InferCPI MCP server

Q: How do I add InferCPI MCP to Claude Code?

Run `claude mcp add --transport http api https://infercpi.com/mcp` in your terminal. Add `--scope user` to make it available in every project.

Q: How do I add InferCPI MCP to Cursor?

Open `~/.cursor/mcp.json` and add the server under `mcpServers`, using the Cursor config shown in the install section above.

Commit Oct 29, 2026

infer-cpi/api · python

Provides AI agents with real-time data on inference costs, model pricing, speed benchmarks, and capability indices.

Also known as Infer-CPI/api, api

remote Finance & Market Data AI & LLM Tools No API key

Install GitHub ↗

Stars: 0
Tools: —
Downloads, 30 days: —
Latest version: 1.0.0
Last commit: Oct 29, 2026
License: —

What is InferCPI MCP?

InferCPI provides AI agents with real-time data on inference costs, model pricing, speed benchmarks, and capability indices.

Summary generated from the project's README

About InferCPI MCP server

Equipping AI agents with real-time intelligence on inference costs and model performance is the primary function of InferCPI. Developers and researchers can use this server to access data regarding model pricing, speed benchmarks, and capability indices. It provides insights into what buyers actually pay, comparing open versus closed models, third-party hosting, and self-hosting options.

Users can connect to the server via a hosted HTTP endpoint that requires no API keys, or they can run the Python script locally using Claude Desktop or Claude Code. The server provides ten read-only tools, including model_price, speed, events, and cost_per_task, to query specific datasets. These tools pull from various sources such as SEC filings, LiteLLM, and the Epoch AI Capabilities Index to deliver information on tokens per second, time to first token, and hyperscaler capex.

What you can do with it

1Compare model pricingAsk an agent to find the input, output, and blended cost per million tokens for specific models.
2Analyze inference speedRequest data on how fast different models generate tokens to optimize latency.
3Track market changesHave an AI monitor recent model launches, price increases, or removals.
4Evaluate hosting strategiesCompare the financial implications of using third-party hosts versus self-hosting.

Written from the project's README. Every use case is checked against a quote from it.

How to install InferCPI MCP

Formats verified 10 Nov 2026Add to Cursor Add to Goose

Claude CodeCursorVS CodeVS Code CLICodexCodex config.tomlGemini CLIGemini settings.json

$ claude mcp add --transport http api https://infercpi.com/mcp

~/.cursor/mcp.json

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

.vscode/mcp.json

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

$ code --add-mcp '{"name":"api","type":"http","url":"https://infercpi.com/mcp"}'

$ codex mcp add api --url https://infercpi.com/mcp

~/.codex/config.toml

[mcp_servers.api]
url = "https://infercpi.com/mcp"

$ gemini mcp add -s user --transport http api https://infercpi.com/mcp

~/.gemini/settings.json

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

No environment variables or API keys required.Setup guides:Claude Code Cursor VS Code Claude Desktop

Automated checks

Ran Nov 15, 2026Full report →

58/100

Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points

Show this score in your README

Source repository linked and reachableinfer-cpi/api is public and reachablegithub.com/infer-cpi/api ↗Pass
Package names this repository as its sourceNot checked
Build provenance (Sigstore attestation)Not checked
Open source license (OSI)No licenseFinding
Commit or release in the last yearLast commit or release 2026-10-29github.com/infer-cpi/api ↗Pass
OpenSSF ScorecardNot checked
Package name not close to a popular packageNot checked
No critical advisory in the package or its dependenciesNot checked
No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
Destructive tools are labelledNot checked
Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 128 msPass

README

View on GitHub

InferCPI API

InferCPI tracks what AI inference costs: list prices, what buyers actually pay, the cost of a fixed level of capability, open vs closed models, third-party hosts, self-hosting, and cost per completed task. Site: https://infercpi.com.

This repo holds the public API docs, examples and the MCP server. The data is free, needs no key, and is licensed CC BY 4.0: cite as InferCPI, infercpi.com.

API

Static JSON at https://infercpi.com/v1/. Full reference: https://infercpi.com/api.html.

File	What
`latest.json`	Last value of every series, plus the weekly editorial note
`index.json`	Catalogue of every series: point count, dates, method string, URL
`series/<signal>/<key>.json`	Full history: `points: [[unix_ts, value], ...]` and `method`
`basket.json`	Every model priced this week: input, output and blended $/1M, context, Epoch ECI, open or closed
`events.json`	Launches, price cuts, increases and removals since Sep 2023
`speed.json`	Our daily speed run: time to first token, tokens per second
`token_mix.json`	Tokens routed through OpenRouter per week, by lab and region
`capex.json`	Hyperscaler capex, chip and cloud revenue by quarter (SEC filings)

curl -s https://infercpi.com/v1/latest.json | jq '.latest["weighted_index/paid_usd_1m"]'

MCP server

mcp_server.py gives agents ten read-only tools over the API: index_latest, index_series, index_catalogue, basket, model_price, events, speed, open_vs_closed, self_hosting, cost_per_task.

Hosted, no key: https://infercpi.com/mcp (streamable HTTP).

claude mcp add --transport http infercpi https://infercpi.com/mcp   # Claude Code

Claude.ai and Claude Desktop: Settings → Connectors → Add custom connector, paste the URL.

Or run it yourself:

mkdir -p ~/.local/share/infercpi
curl -so ~/.local/share/infercpi/mcp_server.py https://raw.githubusercontent.com/Infer-CPI/api/main/mcp_server.py
pip install mcp                                       # mcp 1.x or 2.x both work
claude mcp add infercpi -s user -- python3 ~/.local/share/infercpi/mcp_server.py   # Claude Code
python3 ~/.local/share/infercpi/mcp_server.py --http  # or: streamable HTTP on :8765

Claude Desktop (claude_desktop_config.json):

{ "mcpServers": { "infercpi": { "command": "python3", "args": ["/home/YOU/.local/share/infercpi/mcp_server.py"] } } }

It reads https://infercpi.com by default; set INFERCPI_BASE to point elsewhere.

Method and sources

How every series is built: https://infercpi.com/methodology.html. Inputs: LiteLLM and pydantic/genai-prices (MIT), Epoch AI Capabilities Index (CC BY 4.0), OpenRouter rankings (CC BY 4.0), SEC filings (public domain). Speed and cost per task are our own measurements.

Licence

Code in this repo: MIT. Index data: CC BY 4.0. Questions, corrections or a series you need: open an issue.

Read full README

InferCPI MCP questions

How do I add InferCPI MCP to Claude Code?

Run claude mcp add --transport http api https://infercpi.com/mcp in your terminal. Add --scope user to make it available in every project.

How do I add InferCPI MCP to Cursor?

Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.

Does using the InferCPI API require an API key?

No, the data is free and does not require an API key.

How can I run the MCP server locally?

You can download the mcp_server.py script, install the mcp library, and run it using python3.

Facts

Nov 15, 2026

Stars: 0
Downloads, 30 days: —
Latest version: 1.0.0
Last commit: Oct 29, 2026
License: —
Transport: remote
Package: —

Infer-CPI ↗

Community publisher

Published by an independent maintainer.

Alternatives

Works with

Claude Code Cursor VS Code Claude Desktop Codex Gemini CLI Windsurf Devin

Badge for your README

Show your HostedMCP checks score. The badge links readers to install instructions for every client.

[![HostedMCP checks](https://api.hostedmcp.org/v1/badge/server/infer-cpi/api.svg)](https://hostedmcp.org/servers/infer-cpi/api/checks)

Maintainer?

Claim this listing to edit it and add the HostedMCP badge to your README.

Claim listing

Before you install

Servers run with the permissions you give them. Use the narrowest token or database role that does the job.

About InferCPI MCP server

What you can do with it

1Compare model pricingAsk an agent to find the input, output, and blended cost per million tokens for specific models.
2Analyze inference speedRequest data on how fast different models generate tokens to optimize latency.
3Track market changesHave an AI monitor recent model launches, price increases, or removals.
4Evaluate hosting strategiesCompare the financial implications of using third-party hosts versus self-hosting.

Written from the project's README. Every use case is checked against a quote from it.

File

What

latest.json

Last value of every series, plus the weekly editorial note

index.json

Catalogue of every series: point count, dates, method string, URL

series/<signal>/<key>.json

Full history: points: [[unix_ts, value], ...] and method

basket.json

Every model priced this week: input, output and blended $/1M, context, Epoch ECI, open or closed

events.json

Launches, price cuts, increases and removals since Sep 2023

speed.json

Our daily speed run: time to first token, tokens per second

token_mix.json

Tokens routed through OpenRouter per week, by lab and region

capex.json

Hyperscaler capex, chip and cloud revenue by quarter (SEC filings)

mkdir -p ~/.local/share/infercpi curl -so ~/.local/share/infercpi/mcp_server.py https://raw.githubusercontent.com/Infer-CPI/api/main/mcp_server.py pip install mcp # mcp 1.x or 2.x both work claude mcp add infercpi -s user -- python3 ~/.local/share/infercpi/mcp_server.py # Claude Code python3 ~/.local/share/infercpi/mcp_server.py --http # or: streamable HTTP on :8765

InferCPI MCP questions

How do I add InferCPI MCP to Claude Code?

Run claude mcp add --transport http api https://infercpi.com/mcp in your terminal. Add --scope user to make it available in every project.

How do I add InferCPI MCP to Cursor?

Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.

Does using the InferCPI API require an API key?

No, the data is free and does not require an API key.

How can I run the MCP server locally?

You can download the mcp_server.py script, install the mcp library, and run it using python3.

InferCPI MCP server

What is InferCPI MCP?

About InferCPI MCP server

What you can do with it

How to install InferCPI MCP

Install InferCPI MCP in Claude Code

Install InferCPI MCP in Cursor

Install InferCPI MCP in VS Code

Install InferCPI MCP in VS Code CLI

Install InferCPI MCP in Codex

Install InferCPI MCP in Codex config.toml

Install InferCPI MCP in Gemini CLI

Install InferCPI MCP in Gemini settings.json

Automated checks

README

InferCPI API

API

MCP server

Method and sources

Licence

InferCPI MCP questions

InferCPI MCP server

What is InferCPI MCP?

About InferCPI MCP server

What you can do with it

How to install InferCPI MCP

Install InferCPI MCP in Claude Code

Install InferCPI MCP in Cursor

Install InferCPI MCP in VS Code

Install InferCPI MCP in VS Code CLI

Install InferCPI MCP in Codex

Install InferCPI MCP in Codex config.toml

Install InferCPI MCP in Gemini CLI

Install InferCPI MCP in Gemini settings.json

Automated checks

README

InferCPI API

API

MCP server

Method and sources

Licence

InferCPI MCP questions