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.
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。