MCP server · FlutterFlow

flutterflow-ai

Official FlutterFlow AI MCP server. Exposes FlutterFlow's Project APIs to an MCP-compatible agent (Claude Code, Gemini CLI, Codex) so it can read and modify a FlutterFlow project using real project context — plan changes, apply them, and report back into the visual builder.

Open docs → FlutterFlow provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: FlutterFlow Type: Documentation link Transport: stdio Host: docs.flutterflow.io

Documentation

https://docs.flutterflow.io/ff-concepts/advanced/flutterflow-cli/flutterflow-mcp

Documentation link · transport stdio

Tools

run — Apply generated changes / build the project.
validate — Validate project changes before applying.
inspect — Inspect project structure and resources.
resources — List available project resources.
search — Search within the project.
status — Report project / session status.
plan — Plan a set of changes before applying.
trace — Trace how a change propagates.
history — Review change history.
context-check — Check that project context is current.
refresh-context — Refresh cached project context.
precache — Pre-cache project context for faster runs.
upgrade — Upgrade the workspace/toolchain.
refresh-workspace — Refresh the local workspace.
doctor — Diagnose the workspace and toolchain.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.