mcpbeat Sign in

Liquid Inference MCP Server

by liquidinference Your server? Claim it
answering

Liquid Inference is answering right now. Last checked 7 min ago.

Auction exchange for LLM inference: browse models and prices, preview and buy answers.

Uptime history 69 hours of history
69 hours agonow
100.0%
Uptime 24h
91 of 91 checks
—
Tools
hidden behind auth
494 ms
Response time
average over 24h
OAuth sign-in
Access
streamable-http

Nothing serious here today

Today is the operative word: we check Liquid Inference every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.

run in your terminal
claude mcp add liquid --transport http https://router.inference.ai.exchange/mcp
Settings → Connectors → Add custom connector, then paste this address
https://router.inference.ai.exchange/mcp
~/.codex/config.toml
[mcp_servers.liquid]
url = "https://router.inference.ai.exchange/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "liquid": {
      "url": "https://router.inference.ai.exchange/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "liquid": {
      "type": "http",
      "url": "https://router.inference.ai.exchange/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.

Endpoints

URLTransportStateLatencyChecked
https://router.inference.ai.exchange/mcp streamable-http sign-in 479 ms 7 min ago

Alternatives to Liquid Inference

same job, measured the same way
Inferenceindexer MCP
by desmartin01

AI inference pricing for agents: live and historical model prices, provider comparison.

113 installs/wk 10 tools answering
buy
by usebuy

Pay per request for APIs, compute, browsers, RPC and LLM inference with stablecoins on Celo.

326 installs/wk local only
Tabela FIPE
by mcp-dir

Reference vehicle prices in Brazil (FIPE table), cars, motorcycles and trucks. Browse by brand/model

13 tools answering
PrivateDAO Agent Exchange
by x-pact

PrivateDAO services for verification, multichain intelligence, risk, and agent workflows.

17 tools answering
ZebPay MCP Server
by zebpayrajesh

MCP server for ZebPay crypto exchange — fetch prices, balances, and manage orders

33 installs/wk local only
eBay Browse
by cunicopia-dev

eBay Browse API MCP server — buy-side listing search and price intelligence.

116 installs/wk local only
Cheap GPUs
by cheap-gpus

Live GPU rental and LLM inference prices across dozens of providers, plus GPU price forecasts.

7 tools answering
OrcaRouter
by continuum-ai-corp

Browse 160+ LLM models and live pricing — no API key needed for catalog. Add key to route chat.

115 installs/wk local only

Liquid Inference — questions

Answers built from our own checks of this server.

Why is there no tool list for Liquid Inference?
The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.
Is Liquid Inference working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 494 ms. The bar chart above shows every period we have measured.
How do I connect Liquid Inference?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to Liquid Inference?
No API key is involved. Liquid Inference answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
How fast is Liquid Inference?
It answers our handshake in 494 ms on average, which is faster than 24% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.