AI & Machine Learning

agenttoolbox.net

Provides AI agent developers with token-cost estimation, JSON Schema conversion to OpenAI/Anthropic/MCP tool definitions, MCP server config generation, and search over an AI agent tool directory.

1 endpoint4 known toolsFirst detected October 17, 2026Last detected October 17, 2026

ENDPOINT 1

https://agenttoolbox.net/api/mcp

No auth detected

MCP server metadata

Name: agenttoolbox
Version: 1.0.0

Capabilities

tools

Known tools 4

estimate_tokens

Estimate tokens and USD cost of a text across current frontier models (list prices verified 2026-10-16).

Inferred read-only

convert_schema

Convert a JSON Schema into OpenAI, Anthropic and MCP tool definitions.

Inferred read-only

mcp_config

Generate an mcpServers config block.

Inferred read-only

search_directory

Search the Agent Toolbox directory of AI agent tools.

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.agenttoolbox]
url = "https://agenttoolbox.net/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agenttoolbox": {
      "type": "http",
      "url": "https://agenttoolbox.net/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agenttoolbox
Remote MCP URL: https://agenttoolbox.net/api/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": {
    "agenttoolbox": {
      "url": "https://agenttoolbox.net/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agenttoolbox": {
      "type": "http",
      "url": "https://agenttoolbox.net/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agenttoolbox",
  "transport": "streamable-http",
  "url": "https://agenttoolbox.net/api/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.