By iowarp
Run a local MCP server to perform compression and decompression tasks using clio-kit. It launches as a uvx Python subprocess with no API keys needed, enabling seamless integration into Model Context Protocol workflows for local data handling without external dependencies.
npx claudepluginhub iowarp/clio-kit --plugin clio-compressionHDF5 FastMCP - Scientific Data Access for AI Agents | CLIO Kit MCP Server
Share bugs, ideas, or general feedback.
Model Context Protocol Mcp Expert subagent
MCP server development helper with tool and resource scaffolding
Build FastMCP 3.x Python MCP servers — covers provider/transform architecture (including CodeMode, Tool Search, and server-level transforms), component versioning, session state, authorization (MultiAuth, PropelAuth, connection-pooled token verifiers), evaluation creation, Pydantic validation, async patterns, STDIO and HTTP transports, nginx reverse proxy deployment, background tasks, Prefab Apps UI, security patterns, client SDK usage, testing, deployment, and migration from FastMCP v2. TypeScript is a legacy reference only and is not updated for v3.
Reviews code for quality, maintainability, and correctness with actionable feedback. Ideal for PR evaluation, API design assessment, and implementation feedback.
Auto-generate MCP servers from any scriptable application's source code or API spec. Bundles slash commands to run the mcp-anything CLI pipeline from inside Claude Code.