The Wunder Mobility API MCP server brings the full API documentation — every guide, every endpoint, every request/response schema — directly into your AI coding assistant.
Instead of switching between your editor and the docs, you can ask your assistant questions like:
“What endpoints do I need to build a payment flow for my users?” “Show me the full spec for creating a booking.” “How does vehicle discovery work in the User API?”
…and get back ranked, cited answers with links to the relevant documentation.
Works with Claude Code, Cursor, Windsurf, and any other MCP-compatible client.
uvx runs the package directly from PyPI — no cloning, no Python environment setup.
Install uv first if you don’t have it:
curl -LsSf https://astral.sh/uv/install.sh | sh # macOS / Linux
brew install uv # macOS via Homebrew
winget install astral-sh.uv # Windows
Claude Code:
claude mcp add wunder-api uvx wunder-mobility-mcp
Cursor — add to your MCP settings (~/.cursor/mcp.json or via Settings → MCP):
{
"mcpServers": {
"wunder-api": {
"command": "uvx",
"args": ["wunder-mobility-mcp"]
}
}
}
Windsurf — add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"wunder-api": {
"command": "uvx",
"args": ["wunder-mobility-mcp"]
}
}
}
On first start the server fetches the latest docs from GitHub (~5–10 seconds) and caches them locally. Every subsequent start is instant.
Once connected, open your assistant and try:
You should see the assistant calling the tools and returning results with documentation links.
The MCP server exposes four tools your assistant uses automatically:
| Tool | What it does |
|---|---|
search_api_docs(query) |
Full-text search across all guides and OpenAPI specs. |
list_endpoints(api, tag?) |
Browse endpoints by API namespace and tag. |
get_endpoint_spec(operation_id) |
Returns the full OpenAPI operation object for one endpoint. |
get_guide(slug) |
Returns the full markdown content of a documentation guide. |
wunder-mobility-mcpWunder-Mobility/public-api-mcp