fillout-mcp-server
Enables form management, response handling, and analytics via the Fillout.io API, allowing users to create, update, and fetch forms and submissions through natural language.
README
Fillout.io MCP Server
MCP Server for the Fillout.io API, enabling form management, response handling, and analytics.
Token Setup
-
Get your Fillout.io API Key:
- Log in to your Fillout.io account
- Go to Account Settings → API & Webhooks
- Click "Create new API Key"
- Copy your new API key
-
API Key Information:
- Production keys start with
fo_live_ - Test keys start with
fo_test_ - Test keys only work with test forms
- API keys provide access to all resources in your account
- Production keys start with
-
Replace
your-fillout-api-keyin the configuration with your API key.
⚠️ Security Notes:
- Keep your API key secure and private
- Use test keys for development
- Store keys in environment variables
- Rotate keys periodically
- Never commit keys to version control
Token Troubleshooting
Common Error Messages
-
"Invalid API key provided" or "Authentication failed"
- Cause: API key is missing, malformed, or invalid
- Solution:
- Verify key starts with
fo_live_orfo_test_ - Check for extra spaces or characters
- Ensure environment variable is set correctly
- Create a new key if necessary
- Verify key starts with
-
"Test mode key used with live form"
- Cause: Using test key (
fo_test_) with production form - Solution:
- Use live key for production forms
- Create test form for development
- Switch to appropriate key type
- Cause: Using test key (
-
"Rate limit exceeded"
- Cause: Too many API requests
- Solution:
- Implement request throttling
- Check usage in dashboard
- Optimize request patterns
Validation Steps
-
Check API Key Format:
# Key should: - Start with 'fo_live_' or 'fo_test_' - Be approximately 50 characters - Contain only letters, numbers, and underscores -
Test API Key:
curl -H "Authorization: Bearer your-api-key" \ https://api.fillout.com/v1/api/forms
Features
Form Management
- List all forms
- Get form details
- Create new forms
- Delete forms
- Update form settings
Response Handling
- Submit form responses
- Get form submissions
- Filter responses
- Export responses
Analytics
- Response rates
- Completion times
- Submission trends
Tools
-
list_forms- Get all accessible forms
- Parameters:
limit(optional): Number of forms to returnoffset(optional): Pagination offset
- Returns: Array of form objects
-
get_form- Get detailed form information
- Parameters:
formId(string): Form identifier
- Returns: Form details including questions and settings
-
create_form- Create a new form
- Parameters:
name(string): Form namedescription(optional string): Form descriptionquestions(array): Array of question objectstype: Question type (e.g., 'ShortAnswer', 'MultipleChoice')name: Question textrequired: Whether question is requiredchoices: Array of choices for multiple choice questions
- Returns: Created form object
-
get_form_responses- Get form submissions
- Parameters:
formId(string): Form identifierfilters(optional): Response filterspageSize(optional): Results per pageafterDate(optional): Filter by submission datebeforeDate(optional): Filter by submission datestatus(optional): Filter by completion status
- Returns: Array of form responses
-
submit_form_response- Submit a new response
- Parameters:
formId(string): Form identifierresponses(array): Array of answersquestionId: Question identifiervalue: Response value
calculations(optional): Custom calculations
- Returns: Submission confirmation
Setup
Usage with Claude Desktop
Docker Configuration
{
"mcpServers": {
"fillout": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"FILLOUT_API_KEY",
"mcp/fillout"
],
"env": {
"FILLOUT_API_KEY": "your-fillout-api-key"
}
}
}
}
NPX Configuration
{
"mcpServers": {
"fillout": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-fillout"
],
"env": {
"FILLOUT_API_KEY": "your-fillout-api-key"
}
}
}
}
Building
Prerequisites
- Node.js 18 or later
- npm or yarn
- Docker (optional)
Local Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build for production
npm run build
Docker Build
# Build image
docker build -t mcp/fillout .
# Run container
docker run -e FILLOUT_API_KEY=your-key mcp/fillout
Examples
Creating a Form
const form = await client.createForm({
name: "Customer Feedback",
description: "Please share your experience",
questions: [
{
type: "ShortAnswer",
name: "What did you like most?",
required: true
},
{
type: "MultipleChoice",
name: "Would you recommend us?",
required: true,
choices: ["Yes", "No", "Maybe"]
}
]
});
Submitting a Response
const response = await client.submitFormResponse(formId, {
responses: [
{
questionId: "q1",
value: "Great customer service!"
},
{
questionId: "q2",
value: "Yes"
}
]
});
Error Handling
The server provides detailed error messages for common issues:
try {
const forms = await client.listForms();
} catch (error) {
if (error instanceof AuthenticationError) {
// Handle invalid API key
} else if (error instanceof FilloutError) {
// Handle API-specific errors
} else {
// Handle unexpected errors
}
}
License
This project is licensed under the MIT License. See the LICENSE file for details.
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.