Inference MCP is answering right now. Last checked 14 min ago. 207 installs a week from npm. It exposes 6 tools. Last commit 30 Oct 2026.
Pay-per-token Claude & Grok inference, settled in Bitcoin BSV. npm package or hosted remote.
Today is the operative word: we check Inference MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add inference-mcp --transport http https://inference.bsvkey.com/mcp
https://inference.bsvkey.com/mcp
[mcp_servers.inference-mcp]
url = "https://inference.bsvkey.com/mcp"
{
"mcpServers": {
"inference-mcp": {
"url": "https://inference.bsvkey.com/mcp"
}
}
}
{
"servers": {
"inference-mcp": {
"type": "http",
"url": "https://inference.bsvkey.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
channel_balance
infer
list_models
open_channel
x402_infer
xrp_infer
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://inference.bsvkey.com/mcp | streamable-http | answering | 498 ms | 14 min ago |
Spot market for AI inference tokens. Buyers pay per draw in USDC on Base; sellers host delivery.
AI inference price index: token prices, cost per capability, open vs closed, hosts, cost per task.
Hosted Google Ads MCP for Claude and ChatGPT. Preview every write. No developer token.
GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.
Price a Claude, GPT, Gemini or Grok call before you send it. Runs locally.
Curated, on-demand memory for AI coding agents. Cuts Claude Code token cost per session.
Cross-AI personal memory. Save once in ChatGPT, recall in Claude, Mistral, Grok, or any MCP client.
run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.
Answers built from our own checks of this server.