
SkillOS MCP Server
io.github.JoshanihubPublished by GitHub account Joshanihubv3.0.2Updated Oct 25, 2026
SkillOS MCP Runtime exposes the SkillOS skill registry as activatable MCP tools for AI agents.
Overview
A local MCP runtime that exposes the SkillOS skill registry to AI agents as activatable tools.
- What you can do
- Expose the SkillOS skill registry to an AI assistant as MCP tools that can be activated on demand, letting the assistant discover and invoke registered skills during a session. The manifest lists no individual tools, so the exact set of actions depends on the registry contents and the package itself.
- When to use it
- Consider it if you already use the SkillOS skill registry and want an AI assistant to reach those skills through MCP on your desktop.
- Requirements
- Runs as a local stdio process installed from the npm package skillos-mcp-server, so a Node.js runtime is needed. Desktop use only; no web execution. No authentication, environment variables or headers are declared.
Installation
In SourceWeft
- Open SkillOS MCP Server in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
This repository has no README.
Tools
0Version history
1- v3.0.2LatestSep 23, 2026
Score
25% 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 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- 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
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Declare a license in the repository or the registry entry.