About skillsvault
skillsvault gives organizations a governed registry for agent skills, aimed at teams that need to approve, block, and audit skill use. It combines signed, versioned skills with a local policy gate and support across agent harnesses.
Key features
- 01Organization-approved skill registry
- 02Install or remove skills by policy
- 03Offline allow, warn, or halt gate
- 04Skill version and usage audit trail
- 05Skill management across harnesses
Use cases
- 01Distribute approved skills across a team
- 02Check organizational policy before skill execution
- 03Audit skill versions and use across machines
- 04Prevent banned or outdated skills from running
MCP support
It provides an MCP server for clients to list and load organization-approved skills and read skill files, using read-only tools. Skills blocked by policy are refused with the reason.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://skillsvault.io/api/mcpclaude mcp add --transport http io-skillsvault-skillsvault https://skillsvault.io/api/mcp{"mcpServers":{"io-skillsvault-skillsvault":{"type":"http","url":"https://skillsvault.io/api/mcp"}}}Open in Cursor{"servers":{"io-skillsvault-skillsvault":{"type":"http","url":"https://skillsvault.io/api/mcp"}}}Open in VS Code{"mcpServers":{"io-skillsvault-skillsvault":{"type":"http","url":"https://skillsvault.io/api/mcp"}}}{"mcpServers":{"io-skillsvault-skillsvault":{"serverUrl":"https://skillsvault.io/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project README
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
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:
curl -fsSL https://skillsvault.io/install.sh | sh
skillsvault login
skillsvault pull --all
As a Claude Code plugin
claude plugin marketplace add skillsvault/skillsvault-skill
claude 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_skillandget_skill_filelet 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 theskillsvaultCLI 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 ifskillsvault install-hookalready 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 asio.skillsvault/skillsvault.
What it sends, and where
- MCP server. It calls
https://skillsvault.io/api/mcpas 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 registry | Every skill content-addressed, versioned, and signed. pull installs the approved version — and removes banned ones. |
| 🚦 The gate | Every invocation checked locally, before it runs: allow / warn / halt. Works offline from a cached policy bundle. |
| 🧾 Audit trail | Who ran which skill version, on which host, under which policy — append-only and exportable. |
| 🕸️ Every harness | One 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:
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 ones
skillsvault gate --skill <org/skill> # allow / warn / halt — before use
skillsvault publish <path> # push a skill to the org registry
skillsvault status # how fresh is the policy bundle?
Three rules the skill enforces, always:
- If the gate halts a skill → the agent does not run it. Ever.
- The approved version from
pullbeats any sideloaded copy. - A halt is never bypassed — the verdict names the approved replacement.
📚 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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.