INDIVIDUAL MCP TOOL

agent_security_policies

Get drop-in agent security policy templates by profile (coding-agent, browser-agent, payment-agent, research-agent).

agenttoll.devnone authenticationAvailability not checked

LIVE ENDPOINT

https://agenttoll.dev/mcp

No auth detected

Connect to this endpoint to inspect the live schema for agent_security_policies and invoke it with your own arguments.

{}

Potential side effects detected · medium confidence · heuristic, not a guarantee.

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

[mcp_servers.tollbooth]
url = "https://agenttoll.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "tollbooth": {
      "type": "http",
      "url": "https://agenttoll.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: tollbooth
Remote MCP URL: https://agenttoll.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": {
    "tollbooth": {
      "url": "https://agenttoll.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "tollbooth": {
      "type": "http",
      "url": "https://agenttoll.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "tollbooth",
  "transport": "streamable-http",
  "url": "https://agenttoll.dev/mcp"
}

MCP Inspector

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

ping — Health check.
scrape — Fetch a URL and return clean structured content: title, description, meta tags, text content, headings, links, and tech stack signals.
detect_stack — Fingerprint a URL for framework, analytics, hosting, payment, CRM, and site-platform signals.
extract_contacts — Extract visible emails, phone-like strings, social links, and contact/about/pricing/careers URLs from a page.
score_lead — Score a company domain for outbound fit using HTTPS, DNS, tech stack, contact paths, social links, platform, and copy depth.
check_agent_policy — Check robots.txt, llms.txt, security.txt, and agent.json for crawl/discovery signals before an agent touches a site.
find_agent_resource — Search a small curated atlas of agent-useful APIs, self-hosted tools, payment rails, scraping helpers, and automation primitives.
validate_agent_manifest — Validate an agent manifest for identity, endpoint, tools, pricing, and payment fields.