MCP.Market

Inference MCP server

online · 100% uptime
by BSVKey·io.github.BSVKey/inference-mcp·v1.3.6

Pay-per-token Claude & Grok inference, settled in Bitcoin BSV. npm package or hosted remote.

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

not scanned yet

Adoption
Growing

0 stars104 downloads/wk

Reviews

Write one

Nobody has reviewed Inference yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Inference tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Not scanned yet. New listings are scanned within a day or two of arriving.

How Inference compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,243 servers
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
1,631 ms
faster than 5% of 30,027 servers
Downloads a week
104
more than 63% of 12,306 servers with a package

Release history: 6 versions in the registry since 2026-09-09, latest 2026-10-30, typically one every 13 days.

Install Inference in Claude Code, Cursor or VS Code

claude mcp add --transport http inference-mcp https://inference.bsvkey.com/mcp
Add to Cursor

What the publisher says

From the Inference repository's README, as published. We do not edit it. Read it on GitHub

@bsvkey/inference-mcp

An MCP server that lets any agent buy Claude & Grok inference metered per token, settled in BSV, through the hosted gateway at inference.bsvkey.com. Zero dependencies (Node ≥ 18, uses global fetch). It's a thin HTTP client — it never holds your keys or runs models; every call is billed through the gateway.

Tools: listmodels, infer, channelbalance, openchannel, x402infer.

Two ways to pay: a prepaid channel (infer, fund once, draw down per token) or per call via x402 (x402infer — no channel; the agent pays each request in BSV with its own key). x402infer needs a funded WIF (wif arg or BSVKEY_WIF) and the optional @bsvkey/x402-bsv-client + @bsv/sdk packages (installed with this one).

Verifiable metering. Each infer call returns a signed usage receipt, and the tool auto-verifies it offline (with the optional packages installed): the result includes receiptVerified and meterVerified (true, false + receiptCheck, or null). It recovers the broker key (pinned from GET /v1/receipt-key); binds the receipt to the channel you called (from your API key, not the receipt's self-report); checks a monotonic sequence (no replay/gap) and running totals within the funded amount; recomputes the charge from the published rate (you can never be overcharged); and recomputes the token count from the exact bytes of your messages and the completion, under the pinned bsvkey-meter/1 tokenizer. So the channel payment is on-chain and both the meter and the charge are auditable, without trusting the broker's word.

Four things an unattended client should know:

is null (unknown), never true — a down pin weakens the check to unknown, not to trusted.

  • Fails closed. If the pinned-key endpoint is unreachable, receiptVerified

to the amount you funded on-chain. The receipt's own fundedSats is the broker's assertion; when you supply yours, a receipt claiming a different amount is rejected and totals are checked against what you actually paid.

  • Supply your funded amount. Set BSVKEYFUNDEDSATS (or pass fundedSats)

replay before the first receipt this process sees would be invisible). Set BSVKEYRECEIPTSTATE to a file path to persist per-channel seq/totals so replays are caught across restarts.

  • Persist across restarts. Sequence continuity is in-memory by default (a

lag the signed receipt by ~20s; trust the receipt, treat the endpoint as a cache.

  • The receipt is the ledger. The GET /v1/channels/:id balance endpoint can

Spec: https://inference.bsvkey.com/usage-receipts.md

Quick start

load a key in-page). Copy the key it returns: channelId:channelSecret.

  1. Fund a channel once at https://inference.bsvkey.com (BRC-100 wallet, or

BSVKEYAPIKEY.

  1. Add the MCP server to your agent host (below), with that key in
  1. Ask your agent to run inference — it calls infer and pays per token.

listmodels and openchannel work with no key; infer and channel_balance need a funded channel key.

Install

Published on npm as @bsvkey/inference-mcp.

Claude Code

claude mcp add bsvkey-inference \
  --env BSVKEY_API_KEY=channelId:channelSecret \
  -- npx -y @bsvkey/inference-mcp

Claude Desktop / Codex / any MCP host (JSON config)

{
  "mcpServers": {
    "bsvkey-inference": {
      "command": "npx",
      "args": ["-y", "@bsvkey/inference-mcp"],
      "env": { "BSVKEY_API_KEY": "channelId:channelSecret" }
    }
  }
}

No npm? Grab the single-file server directly (https://inference.bsvkey.com/mcp/server.js) and use "command": "node", "args": ["server.js"].

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Inference: common questions

Is Inference MCP server safe?
Mostly: it is graded B (82/100). Read the Inference safety report
How do I install Inference?
It runs remotely at inference.bsvkey.com. 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 Inference need an API key?
Yes. The registry entry asks for BSVKEY_API_KEY, BSVKEY_WIF, Authorization.
Is Inference maintained?
The last commit was 23 days ago (2026-10-13). The latest release is v1.3.6.
Is Inference up?
100% of our last 15 checks got an answer. We check remote servers about four times a day.
How does Inference compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,243 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 1,631 ms (faster than 5% of 30,027 servers). Full comparison.