Flet changes faster than model training data. Controls get renamed, deprecated
and removed (ft.ElevatedButton → ft.Button, and Button(text=...) is now
Button(content=...)), properties change types, icon names get hallucinated.
The only reliable reference is the flet source code actually installed in
your environment — this server ships with flet as a dependency, gives your AI
tools to read it directly, and — uniquely — can before you ever see it.
Model Context Protocol (MCP) server that dynamically fetches and serves official Flet resources to AI agents, including documentation, controls, packages, and ecosystem components.
Estrelas
17
Ferramentas
—
Disponibilidade
—
run and verify AI-written
Flet code against that installed flet
Upgrading from v0.2.x? The plain command below works again — no
--with mcp<2 --with typing_extensions flags needed anymore. v0.2.x broke
because the mcp SDK 2.0 removed mcp.server.fastmcp; v1.0.0 is built on the
new MCPServer API and pins mcp>=2.
uvx flet-mcp-server
Verify your Flet code (the killer feature)
verify_flet_code(code) checks AI-generated Flet code against the installed
flet in two passes and reports every problem with line numbers and hints:
Dynamic: the code runs in a sandboxed subprocess (app launchers are
neutralized — nothing opens, nothing starts) while flet's own validators
fire on every constructed control, catching errors that normally only appear
at runtime — like Slider(min=10, max=5).
{
"status": "errors",
"flet_version": "0.86.5",
"controls_verified": 6,
"diagnostics": [
{"severity": "warning", "code": "deprecated", "line": 4,
"message": "'ElevatedButton' is deprecated in flet 0.86.5.",
"hint": "Did you mean 'FilledButton'?"},
{"severity": "error", "code": "bad-kwarg", "line": 4,
"message": "'ElevatedButton' has no property 'text' in flet 0.86.5."},
{"severity": "error", "code": "runtime", "line": null,
"message": "ValueError: Slider: min (10) must be less than or equal to max (5)"}
]
}
The server's instructions tell AI clients to verify before delivering and
fix-and-reverify until the report is passed — plus three ready-made prompts
(verify_flet_code_prompt, migrate_flet_prompt, build_flet_ui_prompt)
that encode the full workflow.
What your AI gets
Verify (new in v1.0.0) — confidence that AI-written code is actually valid:
verify_flet_code(code) — static + sandboxed dynamic verification against
the installed flet, structured diagnostics with line numbers and hints.
Resources: flet://version and flet-source://<module> (browsable installed
source, path-traversal safe).
Source of truth — reads the flet package installed alongside the server,
so every answer matches the exact version your app runs:
inspect_flet_control(control_name) — every property with type, default and
origin class (inherited fields marked), on_* events, deprecation warnings,
the class hierarchy, and the full class source with per-property docstrings.
get_flet_version() — which flet version the tools are reading, and from where.
search_flet_source(query) — grep the installed flet sources; definitions
rank first.
read_flet_source(module, symbol?) — numbered source of any module, or a
single class/function extracted by AST.
list_flet_api() — the true flet.__all__ of the installed version, grouped
by category (Material / Cupertino / Core controls, Services, Components & hooks).
search_flet_icons(query, icon_set) — valid ft.Icons.* /
ft.CupertinoIcons.* names, so the AI never invents one again.
search_flet_colors(query) — valid ft.Colors.* constants, including shades
like AMBER_500.
Docs & examples — official guides and runnable apps:
Every tool response then reports e.g. [flet 0.86.5 — FLET_MCP_VENV=…/project/.venv],
and inspect_flet_control shows deprecations relative to that version.
Read flet from this project venv instead of the bundled one (Local Mode).
FLET_MCP_TRANSPORT
stdio
stdio, sse, or streamable-http (uses the bundled uvicorn).
FLET_MCP_HOST
127.0.0.1
Bind host for HTTP transports.
FLET_MCP_PORT
8000
Bind port for HTTP transports.
GITHUB_TOKEN
(unset)
Authenticated GitHub API access — higher rate limits.
FLET_REPO
flet-dev/flet
Docs source repo.
FLET_BRANCH
main
Docs source branch.
FLET_MCP_CACHE_DIR
~/.cache/flet-mcp
HTTP cache location (XDG-aware).
Docker / remote deployments: run with FLET_MCP_TRANSPORT=streamable-http FLET_MCP_HOST=0.0.0.0 — a GET /health liveness endpoint is included.
OpenTelemetry traces are emitted automatically by the MCP SDK; configure any
standard OTEL_* environment variables to export them.
Development
git clone https://github.com/Nwokike/flet-mcp-server.git
cd flet-mcp-server
uv sync
uv run pytest # unit tests (75)
uv run ruff check src/ tests/ scripts/ # lint
uv run python scripts/smoke_stdio.py # full MCP handshake from a fresh uvx env
The smoke script is the regression test for the v0.2.0 outage: it installs the
server into a clean ephemeral environment (exactly what end users get) and
verifies the handshake plus one call per tool group.
Model Context Protocol (MCP) server that dynamically fetches and serves official Flet resources to AI agents, including documentation, controls, packages, and ecosystem components.
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Perguntas
Como instalo Flet?
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Flet precisa de uma chave de API?
Este registro não lista nenhuma variável de ambiente obrigatória.
Qual transporte Flet usa?
Flet roda localmente via stdio.
Quando Flet foi verificado pela última vez?
Última verificação: 2026-10-27. Model Context Protocol (MCP) server that dynamically fetches and serves official Flet resources to AI agents, including documentation, controls, packages, and ecosystem components.