Pocket MCP Manager
Pocket MCP Manager provides a flexible client-server architecture for managing multiple Model Context Protocol servers through a unified interface. The system allows users to add, launch, and control MCP servers via a central management UI, generate API keys linked to running servers, and connect to them through a single proxy server in AI tools like Claude or Cursor. Built with a TypeScript server component that routes requests to appropriate backend servers and a Python client with Streamlit UI, it eliminates the need to reconfigure multiple connection settings when changing which MCP servers to use. The implementation includes an example LLM client demonstrating integration with OpenAI's API while leveraging connected MCP servers' capabilities.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/dailydaniel/pocket-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Pocket MCP Manager 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.