Inferenceindexer MCP Server

by desmartin01 Your server? Claim it

answering

Inferenceindexer MCP is answering right now. Last checked 5 min ago. 388 installs a week from pypi. It exposes 10 tools. Last commit 2 Sep 2026.

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

Installs per day peak 249 · avg 29 · +605% w/w

a month agotoday

Uptime history 9 days of history

9 days agonow

100.0%

Uptime 24h

93 of 93 checks

Tools

read from the server

628 ms

Response time

average over 24h

388

Installs / week

npm and PyPI

What changed 2

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 2 September 2026. No other catalogue keeps this.

2 Sep 2 tools appeared explain_model, recommend_models

What the code does

We read the source, 17 h ago · tools taken from the live server · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Dumps the whole environment [пакет] test_mcp_integration.py:18

    env = dict(os.environ)

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add inferenceindexer-mcp --transport http https://api.inferenceindexer.ai/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "inferenceindexer-mcp": {
      "url": "https://api.inferenceindexer.ai/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.inferenceindexer-mcp]
url = "https://api.inferenceindexer.ai/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "inferenceindexer-mcp": {
      "url": "https://api.inferenceindexer.ai/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "inferenceindexer-mcp": {
      "url": "https://api.inferenceindexer.ai/mcp"
    }
  }
}

Available tools 10

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

composite

get_composite_history

Get SIT-Composite index history / trend over time. Args: days: History window in days (1-90, default 30). Returns: historical composite index values.

get_composite_latest

Get the current SIT-Composite index value + per-tier breakdown. The SIT-Composite is a usage-weighted mean of the top-50 models by token volume, reflecting what developers actually pay for inference.

model

get_model

Get full detail + current pricing for one model by its id. Args: model_id: Canonical model id, e.g. 'openai/gpt-5.6' or 'anthropic/claude-sonnet-5'. Returns: pricing, tier, SIT score, quality-adjusted price (Cost/IQ).

get_model_history

Get HISTORICAL price data / trends for one model. This is InferenceIndexer's differentiator: aggregators like OpenRouter expose only current price; this returns the price over time (input, output, blended $/M), enabling trend analysis. Args: model_id: Canonical model id, e.g. 'openai/gpt-5.6'. days: History window in days (1-365, default 30; plan-dependent). Returns: historical price series for the model.

compare

compare_providers

Compare the price of one model across the providers that host it. Args: model_id: Canonical model id, e.g. 'meta/muse-spark-1.1'. Returns: per-provider endpoints with pricing, showing where direct provider prices diverge (e.g. from OpenRouter's negotiated rate).

explain

explain_model

Get everything about one model in a single call: the full picture. Returns current pricing (input/output/blended, Cost/IQ, 24h/7d changes), a price-history summary with trend, all provider endpoints, the cheapest hand-verified endpoint with its native model id (for hot-swapping), privacy flags (ZDR/EU availability), and the AA intelligence score. Everything is as-of stamped. Args: model_id: Canonical model id, e.g. 'anthropic/claude-sonnet-5'. history_days: Price-history window (default 30, max 365). Returns: complete model profile with pricing, endpoints, privacy, quality.

models

search_models

Search and list AI inference models with current pricing. Args: query: Text search on model id/name (optional). tier: Filter by tier: frontier | standard | budget | micro | zdr | eu (optional). limit: Max results (1-100, default 25). sort: Sort key, e.g. 'blended' (price), 'sit' (SIT score) (optional). Returns: models with input/output/blended $/M pricing, provider, tier.

provider

get_provider

Get detail for one provider: models, tier breakdown, price range. Args: provider_name: Provider name, e.g. 'DeepInfra', 'Novita', 'Venice'. Returns: provider detail with model list and pricing.

providers

list_providers

List all inference providers with model counts and price stats.

recommend

recommend_models

Recommend the best-value AI models for given constraints, ranked with receipts. The core answer endpoint: give it constraints and it returns the top models ranked by Cost/IQ (quality-adjusted price, lower is better), each with a plain-English 'why', a hot-swap endpoint_config (provider base_url + native model id, ready to call), as-of timestamps, and runner-ups. Args: budget_max_usd_per_m: Max blended price $/M (optional). context_min: Minimum context window in tokens (optional). modality: 'text' (default), 'vision', or 'any'. zdr: Require zero-data-retention providers (optional). eu_sovereign: Require EU-sovereign providers (optional). reasoning: Filter reasoning models (null = any, true/false). limit: Max recommendations (1-20, default 5). Returns: ranked recommendations with endpoint_config and ranking evidence.

Endpoints

URL	Transport	State	Latency	Checked
https://api.inferenceindexer.ai/mcp	streamable-http	answering	651 ms	5 min ago

Alternatives to Inferenceindexer MCP

same job, measured the same way

Market Intel MCP

by datakoot

Live & historical FX rates and currency conversion for AI agents. No API keys.

5 tools answering

Volthq

by newageflyfish-max

Compute price oracle for AI agents — compare pricing across 8 providers in real time.

88 installs/wk local only

Compute Finance Oracle

by compute-finance

Live AI compute pricing oracle — real-time LLM model prices across providers

75 installs/wk local only

Stocksense

by mikejj-creation

Financial data for AI agents: SEC filings, price history, insider trades, and more.

34 installs/wk local only

Blue Pillow Hotels & Stays

by bluepillow

Neutral hotel & stay price comparison for AI agents: live prices from 16+ booking sites. No signup.

6 tools answering

Espn

by christianclaudio

Model Context Protocol server for live & historical sports stats and odds via ESPN.

1 029 installs/wk local only

Promptibus MCP

by promptibus

Model intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.

132 installs/wk local only

Rival

by nuance-dev

Query AI model benchmarks, pricing, and comparisons from rival.tips

26 installs/wk local only

Inferenceindexer MCP — questions

Answers built from our own checks of this server.

What can Inferenceindexer MCP do?

It exposes 10 tools, read directly from the server on our last check. Among them: compare_providers, explain_model, get_composite_history, get_composite_latest, get_model, get_model_history and 4 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

What is Inferenceindexer MCP mostly used for?

Its tools cluster around composite and model. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is Inferenceindexer MCP working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 93 of 93 checks got a reply (100.0%), average response time 628 ms. The bar chart above shows every period we have measured.

How do I connect Inferenceindexer MCP?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Inferenceindexer MCP need an API key?

No. Inferenceindexer MCP completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 10 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Inferenceindexer MCP?

It answers our handshake in 628 ms on average, which is faster than 23% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use Inferenceindexer MCP?

The pypi package inferenceindexer-mcp was installed 388 times in the last week. Week over week that is +605%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Inferenceindexer MCP open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.