mcpbeat Sign in

LLM Broker MCP Server

by llm-broker Your server? Claim it
answering

LLM Broker is answering right now. Last checked 5 min ago. It exposes 8 tools.

One key, every model: measured scores and live prices, routed per request to the cheapest fit.

Uptime history 10 days of history
10 days agonow
100.0%
Uptime 24h
92 of 92 checks
8
Tools
read from the server
153 ms
Response time
average over 24h
open, no key
Access
streamable-http

What changed 9

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 3 October 2026. No other catalogue keeps this.

6 Oct a tool changed version
5 Oct 2 tools appeared create_account, report_outcome
5 Oct a tool changed version
3 Oct 4 tools appeared estimate_cost, get_balance, get_model and 1 more
3 Oct a tool changed version

Nothing serious here today

Today is the operative word: we check LLM Broker every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

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.

run in your terminal
claude mcp add broker --transport http https://api.llm-broker.net/api/v1/broker/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "broker": {
      "url": "https://api.llm-broker.net/api/v1/broker/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.broker]
url = "https://api.llm-broker.net/api/v1/broker/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "broker": {
      "url": "https://api.llm-broker.net/api/v1/broker/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "broker": {
      "url": "https://api.llm-broker.net/api/v1/broker/mcp"
    }
  }
}

Available tools 8

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

account
create_account
Creates a card checkout (Stripe) for a new broker account — same as POST /api/v1/broker/accounts. Give checkout_url to your human; after payment the API key is shown exactly once at status_url (GET, poll until 200). topup: amount 10/25/50, monthly: limit 50/100/250 (USD/EUR/CHF; other currencies: GET /api/v1/broker/currencies). Omit category and level to choose per request.
balance
get_balance
Balance, credit limit and spend this month (CHF, the book currency), billing mode and payment currency of the account behind Authorization: Bearer ast_sk_….
chat
chat
Sends messages to the broker (OpenAI chat completions). model defaults to `taylor` (strongest measured model); any id from list_models works. routing sets criteria per request, e.g. {"category": "coding", "level": "best"}. Needs Authorization: Bearer ast_sk_… — billed like the REST API.
estimate
estimate_cost
Cost estimate at list price for a model and token counts, in your currency. The bill follows the offer the router actually picks (broker.cost in the chat result).
model
get_model
One model from list_models by id: measured scores per category, price per 1M tokens (default USD), regions, context and capabilities.
models
list_models
Models on the broker with benchmark scores per category (0–1, measured by us), price per 1M tokens (default USD, any currency from GET /api/v1/broker/currencies) and regions. Filter by category, region and price; sorted by score in the category, else by price.
recommend
recommend_model
Picks from the published catalog (our own benchmark scores, list prices): best = highest score in the category, best_value = score per output price, plus alternatives. Only measured models are recommended. Returns chat_arguments for that model and a routing object to let the broker pick per request.
report
report_outcome
Tell the broker if the answer to a request worked for your task — request_id comes from broker.receipt of every chat answer. Outcomes appear per model in list_models as reported (failures_30d / outcomes_30d), so the scores are checked against real tasks. No refund, no price change.

Endpoints

URLTransportStateLatencyChecked
https://api.llm-broker.net/api/v1/broker/mcp streamable-http answering 109 ms 5 min ago

Alternatives to LLM Broker

same job, measured the same way
Modelpricewatch
by modelpricewatch

Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.

32 installs/wk 4 tools answering
OrcaRouter
by continuum-ai-corp

Browse 160+ LLM models and live pricing — no API key needed for catalog. Add key to route chat.

64 installs/wk local only
Model Price Radar
by alialtunar

LLM prices on OpenRouter now and since 2023: history, drops, cheapest model for a job. No API keys.

126 installs/wk local only
Green MCP
by rlawogh1005

Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.

117 installs/wk local only
Modelglass
by modelglass

Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.

answering
Seracade
by rckl88

LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.

47 installs/wk local only
Clawbackai MCP
by rckl88

LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.

30 installs/wk local only
Robot Resources Router
by robot-resources

Intelligent LLM routing proxy — 60-90% cost savings by auto-selecting the cheapest model

38 installs/wk local only

LLM Broker — questions

Answers built from our own checks of this server.

What can LLM Broker do?
It exposes 8 tools, read directly from the server on our last check. Among them: chat, create_account, estimate_cost, get_balance, get_model, list_models and 2 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 →
Is LLM Broker working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 153 ms. The bar chart above shows every period we have measured.
How do I connect LLM Broker?
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 LLM Broker need an API key?
No. LLM Broker completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 8 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is LLM Broker?
It answers our handshake in 153 ms on average, which is faster than 72% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.