MCP Server

The LLM Stats MCP server gives AI agents access to the model catalog, benchmark scores, rankings, and pricing over the Model Context Protocol. One workflow tool (compare-run) also runs prompts through the inference gateway and returns latency, tokens, and cost per model. The server is hosted and read-only over the Stats API. Cursor, Claude Code, Claude Desktop, Continue, and ChatGPT Apps connect directly.

Quota

MCP tool calls are Stats API requests. Each successful data result draws from your organization’s daily quota — the same pool your REST API keys use — and counts toward the organization burst limit. Official MCP connections (OAuth sign-in) are identified server-side as mcp traffic in your usage reports; you do not need to send the X-LLM-Stats-Client header. Workflow tools such as compare-models chain several API calls and consume one data response per underlying call. See Plans and quotas for limits and counting rules.

Organization-level quota enforcement is planned. Until it ships, MCP calls are subject to the same route limits as REST calls. See the changelog.

Setup

Point your MCP client at the hosted server. No installation required.

Connect with OAuth (recommended)

On first connect, your MCP client opens a browser sign-in with Google or GitHub. You do not need to copy an API key into client config — the server brokers access behind the scenes.

Cursor
Claude Code
Claude Desktop
Continue
Other clients

Add this to your Cursor MCP settings (.cursor/mcp.json):

{
  "mcpServers": {
    "llm-stats": {
      "url": "https://mcp.llm-stats.com/mcp"
    }
  }
}

claude mcp add llm-stats --transport http https://mcp.llm-stats.com/mcp

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "llm-stats": {
      "url": "https://mcp.llm-stats.com/mcp"
    }
  }
}

Add this to your Continue config.json:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "name": "llm-stats",
        "url": "https://mcp.llm-stats.com/mcp"
      }
    ]
  }
}

Any client that supports MCP OAuth works. Set the server URL to https://mcp.llm-stats.com/mcp and complete browser sign-in on first connect.

Legacy: API key

If your client does not support OAuth, pass a Stats API key in the Authorization header. Keys must use the sk_ze_ prefix.

Add this to your Cursor MCP settings (.cursor/mcp.json):

{
  "mcpServers": {
    "llm-stats": {
      "url": "https://mcp.llm-stats.com/mcp",
      "headers": {
        "Authorization": "Bearer sk_ze_<your-api-key>"
      }
    }
  }
}

claude mcp add llm-stats --transport http https://mcp.llm-stats.com/mcp \
  --header "Authorization: Bearer sk_ze_<your-api-key>"

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "llm-stats": {
      "command": "npx",
      "args": ["-y", "mcp-use", "client", "connect", "https://mcp.llm-stats.com/mcp"],
      "env": { "MCP_AUTHORIZATION": "Bearer sk_ze_<your-api-key>" }
    }
  }
}

Add this to your Continue config.json:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "name": "llm-stats",
        "url": "https://mcp.llm-stats.com/mcp",
        "headers": { "Authorization": "Bearer sk_ze_<your-api-key>" }
      }
    ]
  }
}

Configure your app with the hosted MCP URL and store the Bearer token in your platform’s secrets manager. ChatGPT renders every widget the server exposes.

URL: https://mcp.llm-stats.com/mcp
Header: Authorization: Bearer sk_ze_<your-api-key>

Any client that supports HTTP transport works. Set the server URL to https://mcp.llm-stats.com/mcp and pass your API key in the Authorization: Bearer sk_ze_<your-api-key> header.

Authentication

OAuth (recommended)

When you connect with OAuth, the MCP client discovers the LLM Stats authorization server, opens a browser sign-in, and receives an access token. The MCP server validates that token and provisions a stable per-user API key for Stats and gateway calls — you never paste a key into client config.

Add the server URL

Configure your MCP client with https://mcp.llm-stats.com/mcp only (no Authorization header).

Your client shows Connect or Needs authentication. Complete sign-in with Google or GitHub on llm-stats.com.

Use tools

After authorization, tool calls use the brokered credentials automatically. Reconnect later without signing in again until the token expires.

Legacy API key

You can still authenticate with a Bearer token. Use the same sk_ze_... key as the Stats API and the Gateway API. Get yours from the developer console.

OAuth is the easiest path for MCP clients that support it — no key to copy. For REST and gateway HTTP calls, or legacy MCP configs, provision one sk_ze_... key from the developer console and reuse it everywhere.

Tools

Read tools

Read tools are safe to call at any time. They don’t modify state and don’t consume gateway credits.

Tool	Description
`list-models`	List models with filters (organization, modality, price, context, sort, cursor).
`get-model`	Full detail for one model id: every benchmark score, provider pricing, and source.
`list-benchmarks`	Benchmark catalog. Use it to disambiguate benchmark ids.
`list-scores`	Score matrix with filters across models and benchmarks.
`get-rankings`	TrueSkill rankings for a category.
`list-updates`	Models added in the last N days (1–30).

Workflow tools

Workflow tools chain multiple API calls. They’re still read-only.

Tool	Description
`compare-models`	Side-by-side comparison of 2–4 model ids.
`find-best-models-for-category`	Top-ranked models for a category, optionally filtered by price or open-weight.
`resolve-model`	Fuzzy lookup: free text in, ranked candidate `model_id`s out. Use before any other tool when the id is fuzzy.

Gateway tools

Gateway tools call the inference gateway. OAuth-provisioned access and legacy sk_ze_... keys both authenticate gateway tool calls.

compare-run hits the gateway and consumes credits. It’s annotated readOnlyHint: false and openWorldHint: true so MCP clients can prompt for approval before calling.

Tool	Description
`compare-run`	Run a single prompt through 2–4 models in parallel; returns per-model latency, tokens, cost, and output. Capped at 2000 max tokens.
`get-gateway-snippet`	Return a ready-to-paste curl, Python, AsyncOpenAI, or JavaScript snippet for invoking a model through the gateway.

Resources

Seven MCP resources are available for introspection and reference lookups.

URI	Description
`config://server-context`	Redacted server config: auth mode, base URL, and connection status.
`docs://capabilities`	Canonical tool, resource, prompt, and widget inventory with annotations.
`data://benchmarks`	Full benchmark catalog (`{ id, name, category, modality, max_score, verified }`) so the LLM picks correct ids.
`data://categories`	Category ids (`coding`, `math`, `reasoning`, …) usable with `get-rankings`.
`data://organizations`	Organization catalog (`{ id, name }`) derived from the model index.
`data://providers`	Provider catalog (`{ id, name }`) derived from every model’s `providers[]`.
`recipe://gateway-quickstart`	Paste-ready gateway quickstart: base URL, auth, OpenAI compatibility, streaming, tools, multimodal, snippets.

Slash-command prompts

Four MCP prompts show up as slash-commands in clients like Cursor and Claude Desktop.

Prompt	Arguments	What it does
`/compare-models`	`model_a`, `model_b`	Resolves each name with `resolve-model`, then calls `compare-models` with the resolved ids and writes a structured comparison.
`/find-cheapest-for`	`task`, optional `max_input_price`	Maps the task to a category via `data://categories`, calls `find-best-models-for-category`, explains the price/quality tradeoff.
`/whats-new-this-week`	(none)	Calls `list-updates` with `days=7` (falling back to 14), summarizes notable releases grouped by org.
`/explain-benchmark`	`benchmark_id_or_name`	Disambiguates via `data://benchmarks`, fetches top scores via `list-scores`, writes a SOTA and saturation summary.

Interactive widgets

Seven tools render an interactive widget alongside a markdown summary. MCP Inspector, ChatGPT Apps, Cursor, Claude Desktop, VS Code, and Goose render both. Text-only clients fall back to the markdown.

Widget	Backing tool(s)
`leaderboard`	`list-models`, `find-best-models-for-category`
`model-card`	`get-model`
`model-compare-table`	`compare-models`
`benchmark-leaderboard`	`list-scores` (sorted, single-benchmark)
`rankings`	`get-rankings`
`updates-timeline`	`list-updates`
`compare-run`	`compare-run`

Overview

Data

Attribution & embeds

Endpoints

Quota

Setup

Connect with OAuth (recommended)

Legacy: API key

Authentication

OAuth (recommended)

Legacy API key

Tools

Read tools

Workflow tools

Gateway tools

Resources

Slash-command prompts

Interactive widgets

​Quota

​Setup

​Connect with OAuth (recommended)

​Legacy: API key

​Authentication

​OAuth (recommended)

​Legacy API key

​Tools

​Read tools

​Workflow tools

​Gateway tools

​Resources

​Slash-command prompts

​Interactive widgets

Quota

Setup

Connect with OAuth (recommended)

Legacy: API key

Authentication

OAuth (recommended)

Legacy API key

Tools

Read tools

Workflow tools

Gateway tools

Resources

Slash-command prompts

Interactive widgets