Connect LLM Broker and your agent gets 8 tools, among them chat, create_account, estimate_cost. It answers at https://api.llm-broker.net/api/v1/broker/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 2 October 2026; the last check, on 17 November 2026, succeeded.
One key, every model: measured scores and live prices, routed per request to the cheapest fit.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 Authorizati Inputs: messages, prompt, model, max_tokens, routing |
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, Inputs: level, category, limit, currency, amount, billing |
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). Inputs: currency, model, input_tokens, output_tokens |
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_…. |
get_model | One model from list_models by id: measured scores per category, price per 1M tokens (default USD), regions, context and capabilities. Inputs: id, currency |
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 cate Inputs: category, limit, currency, region, max_price_per_mtok |
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 mo Inputs: category, currency, region, capabilities, min_score, max_price_per_mtok |
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 again Inputs: reason, request_id, outcome |
Every block below points at https://api.llm-broker.net/api/v1/broker/mcp. Pick your client and copy.
claude mcp add --transport http llm-broker https://api.llm-broker.net/api/v1/broker/mcp
{
"mcpServers": {
"llm-broker": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.llm-broker.net/api/v1/broker/mcp"]
}
}
}{
"mcpServers": {
"llm-broker": {
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}{
"servers": {
"llm-broker": {
"type": "http",
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}{
"context_servers": {
"llm-broker": {
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}{
"mcpServers": {
"llm-broker": {
"serverUrl": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}{
"mcpServers": {
"llm-broker": {
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}name: LLM Broker
version: 0.0.1
schema: v1
mcpServers:
- name: LLM Broker
type: streamable-http
url: https://api.llm-broker.net/api/v1/broker/mcp{
"mcpServers": {
"llm-broker": {
"httpUrl": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}{
"mcpServers": {
"llm-broker": {
"type": "http",
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}{
"mcpServers": {
"llm-broker": {
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.llm-broker.net%2Fapi%2Fv1%2Fbroker%2Fmcp&type=streamable_http&id=llm-broker&name=LLM%20Broker
It answered our last check on 17 November 2026 in 66 ms. Over 4 checks since 2 October 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by llm-broker.net and served from api.llm-broker.net, the vendor's own domain: https://api.llm-broker.net/api/v1/broker/mcp.
8, as returned by the server's own tools/list on 20 November 2026: chat, create_account, estimate_cost, get_balance, get_model, list_models, recommend_model, report_outcome.
It answered our last check on 17 November 2026 in 66 ms. Over 4 checks since 2 October 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.llm-broker.net/api/v1/broker/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: net.llm-broker. Endpoint host: api.llm-broker.net. ARD identifier: urn:air:net.llm-broker:mcp:broker.
First indexed 2 October 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.