Skip to main content

Flet MCP server for LLM agents

Project description

flet-mcp

MCP (Model Context Protocol) server that gives LLM agents access to Flet examples, documentation, and API reference.

Installation

pip install flet-mcp

Usage

Start the MCP server

# stdio transport (default, for use with Claude Desktop, Cursor, etc.)
flet mcp

# HTTP transport
flet mcp --transport streamable-http --port 8000

Configure in Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "flet": {
      "command": "flet",
      "args": ["mcp"]
    }
  }
}

List available tools

fastmcp list packages/flet-mcp/src/flet_mcp/server.py

Call tools from the command line

# Search examples
fastmcp call packages/flet-mcp/src/flet_mcp/server.py search_examples '{"query": "dropdown"}'

# Get full example code
fastmcp call packages/flet-mcp/src/flet_mcp/server.py get_example '{"example_id": "controls_dropdown_styled"}'

# Search documentation
fastmcp call packages/flet-mcp/src/flet_mcp/server.py search_docs '{"query": "TextField validation"}'

# Get control API reference
fastmcp call packages/flet-mcp/src/flet_mcp/server.py get_control_api '{"name": "TextField"}'

# Find an icon
fastmcp call packages/flet-mcp/src/flet_mcp/server.py find_icon '{"query": "settings"}'

# Search large enums
fastmcp call packages/flet-mcp/src/flet_mcp/server.py search_enum_members '{"name": "Icons", "query": "arrow"}'

# Get CLI help
fastmcp call packages/flet-mcp/src/flet_mcp/server.py get_cli_help '{"command": "run"}'

Use with Pydantic AI

from pydantic_ai import Agent
from pydantic_ai.toolsets import MCPToolset
from flet_mcp import mcp

agent = Agent("claude-sonnet-4-20250514", toolsets=[MCPToolset(mcp)])
result = agent.run_sync("Create a Flet app with a login form")

Tools

Tool Description
search_examples Search example projects by keyword
get_example Get full source code for an example
search_docs Search documentation by keyword
get_doc Get full content of a doc section
list_controls List controls and services, with optional filtering
get_control_api Get properties, events, and methods for a control
get_type_api Get fields and methods for a type (ButtonStyle, Padding, etc.)
get_enum Get enum members
search_enum_members Search large enums (Icons, CupertinoIcons)
enum_has_member Check if an enum value exists
find_icon Search Material and Cupertino icons by keyword
get_cli_help Get structured CLI command options

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

flet_mcp-0.1.0.tar.gz (2.4 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

flet_mcp-0.1.0-py3-none-any.whl (2.5 MB view details)

Uploaded Python 3

File details

Details for the file flet_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: flet_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 2.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.24 {"installer":{"name":"uv","version":"0.9.24","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for flet_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 d0e35dd7ded02a44508a6b1a8ec374adcf01d3d686046946f3d072f69d46711b
MD5 5f28d5417353dead4cccd7627808bbf7
BLAKE2b-256 85e6efc21e613775fc2d30d9a4ae627146e8fa2bf37eda7c410f54f08e553da6

See more details on using hashes here.

File details

Details for the file flet_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: flet_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 2.5 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.24 {"installer":{"name":"uv","version":"0.9.24","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for flet_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 041b81868ff5f7160d233b819648cc6b78fdec5cf0fb2a74b82c7d5f7f35abaa
MD5 bd0f98d365ff1c6f041ad1b2c62d4c60
BLAKE2b-256 6a1606c7170d1703b1b13535a84ba8b877dd5520adf2a6cc2cc023486a87c3e9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page