English Français العربية

io.github.DesMartin01/inferenceindexer-mcp

Official registry E-commerce

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

Source code Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http inferenceindexer-mcp 'https://api.inferenceindexer.ai/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "inferenceindexer-mcp": {
            "type": "http",
            "url": "https://api.inferenceindexer.ai/mcp"
        }
    }
}
PYPI package inferenceindexer-mcp
Claude Code 
claude mcp add inferenceindexer-mcp -e 'II_API_BASE=<II_API_BASE>' -e 'II_API_KEY=<your ii_api_key>' -- uvx inferenceindexer-mcp==0.1.1
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "inferenceindexer-mcp": {
            "command": "uvx",
            "args": [
                "inferenceindexer-mcp==0.1.1"
            ],
            "env": {
                "II_API_BASE": "<II_API_BASE>",
                "II_API_KEY": "<your ii_api_key>"
            }
        }
    }
}

Environment variables

  • II_API_BASE Base URL of the InferenceIndexer API (defaults to the public API; no key required for the free tier)
  • II_API_KEY secret Optional InferenceIndexer API key (raises rate limits; free keys at https://www.inferenceindexer.ai/for-agents)

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. InferenceIndexer MCP Server
  2. Tools
  3. Config (env)
  4. Run
  5. Connect an agent / MCP client

InferenceIndexer MCP Server

Model Context Protocol server exposing InferenceIndexer's live + historical inference pricing as agent callable tools. Instead of an agent assembling inference pricing itself (slow, incomplete), it can call these tools to get complete pricing, historical trends, provider comparison, and the SIT index.

Tools

ToolDescription
recommend_modelsCall this first: rank models under your constraints (budget, context, ZDR, quality floor) with ready-to-call endpoint configs
explain_modelEverything about one model in one call: pricing, trend, endpoints, privacy flags
search_modelsSearch/list models with current pricing (by text, tier, sort)
get_modelFull detail + current price for one model
get_model_historyHistorical price trends for one model (the differentiator)
list_providersAll providers with model counts + price stats
get_providerDetail for one provider (models, tiers, price range)
get_composite_latestCurrent SIT-Composite index value + tier breakdown
get_composite_historySIT-Composite index history / trend
compare_providersPrice of one model across all providers that host it

Config (env)

  • II_API_BASE - InferenceIndexer API base (default https://api.inferenceindexer.ai)
  • II_API_KEY - Optional bearer key (public server works without one; a key raises rate limits)
  • II_SSR_SECRET - Optional first-party secret for self-hosted/higher-tier use only. Not set on the public server.

Run

stdio (recommended for local/agent-run):

uv sync
uv run inferenceindexer-mcp

Serve over HTTP/SSE (for remote clients, e.g. the hosted endpoint at https://api.inferenceindexer.ai/mcp):

uv run inferenceindexer-mcp --transport streamable-http --port 8899

Connect an agent / MCP client

Claude Desktop / generic MCP client (stdio):

{
  "mcpServers": {
    "inferenceindexer": {
      "command": "uvx",
      "args": ["inferenceindexer-mcp", "--transport", "stdio"]
    }
  }
}

Updated Oct 2026. Hosted (no install): https://api.inferenceindexer.ai/mcp - add "url": "https://api.inferenceindexer.ai/mcp" to mcpServers for streamable-http clients.

Frequently asked questions

What is io.github.DesMartin01/inferenceindexer-mcp?

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

How do I install io.github.DesMartin01/inferenceindexer-mcp?

It runs as a remote server. In Claude Code: claude mcp add --transport http inferenceindexer-mcp 'https://api.inferenceindexer.ai/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does io.github.DesMartin01/inferenceindexer-mcp need an API key?

Yes. It expects II_API_KEY, which you set in its configuration.

Is io.github.DesMartin01/inferenceindexer-mcp open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains io.github.DesMartin01/inferenceindexer-mcp?

It is published by DesMartin01. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.