flet-mcp-server
# Flet MCP Server [](https://pypi.org/project/flet-mcp-server/) [](https://pepy.tech/project/flet-mcp-server)   An auto-updating Model Context Protocol (MCP) server that dynamically fetches, caches, and serves the official Flet documentation and ecosystem packages directly from GitHub and PyPI. ## Features * **GitHub Tree Sync**: Maps documentation in real-time. * **Intelligent Caching**: Uses `diskcache` for fast responses. * **Ecosystem Discovery**: Finds and verifies official and community Flet packages. * **AI-Optimized**: Tool definitions designed for LLM understanding. ## Tools Included ### 1. `list_flet_controls` List all available Flet UI controls. ### 2. `search_flet_docs(query)` Search the documentation index. ### 3. `get_flet_doc(doc_path)` Get raw Markdown for a specific doc. ### 4. `list_official_packages()` List official Flet extension packages. ### 5. `search_flet_ecosystem(query)` Search for verified community Flet components. ### 6. `get_package_details(package_name)` Fetch version and installation info from PyPI. ## Client Configuration Examples ### 🌌 Antigravity / Cascade Add this to your `mcp_config.json`: ```json { "mcpServers": { "flet-mcp-server": { "command": "uvx", "args": ["flet-mcp-server"] } } } ``` ### 🤖 Claude Desktop Add this to your `claude_desktop_config.json`: ```json { "mcpServers": { "flet-mcp-server": { "command": "uvx", "args": ["flet-mcp-server"] } } } ``` ### 💻 Cursor / Windsurf In your IDE's MCP settings, add a new server: - **Name**: Flet MCP - **Type**: Command - **Command**: `uvx flet-mcp-server`
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- version-control
- Source
- Smithery
- Repository
- github.com/nwokike/flet-mcp-server
- Author type
- human
- Updated
- 2026-09-02
Use via MCP
Resolve flet-mcp-server 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.