Formswrite MCP
Enables LLMs to convert documents to Google Forms, edit questions, list and publish forms, and run AI form assistant tools through the Formswrite API.
README
Formswrite MCP
Connect Claude Desktop, Cursor, Claude Code, and other MCP clients to the Formswrite API.
Convert documents to Google Forms, edit questions, list and publish forms, and run AI form assistant tools — all from your LLM.
What you can do
Once installed, your LLM gains access to the Formswrite toolset:
create_form— create a Formswrite job from a Google Doc, PDF, or pasted textget_form_data— read the current questions, options, and metadata of a formmodify_questions— add, edit, delete, or reorder questionsupdate_form_metadata— update title, description, or introductionpublish_form— publish a draft form so it can accept responsesexport_form— export a form to Google Forms, Moodle, Kahoot, Quizizz, Canvas, and 25+ other formatslist_jobs/get_job— browse and inspect your conversion jobs
Install
1. Get an API token
Sign in to your Formswrite dashboard and create an API token at: https://app.formswrite.com/settings/api-tokens
2. Add to your MCP client
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"formswrite": {
"command": "npx",
"args": ["-y", "@formswrite/mcp"],
"env": {
"FORMSWRITE_API_TOKEN": "fw_..."
}
}
}
}
Restart Claude Desktop. The Formswrite tools will appear in the tools list.
Cursor
In Settings → MCP, add:
{
"formswrite": {
"command": "npx",
"args": ["-y", "@formswrite/mcp"],
"env": { "FORMSWRITE_API_TOKEN": "fw_..." }
}
}
Claude Code
claude mcp add formswrite -- npx -y @formswrite/mcp
Then set the token in ~/.claude/settings.json:
{ "env": { "FORMSWRITE_API_TOKEN": "fw_..." } }
Direct Streamable HTTP (no npm needed)
If your client supports the Streamable HTTP transport natively (Cursor 0.45+, ChatGPT MCP, recent Claude Desktop), you can skip this package and connect directly:
URL: https://mcp.formswrite.com/mcp
Header: Authorization: Bearer fw_...
How it works
This package is a small stdio ↔ Streamable HTTP bridge. It runs locally on your machine, opens a connection to https://mcp.formswrite.com/mcp using your API token, and forwards JSON-RPC messages between your MCP client (stdio) and the Formswrite server (HTTP).
All tool logic lives on the Formswrite backend — this package contains no business logic and never sees your form data outside of forwarding it.
Configuration
| Env var | Required | Default | Description |
|---|---|---|---|
FORMSWRITE_API_TOKEN |
yes | — | API token from your Formswrite dashboard |
FORMSWRITE_MCP_URL |
no | https://mcp.formswrite.com/mcp |
Override for staging or self-hosted |
Troubleshooting
Diagnostic output is written to stderr (stdout is the JSON-RPC channel). To see logs:
- Claude Desktop: open the MCP logs panel (Settings → Developer)
- CLI: run
FORMSWRITE_API_TOKEN=... npx @formswrite/mcp 2>&1 >/dev/null
Common issues:
Missing token—FORMSWRITE_API_TOKENis not set in your client's MCPenvblock401 unauthorized— token is invalid, expired, or for the wrong environment. Generate a new one at the dashboard URL above429 rate_limited— you're past the 60 req/min limit; slow down
License
MIT — see LICENSE.
Links
- Formswrite: https://formswrite.com
- Dashboard: https://app.formswrite.com
- Issues: https://github.com/formswrite/formswrite-mcp/issues
- MCP spec: https://modelcontextprotocol.io
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.