No install? Use cloud.anythingmcp.com directly.
Sign in, install the Typeform in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Read Typeform responses, list forms, fetch form definitions and manage workspaces from any AI agent. 10 tools, Personal Token Bearer auth. Optimized for read+analysis flows (the heavy form-builder write side is out of scope).
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Typeform、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Typeform + Gemini
Read Typeform responses, list forms, fetch form definitions and manage workspaces from any AI agent. 10 tools, Personal Token Bearer auth. Optimized for read+analysis flows (the heavy form-builder write side is out of scope).
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
TYPEFORM_PERSONAL_TOKEN
步骤 1 — 获取凭证
Setup:
- Sign in to Typeform → top-right avatar → Settings → Personal tokens → Generate a new token.
- Grant the scopes you need — at minimum
forms:read,responses:read,workspaces:read. For write operations addforms:write. The connector'sinstructionsdocuments what scopes each tool requires implicitly. - Copy the token (shown ONCE). Set
TYPEFORM_PERSONAL_TOKEN.
Authentication: Bearer token. Same token for all endpoints.
Form IDs: each form has an 8-character alphanumeric ID (e.g. Wf2hrM), visible at the end of the form's public URL (yourname.typeform.com/to/Wf2hrM → ID is Wf2hrM). Use typeform_list_forms once to discover IDs you own.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Typeform应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
typeform_get_current_user | Return the user the personal token belongs to: email, alias, language |
typeform_list_forms | List forms (paginated) |
typeform_get_form | Fetch a form's full definition: title, fields[] (each with id, title, type, properties, ref, validations), thankyou_screens, welcome_screens |
typeform_list_responses | List responses (submissions) for a form, paginated |
typeform_delete_responses | Delete responses by their IDs (max 1000 per call) |
typeform_list_workspaces | List workspaces (folders for organizing forms) |
typeform_get_workspace | Fetch one workspace's full details including members[] and forms[] (URI list) |
typeform_list_form_messages | Get the localized messages (button text, validation errors, etc |
typeform_get_form_insights | Fetch aggregate insights (visits, submissions, completion_rate, average_time_to_complete, etc |
typeform_list_themes | List visual themes (color/font/background combos) available on the account |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对您有帮助吗?