Developer Tools

mcphost.dev

MCP server for managing tenants and publishing/listing tools within a namespace.

1 endpoint17 known toolsFirst detected June 5, 2026Last detected September 6, 2026

ENDPOINT 1

https://mcphost.dev/mcp

No auth detected

MCP server metadata

Name: rmcp
Version: 3.2.0

Capabilities

tools

Server instructions

Call `signup` with a display name to receive a bearer key. The `host.*` control plane -- including `host.tool_publish` and `host.tool_call` -- is already visible in this tools/list, before you have a key. Pass the key `signup` returns as the `tenant_key` argument on every call after that; no reconnect and no Authorization header is required.

Known tools 17

signup

Create a tenant and receive a bearer key and namespace.

Potential side effects

host.whoami

Return the calling tenant's identity.

Inferred read-only

host.tool_publish

Publish a tool of a registered kind under this tenant's namespace.

Potential side effects

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.

Inferred read-only

host.tool_list

List this tenant's published tools.

Inferred read-only

host.tool_remove

Remove a published tool by its local name.

Potential side effects

host.tool_logs

Return the most recent log lines for one of this tenant's tools.

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

host.tool_call

Invoke a tool this tenant has already published, by its local name -- the same real, metered call as calling it directly by its namespaced name (<namespace>.

Inferred read-only

host.usage

Calls, errors and duration percentiles for this tenant over a window.

Inferred read-only

host.secret_set

Store an encrypted secret value under this tenant's namespace.

Inferred read-only

host.secret_list

List this tenant's secret names (never their values).

Inferred read-only

host.registry_publish

Publish this tenant's server.

Potential side effects

billing.plans

The plan catalog (price and quotas per plan) and whether Stripe billing is configured on this host.

Inferred read-only

billing.status

This tenant's plan, usage against each quota, and when the daily call quota resets.

Inferred read-only

billing.checkout

Create (or reuse an open one for the same plan) a Stripe Checkout URL to upgrade this tenant, defaulting to the pro plan.

Potential side effects

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.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.

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.