Agent MCP Gateway MCP server
io.github.roddutra/agent-mcp-gateway·v0.2.5·41 starsOn-demand tool discovery for all your MCPs and per-subagent MCP controls to preserve context window.
41 stars27 downloads/wk
Reviews
Write oneNobody has reviewed Agent MCP Gateway yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agent MCP Gateway tools (4, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
execute_toolwrite actionExecute a tool on a downstream MCP server accessed through this gateway. Gateway validates permissions then forwards your request to the server. Returns the server's response directly.
get_server_toolsDiscover tools available on a downstream MCP server accessed through this gateway. Returns only tools you have permission to use (filtered by policy rules). Use the returned tool definitions to call execute_tool.
get_userGet user by ID
list_serversDiscover downstream MCP servers available through this gateway. Your access is determined by gateway policy rules. Workflow: 1) Call list_servers to discover servers, 2) Call get_server_tools to see available tools, 3) Call execute_tool to use them.
Public scan report
scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it
- Code scan13 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 304 days ago4/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Agent MCP Gateway compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 75/100
- higher than 45% of 4,460 AI and agents servers
- Tools
- 4
- the typical AI and agents server has 6
- Tools that change things
- 25%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 41
- more than 91% of 2,711 AI and agents servers
- Downloads a week
- 27
- more than 13% of 1,538 AI and agents servers with a package
What its tools let an agent do: 3 read · 1 run or deploy
Install Agent MCP Gateway in Claude Code, Cursor or VS Code
claude mcp add agent-mcp-gateway -- uvx agent-mcp-gateway
What the publisher says
From the Agent MCP Gateway repository's README, as published. We do not edit it. Read it on GitHub
Agent MCP Gateway
<!-- mcp-name: io.github.roddutra/agent-mcp-gateway -->
A Model Context Protocol (MCP) gateway that aggregates multiple MCP servers and provides policy-based access control for agents and subagents. Solves Claude Code's MCP context window waste by enabling on-demand tool discovery instead of loading all tool definitions upfront.
Status
- ✅ M0: Foundation - Configuration, policy engine, audit logging, list_servers tool
- ✅ M1: Core - Proxy infrastructure, getservertools, execute_tool, middleware, metrics, hot reload, OAuth support
- 🚧 M2: Production - HTTP transport, health checks (planned)
- 🚧 M3: DX - Single-agent mode, config validation CLI, Docker (planned)
Current Version: M1-Core Complete (with OAuth)
Table of Contents
- Overview
- Installation
- Quick Start
- Command-Line Options
- Configuration File Discovery
- Configuration
- Usage
- Gateway Tools
- Security Considerations
- Troubleshooting
- Testing
- Development
Overview
The Problem
When multiple MCP servers are configured in development environments (Claude Code, Cursor, VS Code), all tool definitions from all servers load into every agent's and subagent's context window at startup:
- 5,000-50,000+ tokens consumed upfront
- 80-95% of loaded tools never used by individual agents
- Context needed for actual work gets wasted on unused tool definitions
The Solution
The Agent MCP Gateway acts as a single MCP server that proxies to multiple downstream MCP servers based on configurable per-agent rules:
- 3 gateway tools load at startup (~2k tokens)
- Agents discover and request specific tools on-demand
- 90%+ context reduction
- Policy-based access control per agent/subagent
How It Works
The gateway sits between agents and downstream MCP servers, exposing only 3 lightweight tools. When an agent needs specific functionality, it discovers available servers and tools through the gateway, which filters visibility based on policy rules - agents only see servers and tools they have access to. This reduces each agent's context window to only relevant tools, while the gateway handles proxying authorized requests to downstream servers.
View detailed diagram with examples → (includes downstream servers, tools, and gateway rules examples)
Key Features
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Agent MCP Gateway: common questions
- Is Agent MCP Gateway MCP server safe?
- Mostly: it is graded B (75/100). Read the Agent MCP Gateway safety report
- How do I install Agent MCP Gateway?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Agent MCP Gateway need an API key?
- No secret keys are declared. It reads 4 settings from the environment.
- Is Agent MCP Gateway maintained?
- The last commit was 337 days ago (2025-12-02). The latest release is v0.2.5.
- What can I use instead of Agent MCP Gateway?
- Servers from other publishers that do the same job: agent-device MCP server, agent-device MCP server and MCP Server for WinDbg Crash Analysis.
- How does Agent MCP Gateway compare with other AI and agents MCP servers?
- safety score 75/100 (higher than 45% of 4,460 AI and agents servers); tools 4 (the typical AI and agents server has 6); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Agent MCP Gateway
Same job from other publishers: the closest match first, then the best rated.
- agent-deviceLet AI agents inspect, control, and debug real iOS, Android, desktop, and TV appsnot reviewedWidely usedA
- agent-deviceOpen source device layer for AI agents: control mobile, web, TV, and desktop apps over MCPnot reviewedWidely usedA
- MCP Server for WinDbg Crash AnalysisA Model Context Protocol server for Windows crash dump analysis using WinDbg/CDBnot reviewedEstablishedA
- DCC-MCP CoreAgent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.not reviewedEstablishedA
- Alibaba Cloud DashScope — QwenAlibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.not reviewedEstablishedB