INDIVIDUAL MCP TOOL

host.tool_remove

Remove a published tool by its local name.

mcphost.devnone authenticationAvailability not checked

LIVE ENDPOINT

https://mcphost.dev/mcp

No auth detected

Connect to this endpoint to inspect the live schema for host.tool_remove 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.rmcp]
url = "https://mcphost.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "rmcp": {
      "type": "http",
      "url": "https://mcphost.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: rmcp
Remote MCP URL: https://mcphost.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": {
    "rmcp": {
      "url": "https://mcphost.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "rmcp": {
      "type": "http",
      "url": "https://mcphost.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

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

MCP Inspector

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

signup — Create a tenant and receive a bearer key and namespace.
host.whoami — Return the calling tenant's identity.
host.tool_publish — Publish a tool of a registered kind under this tenant's namespace.
host.quickstart — Return the shortest ordered sequence of calls to a working tool of `kind`, with your namespace and a filled-in example already substituted in, plus the current limits.
host.tool_list — List this tenant's published tools.
host.tool_logs — Return the most recent log lines for one of this tenant's tools.
host.tool_test — Dry-run a published tool: performs the real call but records no `calls` row and echoes the rendered request back with secrets redacted, for debugging a spec.
host.tool_run — Debug run of a published tool: the same sandbox and limits as a real call, but returns full stdout and stderr (each capped at 64 KiB) and the exit code alongside the result, and records no `calls` row and no metering.