# LLM Broker (remote · api.llm-broker.net)

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

- Trust score: 69/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `api.llm-broker.net`: 69/100 (this document), [markdown](https://verifymcp.io/servers/net-llm-broker-broker/api-v1-broker-mcp.md), [page](https://verifymcp.io/servers/net-llm-broker-broker/api-v1-broker-mcp)

## Channel facts

- Endpoint: `https://api.llm-broker.net/api/v1/broker/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 929 tokens (~116/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 77/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 32% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "chat" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the LLM Broker MCP server?

LLM Broker is a hosted endpoint at https://api.llm-broker.net/api/v1/broker/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http net-llm-broker-broker 'https://api.llm-broker.net/api/v1/broker/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "net-llm-broker-broker": {
      "url": "https://api.llm-broker.net/api/v1/broker/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "net-llm-broker-broker": {
      "type": "http",
      "url": "https://api.llm-broker.net/api/v1/broker/mcp"
    }
  }
}
```

### Codex

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

### opencode

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

### OpenClaw

```bash
openclaw mcp add net-llm-broker-broker --url 'https://api.llm-broker.net/api/v1/broker/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  net-llm-broker-broker:
    url: "https://api.llm-broker.net/api/v1/broker/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "net-llm-broker-broker": {
      "Transport": "http",
      "Url": "https://api.llm-broker.net/api/v1/broker/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add net-llm-broker-broker -t streamable-http -u 'https://api.llm-broker.net/api/v1/broker/mcp'
```

### Other

```json
{
  "mcpServers": {
    "net-llm-broker-broker": {
      "type": "http",
      "url": "https://api.llm-broker.net/api/v1/broker/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-16 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-11 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 27. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-07 (score 65, +2)

- [functional improvement] MCP protocol: fail → pass

### 2026-10-06 (score 63, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: pass → fail
- [functional] Server version: 1.1.0 → 1.2.0
- [functional] New tool “create_account”
- [functional] New tool “report_outcome”

### 2026-10-03 (score 62, +2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “list_models” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 131 → 147
- [functional improvement] Tool coverage: 22% → 32%
- [functional improvement] Schema quality: 131 → 103
- [functional improvement] Tool coverage: 22% → 30%
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.0.0 → 1.1.0
- [functional] New tool “estimate_cost”
- [functional] New tool “get_balance”
- [functional] New tool “get_model”
- [functional] New tool “recommend_model”
- [cosmetic] “list_models” added an optional parameter “currency”
- [cosmetic] “list_models” reworded the description of “max_price_per_mtok”

### 2026-10-02 (score 60)

First indexed and scored.

## MCP tools (8)

### `list_models` (~129 tokens)

List models with measured scores and prices

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.

Input parameters:

- `category` (string)
- `currency` (string): ISO 4217 code, default USD
- `limit` (integer)
- `max_price_per_mtok` (number): Max output price per 1M tokens, in currency
- `region` (string)

### `get_model` (~58 tokens)

Get one model with scores and prices

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

Input parameters:

- `currency` (string): ISO 4217, default USD
- `id` (string, required)

### `recommend_model` (~130 tokens)

Recommend a model for a task

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.

Input parameters:

- `capabilities` (array)
- `category` (string, required)
- `currency` (string): ISO 4217, default USD
- `max_price_per_mtok` (number): Max output price per 1M tokens, in currency
- `min_score` (number)
- `region` (string)

### `estimate_cost` (~78 tokens)

Estimate the cost of a request

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).

Input parameters:

- `currency` (string): ISO 4217, default USD
- `input_tokens` (integer)
- `model` (string, required)
- `output_tokens` (integer)

### `chat` (~119 tokens)

Run a chat completion through the broker

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.

Input parameters:

- `max_tokens` (integer)
- `messages` (array)
- `model` (string)
- `prompt` (string): Shortcut for a single user message
- `routing` (object)

### `get_balance` (~40 tokens)

Account balance and spend

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` (~94 tokens)

Report whether a request did its job

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.

Input parameters:

- `outcome` (string, required)
- `reason` (string)
- `request_id` (string, required)

### `create_account` (~170 tokens)

Buy an API key

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.

Input parameters:

- `amount` (integer): topup amount in currency
- `billing` (string, required)
- `category` (string): optional, with level: a fixed performance promise
- `currency` (string)
- `level` (string)
- `limit` (integer): monthly credit limit in currency

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/net-llm-broker-broker/api-v1-broker-mcp#diagnostics

## Score history

- 2026-10-17: 69
- 2026-10-16: 69
- 2026-10-15: 68
- 2026-10-14: 68
- 2026-10-13: 68
- 2026-10-12: 67
- 2026-10-11: 67
- 2026-10-10: 66
- 2026-10-08: 65
- 2026-10-07: 65
- 2026-10-06: 63
- 2026-10-04: 62
- 2026-10-03: 62
- 2026-10-02: 60

## Common questions

### What is the LLM Broker MCP server?

LLM Broker is an MCP server listed in the public MCP registry as net.llm-broker/broker. One key, every model: measured scores and live prices, routed per request to the cheapest fit. This page covers its hosted endpoint (https://api.llm-broker.net/api/v1/broker/mcp).

### Is the LLM Broker MCP server safe to use?

LLM Broker scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the LLM Broker MCP server expose?

LLM Broker exposes 8 tools: list_models, get_model, recommend_model, estimate_cost, chat, and 3 more. Their descriptions and schemas cost roughly 818 tokens of context every time the server is loaded.

### Does the LLM Broker MCP server require authentication?

No. We connected to LLM Broker without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the LLM Broker MCP server still maintained?

LLM Broker is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.llm-broker.net/api/v1/broker/mcp
- Website: https://llm-broker.net/
- Changelog RSS feed: https://verifymcp.io/servers/net-llm-broker-broker/api-v1-broker-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/net-llm-broker-broker/api-v1-broker-mcp.json
- HTML version of this page: https://verifymcp.io/servers/net-llm-broker-broker/api-v1-broker-mcp