agentmods.dev

mcp

mcp is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from gatewerk/gatewerk. Its token cost is not measured, scanned A, original, AGPL-3.0.

A locally run review service for AI agents, where people make the final decisions about the work agents produce.

In plain words
What is it for?
Reviewing agent-produced changes or results before a person approves them. It runs from an npm package and requires three environment variables.
Why use it?
It adds a human approval step to agent workflows, so generated work is not accepted automatically.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 1 8d ago A scan tokens not measured AGPL-3.0
View the source file gatewerk/gatewerk gatewerk.com
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.

agentmods
npx agentmods add mcp/gatewerk/gatewerk/mcp-mcp
Clone the repo
git clone --depth 1 https://github.com/gatewerk/gatewerk

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.

agentmods badge for mcp

README.md
[![agentmods](https://agentmods.dev/badge/mcp/gatewerk/gatewerk/mcp-mcp.svg)](https://agentmods.dev/mcp/gatewerk/gatewerk/mcp-mcp)
Your own site
<a href="https://agentmods.dev/mcp/gatewerk/gatewerk/mcp-mcp"><img src="https://agentmods.dev/badge/mcp/gatewerk/gatewerk/mcp-mcp.svg" alt="Measured on agentmods" 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. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

mcp 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 5d 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.

packages/mcp/server.json · 14 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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.

  1. 5d ago First seen · 14 lines scan A cb723f55194a

Subscribe to this mod's changes

mcp is an MCP server published in the GitHub repository gatewerk/gatewerk (1 stars, last pushed 8d ago), licensed AGPL-3.0. 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.

Building agentsLLMagentsai-agentsaudit-loghuman-in-the-loopmcp
Related

Other mcp servers, from other repositories

mcp-confidence

A drop-in confidence gate for LLM agents: turn token logprobs into an accept / verify / ask-a-human routing decision, with honest per-model calibration. Runs locally from the mcp-confidence Python package.

shaxzodbek-uzb/mcp-confidence · not measured

webbridge-mcp

MCP server "webbridge-mcp", hosted remotely at 127.0.0.1, as configured in lxinfei5/research-os.

lxinfei5/research-os · not measured

github

MCP server "github" as configured in Bike4Mind/bike4mind. Runs in Docker (ghcr.io/github/github-mcp-server).

Bike4Mind/bike4mind · not measured

usrcp

Encrypted local ledger of structured user state, shared across every MCP-aware AI tool. Runs locally from the usrcp npm package. Needs 1 environment variable to run.

frank-bot07/usrcp · not measured

quellgeist-metrics

Model-agnostic AI agent for first-line production-incident triage; read-only evidence tools exposed as MCP servers. Runs locally from the quellgeist Python package. Needs 1 environment variable to run.

Rajeev-Shyam/Quellgeist · not measured

realmemory

MCP server "realmemory" as configured in re-obscura/realMemory. Runs locally from the realmemory Python package.

re-obscura/realMemory · not measured