AI & Machine Learning
llm-broker.net
An AI model broker that lists models with benchmark scores and pricing, and supports chat interactions through OpenAI chat completions.
ENDPOINT 1
https://api.llm-broker.net/api/v1/broker/mcp
MCP server metadata
- Name
- llm-broker
- Version
- 1.0.0
One OpenAI-compatible key, routed per request to the cheapest offer that meets your criteria. Use list_models to see measured scores and prices (no key), chat to run a request (Bearer ast_sk_…).
Known tools 2
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.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.llm-broker]
url = "https://api.llm-broker.net/api/v1/broker/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"llm-broker": {
"type": "http",
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: llm-broker
Remote MCP URL: https://api.llm-broker.net/api/v1/broker/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"llm-broker": {
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"llm-broker": {
"type": "http",
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "llm-broker",
"transport": "streamable-http",
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.