limesurvey
A MCP (Model Context Protocol) server for interacting with LimeSurvey.
claude mcp add --transport stdio edgarrmondragon-limesurvey-mcp uvx /path/to/limesurvey-mcp run main.py \ --env LIMESURVEY_URL="The URL of your LimeSurvey instance, e.g. https://myinstance.limequery.com/admin/remotecontrol" \ --env LIMESURVEY_PASSWORD="Your LimeSurvey password" \ --env LIMESURVEY_USERNAME="Your LimeSurvey username"
How to use
This MCP server provides a lightweight bridge to manage LimeSurvey surveys and responses via a MCP client. It exposes a Python-based runner (main.py) that communicates with your LimeSurvey instance using the remote control API. By running the server through the MCP client, you can orchestrate survey creation, question updates, and response retrieval as part of automated workflows. The included configuration requires three environment variables to connect to LimeSurvey: LIMESURVEY_URL, LIMESURVEY_USERNAME, and LIMESURVEY_PASSWORD. The MCP client launches the server using uvx, pointing to the directory containing the server and executing main.py.
With the MCP client, you can leverage standard MCP operations to start the server, pass runtime options, and integrate LimeSurvey management into your automation pipelines. Once running, you can issue commands through the client to perform tasks like creating surveys, listing surveys, or fetching responses, depending on what main.py implements for your LimeSurvey instance.
How to install
Prerequisites:
- Python installed on your system (and virtual environment support).
- MCP client tooling (uvx) installed and accessible in your PATH.
- Access to a LimeSurvey instance with RemoteControl API enabled and valid credentials.
Step-by-step installation:
- Install the MCP client runner (uvx) if you haven't already. This typically involves installing the uv tool globally or ensuring it is available in your development environment.
- Prepare your LimeSurvey credentials and endpoint:
- LIMESURVEY_URL: https://your-limesurvey-domain/admin/remotecontrol
- LIMESURVEY_USERNAME: your-limesurvey-username
- LIMESURVEY_PASSWORD: your-limesurvey-password
- Place the MCP server files in a directory, for example: /path/to/limesurvey-mcp
- Install any Python dependencies required by main.py (if a requirements.txt is provided). Example:
- python -m venv venv
- source venv/bin/activate (or venv\Scripts\activate on Windows)
- pip install -r requirements.txt (if present)
- Run the MCP server via the MCP client:
- uvx run /path/to/limesurvey-mcp main.py
- Verify the server is reachable through your MCP client and that the LimeSurvey credentials are accepted.
Additional notes
Tips and notes:
- Ensure LIMESURVEY_URL points to the LimeSurvey RemoteControl endpoint and is reachable from where the MCP server runs.
- Never expose LIMESURVEY_USERNAME and LIMESURVEY_PASSWORD in public repositories; use environment management or secret stores.
- If you encounter authentication failures, double-check that RemoteControl API is enabled in LimeSurvey and that the user has permission to access it.
- The mcpServers entry uses a placeholder path (/path/to/limesurvey-mcp) for the server directory; replace it with the actual path on your system.
- If you update main.py or dependencies, re-run the MCP server to apply changes.
- Consider enabling TLS/SSL on your LimeSurvey instance and ensuring the network path between the MCP host and LimeSurvey is secure.
Related MCP Servers
mcp-ical
A Model Context Protocol Server that allows you to interact with your MacOS Calendar through natural language.
mcp -odoo
A Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems through standardized resources and tools for data retrieval and manipulation.
oxylabs
Official Oxylabs MCP integration
LLaMa -Streamlit
AI assistant built with Streamlit, NVIDIA NIM (LLaMa 3.3:70B) / Ollama, and Model Control Protocol (MCP).
mcp_autogen_sse_stdio
This repository demonstrates how to use AutoGen to integrate local and remote MCP (Model Context Protocol) servers. It showcases a local math tool (math_server.py) using Stdio and a remote Apify tool (RAG Web Browser Actor) via SSE for tasks like arithmetic and web browsing.
knowledgebase
BioContextAI Knowledgebase MCP server for biomedical agentic AI