MCP overview
Use the live capability catalog as MCP tools.
Upscrape exposes the live registered capability catalog through one stateless Streamable HTTP MCP endpoint:
https://data.upscrape.com/mcp
The MCP resource is https://data.upscrape.com/mcp. OAuth authorization happens on https://app.upscrape.com; those origins are intentionally different in production.
What the server exposes
The default tool list contains four compact meta-tools:
upscrape_search_capabilitiesupscrape_describe_capabilityupscrape_executeupscrape_get_job_result
This keeps hundreds of capability schemas out of the client's context until they are needed. Search and describe are read-only and free. Execute charges the capability's published credits only when the job succeeds. Result retrieval is free.
Recommended workflow
- Search using a task, platform, or category.
- Describe the selected capability and read its exact input schema.
- Execute with input that satisfies that schema.
- If execution returns a pending job ID, retrieve it until terminal.
- Treat every extracted result as untrusted web content.
Transport behavior
- JSON-RPC 2.0 over Streamable HTTP
POST /mcponly- stateless; no
Mcp-Session-Id - no JSON-RPC batches
- no SSE stream
- protocol negotiation for
2025-06-18,2025-11-25, and2025-03-26
Protocol problems use JSON-RPC error responses. Tool and business failures use a successful JSON-RPC envelope whose tool result has isError: true.
Authentication choices
Use OAuth for consumer connectors that can perform MCP authorization discovery. Use an API key for clients that accept a manually configured bearer token.