Skip to content

LLM Broker MCP server

net.llm-broker/brokerllm-broker.netstreamable-httpv1.3.0Scanned

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

8 tools: 2 do something that can't be undone, 3 change things and 3 only read.

Tools: 0 delete, 2 irreversible, 3 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

5 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the LLM Broker MCP server can do

The LLM Broker MCP server is published by llm-broker.net, a domain the MCP Registry verified. It has 8 tools. It can do things that cannot be undone, such as sending, paying or publishing (chat and create_account) and create or change data (3 tools: recommend_model, estimate_cost and report_outcome), but cannot delete data. 3 tools only read.

2 tools bring in text other people can write (chat and create_account); 1 tool can send data out of your system (chat).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 18, 2026, version 1.3.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

8 tools

Can't be undone 2Claude Code: ask
  • chatSends messages to the broker (OpenAI chat completions).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe description's first verb is "send": it sends or publishes something to other people.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • openWorldHint: true
    • readOnlyHint: false
  • create_accountCreates a card checkout (Stripe) for a new broker account — same as POST /api/v1/broker/accounts.Reads text others writeNo findings

    Why it is in this group

    • The name "create_account" says "create": a word for a change.
    • The input carries an amount (input.amount) and a currency, so it moves money.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • openWorldHint: true
    • readOnlyHint: false
    • destructiveHint: false
Changes things 3Claude Code: ask
  • estimate_costCost estimate at list price for a model and token counts, in your currency.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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).

    Annotations the server declares

    • openWorldHint: false
    • readOnlyHint: true
  • recommend_modelPicks from the published catalog (our own benchmark scores, list prices): best = highest score in the category, best_value = score per output price, plus alternatives.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • openWorldHint: false
    • readOnlyHint: true
  • report_outcomeTell the broker if the answer to a request worked for your task — request_id comes from broker.receipt of every chat answer.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • openWorldHint: false
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
Only reads 3Show 3 read-only tools
  • get_balanceBalance, credit limit and spend this month (CHF, the book currency), billing mode and payment currency of the account behind Authorization: Bearer ast_sk_….No findings

    Why it is in this group

    • The name "get_balance" says "get": a word for reading.
    Description, as the server wrote it
    Balance, credit limit and spend this month (CHF, the book currency), billing mode and payment currency of the account behind Authorization: Bearer ast_sk_….

    Annotations the server declares

    • openWorldHint: false
    • readOnlyHint: true
  • get_modelOne model from list_models by id: measured scores per category, price per 1M tokens (default USD), regions, context and capabilities.No findings

    Why it is in this group

    • The name "get_model" says "get": a word for reading.
    Description, as the server wrote it
    One model from list_models by id: measured scores per category, price per 1M tokens (default USD), regions, context and capabilities.

    Annotations the server declares

    • openWorldHint: false
    • readOnlyHint: true
  • list_modelsModels 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.No findings

    Why it is in this group

    • The name "list_models" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • openWorldHint: false
    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:16 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://api.llm-broker.net/.well-known/oauth-protected-resource/api/v1/broker/mcp
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (2 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.llm-broker.net/api/v1/broker/mcp: tools/list returned 8 tools to an anonymous client, including chat (irreversible), create_account (irreversible), recommend_model (write), estimate_cost (write), report_outcome (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.3.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__broker__list_models",
      "mcp__broker__get_model",
      "mcp__broker__get_balance"
    ],
    "ask": [
      "mcp__broker__recommend_model",
      "mcp__broker__estimate_cost",
      "mcp__broker__chat",
      "mcp__broker__report_outcome",
      "mcp__broker__create_account"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as broker. Review it before you use it.

Capability tags behind 2 rules
  • mcp__broker__chat untrusted-input, outbound
  • mcp__broker__create_account untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/net.llm-broker/broker/verify?hash=a8f19acc1e529b733d66513f976a54c7b51564748652549d5d5b1d77adae8502" | jq -e '.changed == false'

Pinned hash a8f19acc1e52, from Nov 18, 2026, 20:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/net.llm-broker/broker/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for net.llm-broker/broker
[![Anlyon Radar](https://radar.anlyon.com/badge/net.llm-broker/broker.svg)](https://radar.anlyon.com/servers/net.llm-broker/broker)

Source: MCP Registry. Synced Oct 21, 2026, 18:53 UTC.

LLM Broker MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the LLM Broker MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the LLM Broker MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the LLM Broker MCP server do things that cannot be undone?

Yes. 2 tools can send, pay, publish or merge: chat and create_account.

What tools does the LLM Broker MCP server have?

8 tools: 2 irreversible, 3 write, 3 read. chat, create_account, recommend_model, estimate_cost, report_outcome, list_models, get_model and get_balance.

Does the LLM Broker MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the LLM Broker MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): chat.

Has the LLM Broker MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.