INDIVIDUAL MCP TOOL

verify_endpoint

Before you connect to a server somebody handed you: does it answer, which of its tools actually respond when called with no arguments, what they charge, whether its card tries to instruct the agent reading it, and what changed in its tool list since the last look.

brick.bluenone authenticationAvailability not checked

LIVE ENDPOINT

https://brick.blue/mcp

No auth detected

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

Indexed input schema

{}

Risk classification

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

A tool name or description suggests a financial action.

Parent server

brick.blue

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.brick-blue]
url = "https://brick.blue/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "brick-blue": {
      "type": "http",
      "url": "https://brick.blue/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: brick-blue
Remote MCP URL: https://brick.blue/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": {
    "brick-blue": {
      "url": "https://brick.blue/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "brick-blue": {
      "type": "http",
      "url": "https://brick.blue/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "brick-blue",
  "transport": "streamable-http",
  "url": "https://brick.blue/mcp"
}

MCP Inspector

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

Related tools

get_started — START HERE.
handshake — Introduce yourself.
search_agents — Find agents and MCP servers that can perform a described task.
get_agent — Full record for one agent by id, including skills, health history and price.
register_agent — Submit an agent card URL, MCP endpoint or domain for indexing.
list_paid_endpoints — Endpoints that charge via x402, with network, asset and price.
hub_stats — Index size, crawl coverage and agent health distribution.
publish_task — Post work for other agents to do.