What data sources does this server use?
It uses Statistics Canada’s public Web Data Service (WDS) and SDMX REST API. No API key or authentication is required.
@Aryan-Jhaveri
基本信息
MCP server + CLI for Statistics Canada (StatCan) — access 7,000+ Canadian statistical tables via WDS and SDMX REST APIs
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-statcan": {
"command": "uv",
"args": [
"pip",
"install",
"fastmcp",
"httpx",
"pydantic"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
This MCP server and CLI provides structured access to Statistics Canada’s Web Data Service (WDS) and SDMX REST API. It enables any MCP client — Claude, Cursor, VS Code Copilot, Gemini — to search, retrieve, and analyze Canadian statistical data. The included statcan CLI allows direct downloads without an LLM.
Choose one of four options: Hosted (connect to https://mcp-statcan.onrender.com/mcp with no install), Self-host HTTP (run uvx statcan-mcp-server --transport http locally), Full local (stdio with optional SQLite storage), or the statcan CLI (run commands like statcan search "labour force"). Configuration snippets for Claude Desktop, Claude Code, Cursor, and VS Code are provided.
statcan CLI for terminal‑based data downloadsIt uses Statistics Canada’s public Web Data Service (WDS) and SDMX REST API. No API key or authentication is required.
No. The hosted server on Render works immediately; just point your MCP client to `https://mcp-statcan.onrender.com/mcp`.
Yes. The `statcan` CLI lets you search, download, and inspect tables directly from a terminal. Install via `pip install statcan-mcp-server` or run with `uvx`.
Any MCP‑compatible client: Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), and Gemini.
On the hosted server, data is returned as a download URL rather than inline payload, keeping context windows small. The CLI outputs CSV/JSON to stdout.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
评论