Formester
@formester
关于 Formester
Gives AI agents access to Formester form submissions - read, search, update, and extract content from file attachments.
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"formester": {
"command": "npx",
"args": [
"mcp-remote",
"https://app.formester.com/mcp/sse",
"--header",
"Authorization: Bearer YOUR_TOKEN_HERE"
]
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Formester?
Formester is an MCP server that connects AI agents directly to Formester form submissions, allowing them to read, search, write, and analyze submissions without custom API integration.
How to use Formester?
Create an API token in the Formester app (select forms and permissions), then configure your MCP client to use the SSE endpoint https://app.formester.com/mcp/sse with an Authorization: Bearer YOUR_TOKEN_HERE header. Supported clients include Claude Desktop, VS Code (Copilot), Cursor, Claude Code, and Windsurf.
Key features of Formester
- Read individual submissions and all their field data
- Search and filter multiple submissions with date range and custom field queries
- Write AI-generated data back as custom fields
- Fetch file attachments (images, PDFs, text files) up to 10 MB
- Paginated queries with
limit,offset, andhas_moreindicator - Fine-grained permissions: View Submissions, Update Submissions, View Forms
Use cases of Formester
- Screen job applications by reading CV attachments and scoring candidates
- Triage support requests by classifying incoming submissions by category and urgency
- Qualify leads by analyzing contact form submissions and flagging high-priority entries
- Analyze survey responses with sentiment analysis and tag themes
FAQ from Formester
What permissions can I assign to the agent?
You can assign View Submissions (read data and attachment metadata), Update Submissions (write custom fields), and View Forms (read form metadata). Choose only what the agent needs.
Can the agent overwrite original form submission fields?
No. Only custom fields can be written back — original submission fields cannot be overwritten.
What file types can be fetched and how are they returned?
Images (PNG, JPG, GIF, WebP) are returned as base64 for vision-capable models. PDFs can return extracted text or base64. Plain text files (TXT, MD, CSV, JSON) are returned as raw text.
What is the maximum file size supported?
The maximum file size for fetch_file is 10 MB.
How is the server accessed and authenticated?
It uses SSE transport over HTTPS at https://app.formester.com/mcp/sse with a bearer token passed as a header in the configuration.
其他 分类下的更多 MCP 服务器
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
Nginx UI
0xJackyYet another WebUI for Nginx
Blender
ahujasidOpen-source MCP to use Blender with any LLM
ICSS
chokcoco不止于 CSS
评论