INDIVIDUAL MCP TOOL

lookup_server

Latest probe of one server from the official MCP registry: status, protocol, tool count, token cost of its tool definitions, latency.

ulehla.devnone authenticationAvailability not checked

LIVE ENDPOINT

https://mcp-pulse.ulehla.dev/mcp

No auth detected

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

{}

Inferred read-only · 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.mcp-pulse]
url = "https://mcp-pulse.ulehla.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "mcp-pulse": {
      "type": "http",
      "url": "https://mcp-pulse.ulehla.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: mcp-pulse
Remote MCP URL: https://mcp-pulse.ulehla.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": {
    "mcp-pulse": {
      "url": "https://mcp-pulse.ulehla.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "mcp-pulse": {
      "type": "http",
      "url": "https://mcp-pulse.ulehla.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

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

MCP Inspector

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

search_servers — Find servers by words in name, title, description or host, with optional filters, sorted by token cost by default.
check_server — Connects to an MCP server URL now (initialize and tools/list, no credentials, 10 s timeout) and reports status, protocol, tools and an estimated token cost of the tool definitions.
registry_summary — Aggregates of the latest daily run: how many servers answer, token cost percentiles, protocol versions, heaviest servers.