InferIndex MCP MCP server

An official MCP server provided by InferIndex that allows AI agents to query real-time LLM API pricing data. It enables users to find the cheapest providers for specific models, compare prices across vendors, view price history, and estimate costs for inference tasks using data aggregated from over 158 providers.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-05Operated by InferIndex

MCP endpoint (Streamable HTTP)

https://mcp.inferindex.dev/mcp

Vendor documentation

What you can do with it

Find the cheapest provider for a specific LLM model
Compare pricing gaps between different LLM providers
Estimate inference costs for a given model and token count
Retrieve historical price trends for LLM APIs

Tools advertised by the last live check:

search_models
cheapest
compare_providers
price_history
estimate_cost

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http inferindex-mcp https://mcp.inferindex.dev/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add inferindex-mcp --url https://mcp.inferindex.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable inferindex-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "inferindex-mcp": {
      "url": "https://mcp.inferindex.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "inferindex-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.inferindex.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start inferindex-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "inferindex-mcp": {
      "type": "http",
      "url": "https://mcp.inferindex.dev/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http inferindex-mcp https://mcp.inferindex.dev/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "inferindex-mcp": {
      "url": "https://mcp.inferindex.dev/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "inferindex-mcp": {
      "serverUrl": "https://mcp.inferindex.dev/mcp"
    }
  }
}

See all 782

Do you run InferIndex MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing