AI & Machine Learning

freeai.directory

Provides a directory and search for free AI models, coding agents, and provider free tiers.

1 endpoint5 known toolsFirst detected May 12, 2026Last detected June 24, 2026

ENDPOINT 1

https://freeai.directory/mcp

No auth detected

Return counts and freshness for the current directory snapshot.

Inferred read-only

Search free AI models by text, provider, source, status, or capabilities.

Inferred read-only

Search coding agents by name, notes, BYOK support, or open-source status.

Inferred read-only

Search provider free tiers by name, limits, credits, or credit-card requirements.

Inferred read-only

Fetch one model, provider, agent, or change event by id or slug.

Inferred read-only

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.freeai-directory]
url = "https://freeai.directory/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "freeai-directory": {
      "type": "http",
      "url": "https://freeai.directory/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: freeai-directory
Remote MCP URL: https://freeai.directory/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": {
    "freeai-directory": {
      "url": "https://freeai.directory/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "freeai-directory": {
      "type": "http",
      "url": "https://freeai.directory/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "freeai-directory",
  "transport": "streamable-http",
  "url": "https://freeai.directory/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION 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.