mcpField
F
Formester

Formester

Remote
github.com/formesterProductivity0Updated 28w ago
Repository

About Formester

Formester is a remote MCP server that lets AI agents work with Formester form submissions and attachments. It supports reading, searching, and updating submissions, as well as fetching files, with OAuth or API token authentication.

Key features

  1. 01Read and search form submissions
  2. 02Update submissions with extracted insights
  3. 03Fetch submission attachments
  4. 04Authenticate with OAuth or API tokens

Use cases

  1. 01Summarize support form responses
  2. 02Classify and update contact submissions
  3. 03Extract skills from attached resumes
  4. 04Flag urgent issues in recent submissions

MCP support

Formester exposes a remote MCP endpoint with `read_submission`, `query_submissions`, `update_submission`, and `fetch_file` tools. MCP clients can authenticate using OAuth or an API token.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://app.formester.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Formester MCP Server

Give your AI agent access to form submissions — read responses, query across forms, write insights back, and process file attachments.

Endpoint: https://app.formester.com/mcp

Available tools: read_submission · query_submissions · update_submission · fetch_file

Quickstart

Step 1: Choose your auth method

MethodBest for
OAuthInteractive clients (Claude.ai, Cursor, VS Code) — authorize via browser, no token setup
API TokenScripts, automation, or clients without OAuth support — create once in Formester → API

→ Full authentication guide

Step 2: Connect your AI client


Claude

Via OAuth (recommended)

Settings → Connectors → Add custom connector → enter a name and https://app.formester.com/mcp as the URL. Claude will prompt you to authorize on first connection.

Via API Token

{
  "mcpServers": {
    "formester": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://app.formester.com/mcp",
        "--header",
        "Authorization: Bearer YOUR_TOKEN_HERE"
      ]
    }
  }
}

Fully quit and restart Claude Desktop.

VS Code (GitHub Copilot)

Via OAuth

Create or edit .vscode/mcp.json:

{
  "servers": {
    "formester": {
      "type": "http",
      "url": "https://app.formester.com/mcp"
    }
  }
}

VS Code will handle the OAuth flow automatically. Switch Copilot Chat to Agent mode to use the tools.

Via API Token

{
  "servers": {
    "formester": {
      "type": "http",
      "url": "https://app.formester.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN_HERE"
      }
    }
  }
}

Cursor

Via OAuth

Settings → MCP → Add new MCP server:

{
  "mcpServers": {
    "formester": {
      "url": "https://app.formester.com/mcp"
    }
  }
}

Cursor will prompt you to authorize via browser on first use.

Via API Token

{
  "mcpServers": {
    "formester": {
      "url": "https://app.formester.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN_HERE"
      }
    }
  }
}

Claude Code

Via OAuth

claude mcp add --transport http formester https://app.formester.com/mcp

Via API Token

claude mcp add --transport http formester https://app.formester.com/mcp \
  --header "Authorization: Bearer YOUR_TOKEN_HERE"

Windsurf

Via OAuth

Edit ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "formester": {
      "type": "streamable-http",
      "url": "https://app.formester.com/mcp"
    }
  }
}

Via API Token

{
  "mcpServers": {
    "formester": {
      "type": "streamable-http",
      "url": "https://app.formester.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN_HERE"
      }
    }
  }
}

Restart Windsurf after saving.


Example prompts

Summarize a support ticket

Read submission a1b2c3d4 and summarize the issue reported.

Triage a contact form

Read the last 20 submissions for form xyz, classify each one as 'sales', 'support', or 'other'
based on the message content, and save the category as a custom field called 'ai_category'.

Review a job application

Read submission a1b2c3d4 with files included. Fetch the resume PDF, extract the candidate's
skills and years of experience, and write a brief evaluation back as 'ai_evaluation'.

Process a batch of applications

Query all submissions for form xyz from the past 7 days. For each one, fetch the attached CV,
extract the applicant's name, role applied for, and top 3 skills, then save them as custom fields.

Flag urgent issues

Get the last 50 submissions for form xyz. Identify any that mention billing problems or account
access issues, mark them as starred, and set a custom field 'ai_priority' to 'urgent'.

Docs


Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.