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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。