Upstream MCP server

• check_api_statusFree

  Check if an AI or developer API provider (OpenAI, Anthropic, Gemini, Mistral, Groq, GitHub, Stripe, Cloudflare, Vercel, Supabase, Twilio... ~40 total) is up, degraded or down right now. Use BEFORE calling a provider's API, or right after you get 5xx/429/timeout errors, to decide whether to retry, wait or switch to a fallback. Returns a one-line summary first, then verdict, recommended_action, open incidents, affected components, checked_at and freshness (checked every ~4 min). Example: {"provider":"openai"}. Free within the daily quota, then $0.003 via x402. Alias: get_status.

• check_model_deprecationFree

  Check if an LLM model id is active, deprecated or retired, its shutdown date, and the recommended replacement, from the provider's own deprecation page (OpenAI, Anthropic, Google, etc.). Use before hard-coding or calling a model, or when a model call fails with "model not found / deprecated". Returns summary first, then verdict, recommended_action (keep_using | plan_migration | switch_now | verify_with_provider), replacement, shutdown_date, evidence rows and freshness. Example: {"model":"gpt-4-0613"}. Free within the daily quota, then $0.003 via x402. Alias: get_model (param "id").

• get_digestFree

  Daily digest (free) of AI/dev API incidents, model deprecations/retirements, pricing-page changes and breaking MCP server changes. Use for a once-a-day catch-up instead of polling. Example: {} for the latest, or {"date":"2026-10-14"}.

• list_providersFree

  List the ~40 AI and developer API providers Upstream tracks with their current state (operational/degraded/outage) and checked_at. Use to find the right provider id for check_api_status, or for a quick all-providers health overview. Free.

• list_recent_api_changesFree

  List recent breaking or notable changes across AI and developer APIs: outages and recoveries, deprecation-page edits, model retirements and pricing-page edits. Use to answer "did anything change that could break my integration?" or to explain sudden errors. Returns summary first, then the change list with timestamps and source links. Example: {"provider":"anthropic","kind":"model_retirement"}. Free within the daily quota, then $0.01 via x402. Alias: get_changes.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 720ms20/20
• Tool poisoning5 tool descriptions checked15/15
• Auth qualityAPI key sent as a header8/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner6/10

Safety score

85/100

higher than 73% of 4,460 AI and agents servers

Tools

5

the typical AI and agents server has 6

Tools that change things

0%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote AI and agents server answers 100%

Response time

142 ms

faster than 78% of 2,331 AI and agents servers

Upstream: common questions

Is Upstream MCP server safe?

Yes, by our scan: it is graded A (85/100). Read the Upstream safety report

How do I install Upstream?

It runs remotely at upstream.toolweather.workers.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Upstream need an API key?

Yes. The registry entry asks for X-API-Key.

Is Upstream maintained?

The last commit was 20 days ago (2026-10-15). The latest release is v0.2.0.

Is Upstream up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of Upstream?

Servers from other publishers that do the same job: Watch Skill MCP server, WaveSpeed MCP server and Godot MCP server.

How does Upstream compare with other AI and agents MCP servers?

safety score 85/100 (higher than 73% of 4,460 AI and agents servers); tools 5 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.