marcopolo.dev
MarcoPolo is an AI data runtime from Immersa that connects LLMs and agents to enterprise data sources through a secure, persistent workspace. It lets AI query and analyze data across databases, warehouses, cloud storage, and SaaS systems using the Model Context Protocol.
MarcoPolo exposes a remote streamable-HTTP MCP server at https://mcp.marcopolo.dev, authenticated either by OAuth sign-in or workspace API tokens; it also publishes a Python package `langchain-marcopolo` that uses the same API token.
- MarcoPolo MCP serverdiscovered
- langchain-marcopolo CLI / packagediscovered
Add the MarcoPolo MCP server URL https://mcp.marcopolo.dev in your MCP-capable client, then choose Connect in the client to start sign-in. The docs say you can establish identity with Google, Microsoft, GitHub, or your Email address; the first authentication also provisions your workspace automatically. See Getting Started and the homepage connection instructions.
Open the MarcoPolo app at mcp.marcopolo.dev/app, go to the Developer page, and click + Create Token. The Developer SDKs docs state these tokens are scoped to your workspace and can be used for MCP authentication or the Sandbox SDK. Store the value and provide it to your client as the API token; the LangChain example uses env var MARCOPOLO_API_TOKEN.
conventions · 1/8 published
- integrations.json✗
/.well-known/integrations.json - llms.txt✓https://marcopolo.dev/llms.txt
- API catalog✗
/.well-known/api-catalog - OpenAPI document✗
/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json - MCP server card✗
/.well-known/mcp/server-card.json - OAuth protected resource✗
/.well-known/oauth-protected-resource - Agent card✗
/.well-known/agent-card.json - Agent skills✗
/.well-known/agent-skills/index.json
Publish these signals → /publishing