limesurvey-mcp-server
MCP server that exposes LimeSurvey's RemoteControl 2 JSON-RPC API as tools, enabling survey creation, activation, response export, and participant management through natural language.
README
limesurvey-mcp
MCP (Model Context Protocol) server for LimeSurvey 6's RemoteControl 2 JSON-RPC
API. It exposes one MCP tool per API method (import_survey, activate_survey,
list_surveys, export_responses, add_participants, etc.), plus a diagnostic tool,
limesurvey_connection_test.
This repository is the standalone server: it doesn't depend on any other project. If
you're looking for help getting a coding agent to generate .lss/.lsq/.lsg surveys
and upload them with this server, check out the
limesurvey-ai-boost skill, which is
complementary and consumes these same tools.
Features
- Automatic session handling: credentials come from your configuration; the session
key is obtained, cached, and renewed automatically. The MCP client never handles
sSessionKey. - Files by path: import methods (
import_survey,import_group,import_question,upload_file) acceptfile_path; export methods (export_responses,export_statistics, ...) acceptoutput_path. The server base64-encodes/decodes for you — it never dumps large files into the LLM's context. The same methods also accept base64 content sent directly over HTTP. - Actionable errors: API failures come back as
ERROR: ...text with the error code (ERR_NO_PERMISSION,ERR_INVALID_SURVEY, ...) instead of a stack trace. - Full coverage of the RemoteControl 2 API: surveys, groups, questions, languages, participants/tokens, responses, quotas, users.
Installation
Requires Python ≥3.10. pipx is recommended for installing it in an isolated environment without managing venvs by hand:
pipx install limesurvey-mcp
It also works with plain pip, inside your own virtual environment:
python3 -m venv .venv
source .venv/bin/activate # on Windows: .venv\Scripts\activate
pip install limesurvey-mcp
Both leave a limesurvey-mcp-server command available (on the PATH with pipx, or inside
the venv with pip).
Configuration
The server needs 3 required variables and a few optional ones. You can provide them in two ways:
Option A — direct environment variables (recommended if your MCP client injects them, see below):
LIMESURVEY_URL=https://your-server/index.php/admin/remotecontrol
LIMESURVEY_USERNAME=admin
LIMESURVEY_PASSWORD=change-this
Option B — a .env file. Copy the template and fill it in:
cp .env.example .env # or download it from the repo if you only installed the package
The server looks for .env in this order: LIMESURVEY_MCP_ENV_FILE (explicit path) →
$LIMESURVEY_MCP_HOME/.env → ~/.config/limesurvey-mcp/.env → ./.env in the directory
it's launched from. If none is found, it doesn't fail: it assumes the variables are
already present in the environment (Option A).
In LimeSurvey: Global settings → Interfaces → RemoteControl must be set to JSON-RPC (this server always uses JSON, never XML-RPC).
Available variables — see .env.example for details on each one
(LIMESURVEY_URL, LIMESURVEY_USERNAME, LIMESURVEY_PASSWORD, LIMESURVEY_AUTH_PLUGIN,
LIMESURVEY_TIMEOUT, LIMESURVEY_VERIFY_SSL).
Registering the server with your MCP client
stdio transport. Generic example (Claude Desktop, Claude Code, or any other MCP-compatible client):
{
"mcpServers": {
"limesurvey": {
"command": "limesurvey-mcp-server",
"env": {
"LIMESURVEY_URL": "https://your-server/index.php/admin/remotecontrol",
"LIMESURVEY_USERNAME": "admin",
"LIMESURVEY_PASSWORD": "change-this"
}
}
}
}
If you'd rather not put credentials directly in the client config, omit the env block
and use a .env file (Option B) — in that case, add LIMESURVEY_MCP_HOME pointing to
the folder where you placed the .env.
Verify the installation with the limesurvey_connection_test tool before operating: it
authenticates and returns the site name and how many surveys you can see.
Security
- The server operates against a real LimeSurvey instance.
delete_survey,delete_group,delete_question,delete_response,delete_participants, andactivate_surveyare destructive or hard to reverse. invite_participants,remind_participants, andmail_registered_participantssend real emails.- The
.envfile (if you use one) contains credentials: don't commit it to version control (.gitignorealready excludes it) or share it in plain text. - Prefer testing against a test instance/survey before pointing at production.
Local development
git clone https://github.com/pmanciniq/limesurvey-mcp-server.git
cd limesurvey-mcp-server
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
cp .env.example .env # and fill it in
limesurvey-mcp-server
License
MIT. See LICENSE.
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.