Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "broker": {
      "type": "http",
      "url": "https://api.llm-broker.net/api/v1/broker/mcp",
      "headers": {
        "Authorization": "Bearer ${BROKER_TOKEN}"
      }
    }
  }
}

claude mcp add --transport http broker https://api.llm-broker.net/api/v1/broker/mcp --header "Authorization: Bearer ${BROKER_TOKEN}"

[mcp_servers.broker]
url = "https://api.llm-broker.net/api/v1/broker/mcp"
bearer_token_env_var = "BROKER_TOKEN"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "broker": {
      "type": "remote",
      "url": "https://api.llm-broker.net/api/v1/broker/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:BROKER_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "broker": {
      "type": "http",
      "url": "https://api.llm-broker.net/api/v1/broker/mcp",
      "headers": {
        "Authorization": "Bearer ${BROKER_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=broker&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLmxsbS1icm9rZXIubmV0L2FwaS92MS9icm9rZXIvbWNwIiwiaGVhZGVycyI6eyJBdXRob3JpemF0aW9uIjoiQmVhcmVyICR7QlJPS0VSX1RPS0VOfSJ9fQ%3D%3D"
}

{
  "servers": {
    "broker": {
      "type": "http",
      "url": "https://api.llm-broker.net/api/v1/broker/mcp",
      "headers": {
        "Authorization": "Bearer ${BROKER_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "broker": {
      "httpUrl": "https://api.llm-broker.net/api/v1/broker/mcp",
      "headers": {
        "Authorization": "Bearer ${BROKER_TOKEN}"
      }
    }
  }
}

extensions:
  "broker":
    enabled: true
    name: "broker"
    type: streamable_http
    uri: "https://api.llm-broker.net/api/v1/broker/mcp"
    headers:
      "Authorization": "Bearer ${BROKER_TOKEN}"
    timeout: 300

Placeholders to fill from your own secret store: ${BROKER_TOKEN}. The registry never accepts secret values.

Quality 92 / 100strong

protocol100 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
pass
protocol.list_ttltool list is cacheable (ttlMs 300000)

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations8 of 8 tools declare readOnlyHint or destructiveHint
warn
tools.directory_hints1 of 8 tools declare all four hints; missing: get_model (destructiveHint, idempotentHint); create_account (idempotentHint); get_balance (destructiveHint, idempotentHint); …
pass
tools.token_costabout 1,194 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability75 · weight 15

warn
stability.changes7 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

8 tools, about 1,194 tokens to load them all · tool set 140c1b1b6b95 · tools last changed 2026-10-05 · checked 2026-10-20 17:34 UTC

Tool changes

2026-10-05report_outcomeadded
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.
2026-10-05create_accountadded
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.
2026-10-03get_balanceadded
Balance, credit limit and spend this month (CHF, the book currency), billing mode and payment currency of the account behind Authorization: Bearer ast_sk_….
2026-10-03estimate_costadded
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).
2026-10-03recommend_modeladded
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.
2026-10-03get_modeladded
One model from list_models by id: measured scores per category, price per 1M tokens (default USD), regions, context and capabilities.
2026-10-02list_modelschangeddescription, input schema
before
Models on the broker with benchmark scores per category (0–1, measured by us), price per 1M tokens in CHF and regions. Filter by category, region and price; sorted by score in the category, else by price.
after · 71% of words in common
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.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 83 / 100

no-repository

provenance55

liveness100

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-100% +updated-14d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://api.llm-broker.net/api/v1/broker/mcp` streamable-http	none	yes	100%	416 ms	2026-07-28, 2025-06-18, 2025-03-26, 2024-11-05	2026-10-20

Tools (8)

`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.
`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.
`estimate_cost`read-only	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).
`get_balance`read-only	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`read-only	One model from list_models by id: measured scores per category, price per 1M tokens (default USD), regions, context and capabilities.
`list_models`read-only	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_model`read-only	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_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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "net.llm-broker/broker",
  "title": "LLM Broker",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.llm-broker.net/api/v1/broker/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "description": "Bearer ast_sk_… — only for the chat tool; list_models needs no key"
        }
      ]
    }
  ],
  "version": "1.3.0",
  "websiteUrl": "https://llm-broker.net/",
  "description": "One key, every model: measured scores and live prices, routed per request to the cheapest fit."
}