recorded 4 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 Skills Anywhere MCP server expose?
Skills Anywhere exposes 3 tools: list_skills, find_skills, open_skill. Their descriptions and schemas cost roughly 373 tokens of context every time the server is loaded.
Is the Skills Anywhere MCP server still maintained?
Skills Anywhere 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 Skills Anywhere MCP server under?
Skills Anywhere declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.