MCP Server for LimeSurvey
Enables interaction with LimeSurvey API to create and manage surveys, questions, question groups, activate surveys, and export responses through standardized MCP endpoints.
README
MCP Server for LimeSurvey
This MCP server enables interaction with the LimeSurvey API while adhering to the Model Context Protocol specifications. It exposes core LimeSurvey functionality through standardized MCP endpoints.
Features
- 🚀 Survey creation
- ❓ Question and answer management
- 📋 Question group handling
- ✅ Survey activation
- 📊 Response exporting
- 🔍 List available surveys
Prerequisites
- Python 3.7+
- Access to a LimeSurvey instance (version 3.X+)
- LimeSurvey admin account
Installation
- Clone the repository:
git clone https://gitlab.com/mehdi_guiraud/mcp-limesurvey.git
cd mcp-limesurvey
- Configure environment variables:
cp .env.example .env
# Edit .env with your LimeSurvey credentials
nano .env
- Install dependencies:
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Starting the Server
./start_server.sh
The server will be available at http://localhost:8080
Integration with Claude Desktop
Step 1: Add the MCP Server in Claude Desktop
- Open Claude Desktop
- Navigate to Settings → Model Context Protocol
- Click Add Custom Server
- Provide server details:
- Server Name: LimeSurvey MCP
- Base URL:
http://localhost:8080/mcp - Specification URL:
http://localhost:8080/spec
Step 2: Usage with Claude Desktop
Interact with LimeSurvey directly from Claude Desktop using MCP syntax:
Create a new survey
{
"model": "limesurvey",
"action": "create_survey",
"parameters": {
"survey_title": "Customer Feedback",
"survey_language": "en"
}
}
Add a question
{
"model": "limesurvey",
"action": "add_question",
"parameters": {
"survey_id": 123456,
"group_id": 1,
"question_text": "How satisfied are you with our service?",
"question_type": "5",
"question_options": {
"subquestions": ["Very satisfied", "Satisfied", "Neutral", "Unsatisfied", "Very unsatisfied"]
}
}
}
Activate a survey
{
"model": "limesurvey",
"action": "activate_survey",
"parameters": {
"survey_id": 123456
}
}
Export responses
{
"model": "limesurvey",
"action": "export_responses",
"parameters": {
"survey_id": 123456,
"format": "json"
}
}
Available MCP Endpoints
| Action | Required Parameters | Description |
|---|---|---|
create_survey |
survey_title, survey_language |
Create a new survey |
add_question |
survey_id, group_id, question_text, question_type |
Add a question to a survey |
add_group |
survey_id, group_title, group_description |
Add a question group |
activate_survey |
survey_id |
Activate a survey |
list_surveys |
None | List all surveys |
export_responses |
survey_id |
Export survey responses |
Technical Specification
The server fully implements the MCP specification (2025-06-18). Access the complete specification at:
GET http://localhost:8080/spec
Security
- Authentication: Uses credentials stored in
.env - Validation: All requests are validated against the MCP schema
- Session Management: Automatically caches and recycles LimeSurvey sessions
Customization
To add new API methods:
- Add the endpoint in
config/config.yaml - Implement the method in
app/main.py - Update documentation in the
get_mcp_specfunction
Troubleshooting
- Ensure RPC API is enabled in LimeSurvey (
Configuration → Interfaces → Enable RPC API) - Verify correct credentials in
.env - Check server logs for detailed error messages
License
This project is licensed under MIT. See LICENSE for details.
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。