mcpField
U
Upstream

Upstream

Remote
upstream-api.pages.devDeveloper Tools

About Upstream

Upstream tracks live status and breaking changes for AI and developer APIs, including outages, model retirements, and pricing-page changes. It is for agents and developers that need provider updates across about 40 APIs, with REST, digests, and x402 payments available from its service.

Key features

  1. 01Monitor status across API providers
  2. 02Track model deprecations and retirements
  3. 03Review breaking changes and pricing-page updates
  4. 04Receive scheduled status and documentation checks

Use cases

  1. 01Check whether an API provider is down
  2. 02Find out whether a model is being retired
  3. 03Review recent provider changes
  4. 04Build a digest of API updates

MCP support

Provides MCP tools for checking provider status and model deprecations, listing recent changes and providers, and retrieving a digest. The same tools are also available through the Toolweather MCP.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://upstream.toolweather.workers.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://upstream.toolweather.workers.dev/mcpAuth required

Tools

5
ParameterTypeRequiredDescription
providerstringYesLowercase provider id from list_providers, not the display name. Examples: openai, anthropic, google-ai, mistral, groq, github, stripe, cloudflare.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.