What is agentomy-mcp-gateway?

A local gateway for MCP servers that sits between an agent and tool calls and blocks calls when its checks fail. MCP is a standard way for an AI agent to use tools from another program; stdio means communication through the process input and output streams.

Use it to govern local stdio MCP servers by routing their tool calls through the agentomy-mcp-gateway.

It adds a fail-closed control point for tool calls, so an MCP request is not passed through when the gateway rejects it.

agentomy-mcp-gateway — MCP server for Claude Code and Codex by getagen

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/getagentomy/mcp-gateway

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/getagentomy/mcp-gateway/agentomy-mcp-gateway/github.svg)](https://agentmods.dev/mcp/getagentomy/mcp-gateway/agentomy-mcp-gateway)

Your own site

<a href="https://agentmods.dev/mcp/getagentomy/mcp-gateway/agentomy-mcp-gateway"><img src="https://agentmods.dev/badge/mcp/getagentomy/mcp-gateway/agentomy-mcp-gateway/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/getagentomy/mcp-gateway/agentomy-mcp-gateway"><img src="https://agentmods.dev/badge/mcp/getagentomy/mcp-gateway/agentomy-mcp-gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

agentomy-mcp-gateway scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

listed in the official MCP registry · 9 lines

What it actually says

{ "agentomy-mcp-gateway": { "command": "npx", "args": [ "-y", "agentomy-mcp-gateway" ] } }

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 9 lines scan A 02d36ce889b8

Subscribe to this mod's changes

agentomy-mcp-gateway is an MCP server published in the GitHub repository getagentomy/mcp-gateway (0 stars, last pushed 6d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security agent-security agentic-ai ai-agents ai-governance gateway mcp

mcp-server

Exact-action approval for consequential agent actions: request, track, and verify signed receipts. Runs locally from the @emilia-protocol/mcp-server npm package. Needs 3 environment variables to run.

emiliaprotocol/emilia-protocol · not measured

mcp

Authorize consequential AI agent actions before execution. Runs locally from the @decionis/mcp npm package. Needs 1 environment variable to run.

decionis/agent-safe-pipeline · not measured

termlink

MCP server "termlink" as configured in DimitriGeelen/agentic-engineering-framework. Launched with termlink mcp serve. Needs 1 environment variable to run.

DimitriGeelen/agentic-engineering-framework · not measured

fw

MCP server "fw" as configured in DimitriGeelen/agentic-engineering-framework. Runs agents/mcp/framework_mcp_server.py with python3.

DimitriGeelen/agentic-engineering-framework · not measured

arifos

Constitutional AI kernel with 13 MCP tools, 888JUDGE verdict pipeline, and VAULT999 ledger. Remote server at arifos.arif-fazil.com.

ariffazil/arifOS · not measured

arifos-mcp

mcp-name: io.github.ariffazil/arifos | .ariffazil/arifos | arifOS v1!2026.7.26 — Constitutional AI Governance Kernel. 8 kernel ABI capabilities → 6 public tools (arifverbnoun, generated from arifosmcp/abi/capabilityregistry.json), dynamic F1-F13 enforcement via ConstitutionKernel + FloorEvaluator, VAULT999 immutable…