skillsvault

io.skillsvaultPublished by skillsvault.ioOfficial publisherv1.1.0Updated Nov 6, 2026

Your organisation's approved agent skills, governed by its policies.

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & MonitoringAI & ML

Overview

AI-generated overview

Remote MCP server that lets an assistant read its organisation's approved agent skills and refuse ones blocked by policy.

What you can do
  • List the approved skills in your organisation's registry
  • Load a skill's content and read individual skill files
  • Refuse a skill that your policies block, returning the reason
  • Record each skill load in the organisation's audit log
  • Pair with a CLI and gate hook that check every skill invocation against cached policy
When to use it
For teams that want agents to use only skills approved and versioned by their organisation, with blocked skills refused and every load audited, across Claude Code, Codex, Cursor and other MCP harnesses.
Requirements
A remote endpoint at skillsvault.io over streamable HTTP; OAuth sign-in is required and you pick your organisation on first connect. The full gate and pull workflow also needs the skillsvault CLI installed locally, and the gate hook does nothing until that CLI is present.
Before you install
Sign-in is OAuth and grants access as you to your organisation's registry. Skill names requested and skill content are exchanged with skillsvault.io and each load is written to the organisation's audit log; the CLI also reports gate decisions and a periodic heartbeat with machine name and installed skill names. The README states prompts and code are not sent.

Installation

In SourceWeft

  1. Open skillsvault in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.skillsvault%2Fskillsvault/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "skillsvault": {
      "type": "http",
      "url": "https://skillsvault.io/api/mcp"
    }
  }
}

README

[skillsvault — version, gate, and audit every skill your AI agents run]

[Website] [Docs] [License]

[skillsvault]

The control plane for agent skills. One skill that connects your agent to your organisation's registry — install what's approved, block what's banned, audit everything.

Works with Claude Code · Codex · Pi · every other harness

⚡ Add it to your agent

bash
npx skills add skillsvault/skillsvault-skill

That's it. Your agent reads the skill and bootstraps itself — it installs the skillsvault CLI, asks you to sign in once, then pulls your organisation's approved skills into every harness on the machine:

bash
curl -fsSL https://skillsvault.io/install.sh | shskillsvault loginskillsvault pull --all

As a Claude Code plugin

bash
claude plugin marketplace add skillsvault/skillsvault-skillclaude plugin install skillsvault@skillsvault

The first time Claude uses it, run /mcp and sign in to skillsvault: you pick your organisation, and no key is pasted or stored in a file. The plugin adds:

  • The skillsvault skill: the same skill as above.
  • The skillsvault MCP server: list_skills, load_skill and get_skill_file let Claude read your organisation's approved skills. All three are read-only. A skill your policies block is refused, with the reason.
  • The gate hook: before Claude runs a skill, subagent or typed /command, it asks the skillsvault CLI whether your organisation allows it. A block shows the policy's reason and a link to request an exception. The hook does nothing until the CLI is installed, and steps aside if skillsvault install-hook already wired the gate.

In other agents

The same repository is a plugin for other agents too. Each one signs you in to skillsvault the first time it connects:

  • Cursor, Codex and ChatGPT: add the MCP server https://skillsvault.io/api/mcp. Marketplace listings are on their way; the plugin already follows the Agent Plugins standard (plugin.json, mcp.json, skills/).
  • Gemini CLI: gemini extensions install https://github.com/skillsvault/skillsvault-skill
  • Anything else that speaks MCP: add https://skillsvault.io/api/mcp. It is listed in the official MCP Registry as io.skillsvault/skillsvault.

What it sends, and where

  • MCP server. It calls https://skillsvault.io/api/mcp as you, once you sign in. It sends the skill names Claude asks for, and receives your organisation's skill content. Each load is recorded in your organisation's audit log.
  • Gate hook. It runs on your machine against a signed copy of your organisation's policies, with no network call per decision. The CLI reports each decision (skill name and version, decision, reason, machine name) to your organisation's audit log. It also sends a periodic heartbeat (CLI version, whether the gate hook is wired, and the names of the skills installed on the machine), so your organisation can see which machines are covered.
  • Nothing else. Nothing is sent anywhere other than skillsvault.io. Your prompts and code are never sent. See the privacy policy.

🎬 See it work

🧭 Why

Agents pick up skills from everywhere — repos, marketplaces, teammates, other agents. Nobody knows which version runs where, and a poisoned or outdated skill looks exactly like a good one. skillsvault gives your organisation one source of truth:

📦 Versioned registryEvery skill content-addressed, versioned, and signed. pull installs the approved version — and removes banned ones.
🚦 The gateEvery invocation checked locally, before it runs: allow / warn / halt. Works offline from a cached policy bundle.
🧾 Audit trailWho ran which skill version, on which host, under which policy — append-only and exportable.
🕸️ Every harnessOne policy for Claude Code, Codex, Pi, and anything else that runs skills.

🛠️ What your agent does with it

Once connected, the skill teaches your agent to govern itself:

bash
skillsvault whoami                    # which org am I connected to?skillsvault install-hook              # gate every skill invocation (Claude Code)skillsvault pull --all                # install approved skills, remove banned onesskillsvault gate --skill <org/skill>  # allow / warn / halt — before useskillsvault publish <path>            # push a skill to the org registryskillsvault status                    # how fresh is the policy bundle?

Three rules the skill enforces, always:

  1. If the gate halts a skill → the agent does not run it. Ever.
  2. The approved version from pull beats any sideloaded copy.
  3. A halt is never bypassed — the verdict names the approved replacement.

🔎 Scan your skills in CI

Publishing skills? Check them on every push and pull request. The action installs the CLI (verified against the release checksums), scans every folder with a SKILL.md, and fails the job when one pipes a download into a shell, reads secret paths or hides content. Nothing is sent anywhere.

yaml
# .github/workflows/skills.ymlname: skillson: [push, pull_request]jobs:  scan:    runs-on: ubuntu-latest    steps:      - uses: actions/checkout@v4      - uses: skillsvault/skillsvault-skill@main        with:          path: skills          # default: the whole repository          fail-on-flag: true    # default

To see findings as code-scanning alerts on the pull request, write SARIF and upload it:

yaml
    permissions:      security-events: write    steps:      - uses: actions/checkout@v4      - uses: skillsvault/skillsvault-skill@main        with:          path: skills          sarif: skillsvault.sarif      - uses: github/codeql-action/upload-sarif@v3        if: always()        with:          sarif_file: skillsvault.sarif

Locally, the same check is skillsvault scan --dir skills --fail-on-flag (add --sarif for SARIF).

📚 Learn more

  • 📖 Documentation — CLI reference, policies, the signed bundle contract
  • 🚀 Quickstart — zero to governed in five minutes
  • 🔍 SKILL.md — the skill itself, exactly what your agent reads
  • 🧾 references/cli.md — full command reference

License

Apache-2.0 — see LICENSE. This covers the skill and plugin in this repository; the skillsvault service is governed by its terms.

Built in Germany 🇩🇪 · skillsvault.io · [email protected]

Source: README.md at commit a41909a

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.1.0LatestOct 29, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts