Rails MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 47 installs a week from pypi. Last commit 12 Aug 2026.
Default-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).
Today is the operative word: we check Rails MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add rails-mcp -- uvx rails-mcp
{
"mcpServers": {
"rails-mcp": {
"args": [
"rails-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.rails-mcp]
command = "uvx"
args = ["rails-mcp"]
{
"mcpServers": {
"rails-mcp": {
"args": [
"rails-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"rails-mcp": {
"args": [
"rails-mcp"
],
"command": "uvx"
}
}
}
MCP server registry and marketplace - discover, install, activate tools on demand
Read-only MCP tools over Inferrail's local receipt ledger: attributed spend and gateway health.
Read-only XRP Ledger MCP tools with proof-annotation envelopes and signed daily snapshots.
CIW Registration: the site's own MCP server — enquiry (enquiry = a human handoff, not a...
FHIR chart tools for MCP: read-only by default, with elicitation-gated, human-approved writes.
Care Inspectorate Registration: the site's own MCP server — enquiry (enquiry = a human handoff,...
PostgreSQL MCP wrapper with .env credential mapping, tool selection, and safe read-only defaults.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Answers built from our own checks of this server.