LLM Broker MCP server

• Registry namenet.llm-broker/brokerverified in the MCP registry

The registry name sits under llm-broker.net. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-26
• Tools8
• Server calls itselfllm-broker
• Server version1.3.0
• Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 514 ms.

• Its tools do every use case we checked: compare live token prices across LLM API providers; check measured performance of models by provider.
• Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
• What an agent can do with it2 of 2 use cases
• Answeredmeasuring2 of the 7 daily checks it takes to print a share
• Median first answer543 ms
• Space in an agent's context≈ 1,182 tokensthe definitions of all its tools (8), which an agent carries on every turn
• Tool definitionsB · 85 of 100
• Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 7 of 8

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• 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…

• get_model

  One model from list_models by id: measured scores per category, price per 1M tokens (default USD), regions, context and capabilities.

• 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…

• 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).

• 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…

• 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_….

• 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…

• 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…