INDIVIDUAL MCP TOOL

test_completion

Send one small chat completion to confirm the key and model work, and report what it cost.

inferenceapis.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://api.inferenceapis.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for test_completion and invoke it with your own arguments.

{}

Potential side effects detected · medium confidence · heuristic, not a guarantee.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.inferenceapis]
url = "https://api.inferenceapis.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "inferenceapis": {
      "type": "http",
      "url": "https://api.inferenceapis.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: inferenceapis
Remote MCP URL: https://api.inferenceapis.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "inferenceapis": {
      "url": "https://api.inferenceapis.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "inferenceapis": {
      "type": "http",
      "url": "https://api.inferenceapis.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "inferenceapis",
  "transport": "streamable-http",
  "url": "https://api.inferenceapis.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

signup — Create an Inference APIs account and API key for a person, without a browser.
list_models — List available models with prices (USD), context length, capabilities and aliases.
account — The account behind the key: email, current balance in USD, starter-credit and email-confirmation status, and where to add funds.
usage — Balance, spend today/this week/this month and over the last N days (default 7, max 90) by model, the account spend limit, and every key's limit, spend, pause/expiry status and allowed models.
create_api_key — Create an additional API key for the same account (for a second tool or machine), optionally with a spend limit, expiry and allowed models.
update_api_key — Change a key's spend limit, period, expiry, allowed models, or pause/resume it.
set_account_limits — Set the account-wide spend limit (caps every key together) and the low-balance email threshold.
docs — The plain-text documentation an agent needs: endpoints, models and prices, per-tool config blocks, limits, error codes.