MCP server · Marco Polo

MarcoPolo MCP Server

MarcoPolo is an MCP-first enterprise AI data platform. Its product surface IS a hosted, remote MCP server that lets any MCP client (Claude, ChatGPT, Cursor, Codex, or a custom agent) connect governed enterprise data sources into a sandboxed workspace, run queries, and cache results in DuckDB - "without the leaks." Operated by Immersa.

Open endpoint → Marco Polo provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Marco Polo Type: Hosted endpoint Transport: streamable-http Host: mcp.marcopolo.dev

Endpoint

https://mcp.marcopolo.dev

Hosted endpoint · transport streamable-http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "marco-polo": { "url": "https://mcp.marcopolo.dev" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "marco-polo": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.marcopolo.dev"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://mcp.marcopolo.dev \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

install_demo_connection — Deploy demo datasets so a client can begin querying immediately.
connection_list — Enumerate the data-source connections available to the workspace.
connection_describe — Inspect a connection's table/schema metadata.
connection_query — Execute a query file against a data source; full result cached in DuckDB.
workspace_shell — Run CLI commands within the sandboxed workspace.
connection_setup — Generate a secure credential-configuration link for a new connection.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.