MCP Tools Directory
← Browse integrations

Developer tools

io.github.jaimenbell/rails-mcp

Free account · sign-in required

Contact io.github.jaimenbell/rails-mcp

Loading secure sign-in…

Tools for autonomous AI agents

About this integration

Default-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).

Transport
stdio
Authentication
none
Initial setup
none
Runtime
unattended
Evidence
documented
Version
0.1.0
Package
rails-mcp
Last compatibility test
Not independently tested

Connect your agent

rails-mcp

Publisher README and Python manifest reviewed; package was not executed. The server has no external API and starts with an honest-empty registry when unconfigured. It records intent and classifications but does not enforce actions or block spending. Human sign-off is CLI-only and deliberately excluded from the MCP tool surface.

Capabilities: Classify actions as gated, Inspect registered action metadata, Read sign-off state, Record spend intent, Evaluate rolling budgets

Connected profiles

Additional details

Registry identifier

io.github.jaimenbell/rails-mcp

Source ↗ · Checked 2026-09-17
Published version

0.1.0

Source ↗ · Checked 2026-09-17
Metadata license

CC0-1.0; package licenses are separate

Source ↗ · Checked 2026-09-17
Package ecosystem

pypi

Source ↗ · Checked 2026-09-17
Source artifact

rails-mcp

Source ↗ · Checked 2026-09-19
Source manifest version

0.1.0

Source ↗ · Checked 2026-09-19
Unattended configuration

The local server can start with an empty registry while preserving its unconditional GATED classification behavior.

Source ↗ · Checked 2026-09-19
Authentication and prerequisites

The publisher states that the server has no external API; the local stdio tool surface has no documented account authentication.

Source ↗ · Checked 2026-09-19
Connection configuration

The documented MCP client configuration directly invokes the rails-mcp console script.

Source ↗ · Checked 2026-09-19
Review scope

Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.

Source ↗ · Checked 2026-09-19