A local service that governs spending and avoids duplicate work across groups of AI agents. It connects through the Model Context Protocol and uses x402, a way to settle payments between software services.

Use it as a local proxy in an AI-agent setup where spending rules, cross-agent deduplication, and x402 payment settlement are needed. It runs through an npm package and requires an API key and gateway address.

It helps agent fleets control costs and reduce repeated work when several agents may handle related tasks.

gatewards — MCP server for Claude Code and Codex by rtahabas: A local service that governs spending and avoids duplicate…

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/rtahabas/gatewards-sdk/mcp-server-gatewards

Clone the repo

git clone --depth 1 https://github.com/rtahabas/gatewards-sdk

Made for: Claude Code, Codex, Cursor.

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/rtahabas/gatewards-sdk/mcp-server-gatewards.svg)](https://agentmods.dev/mcp/rtahabas/gatewards-sdk/mcp-server-gatewards)

Your own site

<a href="https://agentmods.dev/mcp/rtahabas/gatewards-sdk/mcp-server-gatewards"><img src="https://agentmods.dev/badge/mcp/rtahabas/gatewards-sdk/mcp-server-gatewards.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 original No closer match found in the catalogue.

Security

Grade A, and why

gatewards 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 4d 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/server.json · 13 lines

What it actually says

{
  "gatewards": {
    "command": "npx",
    "args": [
      "-y",
      "@gatewards/mcp-server"
    ],
    "env": {
      "GATEWARDS_API_KEY": "",
      "GATEWARDS_GATEWAY_URL": ""
    }
  }
}

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.

4d ago First seen · 13 lines scan A 788a067c31d2

Subscribe to this mod's changes

gatewards is an MCP server published in the GitHub repository rtahabas/gatewards-sdk (0 stars, last pushed 2mo 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.

Building agents CrewAI Finance and fintech LangChain Multi-Agent agent-governance ai-agents autogen

quesen

Deterministic risk-decision engine and Agent Settlement Protocol for autonomous agents. Remote server at web-production-30ab5.up.railway.app.

Shxnque/quesen · not measured

agent-context-token-optimizer

MCP server "agent-context-token-optimizer" as configured in DeathOVOGod/agent-context-token-optimizer. Runs locally from the agent-context-token-optimizer Python package.

DeathOVOGod/agent-context-token-optimizer · not measured

snaprender

Screenshot, extract content, and render web pages. PNG/JPEG/WebP/PDF, batch, signed URLs. Runs locally from the snaprender-mcp npm package. Needs 1 environment variable to run.

User0856/snaprender-integrations · not measured

agentfetch

MCP server "agentfetch" as configured in SID1ART/agentfetch. Runs locally from the agentfetch Python package.

SID1ART/agentfetch · not measured

network-ai

AI agent orchestration framework for TypeScript/Node.js - 32 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, OpenAI Responses, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex, MiniMax, NemoClaw, APS, Copilot, LangGrap. Runs locally from the network-ai npm package.

Jovancoding/Network-AI · not measured

sidclaw-governance-mcp

Governance proxy for MCP servers — policy evaluation, human approval, audit trails. Runs locally from the @sidclaw/sdk npm package. Needs 5 environment variables to run.

sidclawhq/platform · not measured