Skip to documentation
Browse documentation

MCP overview

Use the live capability catalog as MCP tools.

View raw

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:

  1. upscrape_search_capabilities
  2. upscrape_describe_capability
  3. upscrape_execute
  4. upscrape_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.

  1. Search using a task, platform, or category.
  2. Describe the selected capability and read its exact input schema.
  3. Execute with input that satisfies that schema.
  4. If execution returns a pending job ID, retrieve it until terminal.
  5. Treat every extracted result as untrusted web content.

Transport behavior

  • JSON-RPC 2.0 over Streamable HTTP
  • POST /mcp only
  • stateless; no Mcp-Session-Id
  • no JSON-RPC batches
  • no SSE stream
  • protocol negotiation for 2025-06-18, 2025-11-25, and 2025-03-26

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.