PoYo MCP Server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@PoYo MCP Serverlist available AI models"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PoYo Devtools
Official PoYo CLI, stdio MCP bridge, and Agent Skill. Model schemas and pricing are discovered from the hosted PoYo Capability Catalog.
Workspace
@poyoapi/core: Catalog, chat, generation-task, account, and credential client.@poyoapi/cli: Catalog-drivenpoyocommand with chat SSE support.@poyoapi/mcp: Local stdio bridge to the hosted PoYo MCP server.poyo-ai-models: Agent workflow for discovering and safely executing PoYo models.
Related MCP server: GenieOS MCP Server
Development
pnpm install
pnpm build
pnpm typecheck
pnpm testRefresh production artifacts before release:
pnpm sync:catalog
pnpm generate:skills
pnpm skill:checkPublishing to npm
The three public packages are published together with the same version:
@poyoapi/core@poyoapi/mcp@poyoapi/cli
Configure an npm Trusted Publisher for each package with:
Organization or user:
PoyoAPIRepository:
poyo-devtoolsWorkflow:
publish.ymlEnvironment:
npm
For a stable release, prepare and push the release commit:
pnpm release:stable -- 0.1.0
git pushThen run the Publish npm packages GitHub Actions workflow with:
dist_tag: latest
confirmation: publish:0.1.0:latestFor a prerelease, set all package versions to the same prerelease version and
run the workflow with the beta tag, for example:
dist_tag: beta
confirmation: publish:0.2.0-beta.1:betaThe workflow validates the version, refreshes the production catalog, builds
and tests the workspace, packs the packages in dependency order, and publishes
them with npm provenance. No long-lived NPM_TOKEN secret is required when the
Trusted Publishers are configured.
This server cannot be deployed
Maintenance
Related MCP Connectors
- QuallaaOAuthcom.quallaa
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
- UnifAPIOAuthcom.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA general-purpose MCP gateway that exposes your local CLI skills to any AI assistant.35 npm1MIT

GenieOS MCP Serverofficial
AlicenseAqualityCmaintenanceStdio bridge for editors to connect to the GenieOS MCP server, enabling AI agents to interact with GenieOS via Streamable HTTP transport.6416 npmMIT- AlicenseNot gradedqualityAmaintenanceMCP stdio bridge to a running Navop desktop application, enabling AI agents to interact with Navop via MCP protocol.5MIT
- AlicenseNot gradedqualityCmaintenanceBridges stdio MCP clients to the locally installed Juvina memory engine, enabling persistent local AI memory for coding assistants.MIT