Goose Extensions
Goose MCP is a collection of MCP servers designed to extend the capabilities of the Goose AI assistant. It includes five specialized servers: mcp_plex for interacting with Plex Media Server, mcp_rt for scraping movie information from Rotten Tomatoes, mcp_sales_history for fetching eBay sales data, mcp_searxng_search for web searches via SearxNG instances, and mcp_taskwarrior for task management. Each server is built using FastMCP, requires Python 3.10+ with UV package management, and is designed to be easily integrated into Goose through its extension system, enabling users to access external services and data sources directly within their AI assistant conversations.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/jay4242/goose_mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Goose Extensions from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.