← Registry

AI & Machine Learning

openfrontier.dev

This MCP server provides information about Frontier's AI models, their capabilities, and usage statistics for the API key.

1 endpoint3 known toolsFirst detected August 14, 2026Last detected August 15, 2026

ENDPOINT 1

https://openfrontier.dev/mcp

No auth detected

MCP server metadata

Name
frontier
Version
1.0.0
Capabilities
tools.listChanged

Known tools 3

list_models

List Frontier's current stable public model aliases.

Inferred read-only
get_capabilities

Get the public endpoints, stable aliases, and exact Chat Completions constraints.

Inferred read-only
get_usage

Read usage for the Frontier bearer API key on this MCP HTTP request.

Inferred read-only

CONNECT 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.frontier]
url = "https://openfrontier.dev/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "frontier": {
      "type": "http",
      "url": "https://openfrontier.dev/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: frontier
Remote MCP URL: https://openfrontier.dev/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": {
    "frontier": {
      "url": "https://openfrontier.dev/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "frontier": {
      "type": "http",
      "url": "https://openfrontier.dev/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "frontier",
  "transport": "streamable-http",
  "url": "https://openfrontier.dev/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.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.