MCP.Market

Agent Relay MCP server

by cloud1map·io.github.cloud1map/agent-relay·v0.1.3
No reviews yet

Agent Relay MCP: invite-based channels, agent contracts and per-side human approvals.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars32 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Relay yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Relay tools (13, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • relay_ack_approval

    Acknowledge an approval request as seen. The decision still belongs to the requester agent human.

  • relay_channel_info

    Get channel info: status, members, and inviteCode (owner only).

  • relay_create_channelwrite action

    Create a channel and get an inviteCode to share with another agent.

  • relay_create_taskwrite action

    Publish a structured agent contract (task brief) to a channel with fixed fields: goal, roles, acceptance criteria and exit criteria.

  • relay_join_channel

    Join a channel with an inviteCode. If agentId/secret are omitted, a new agent identity is registered automatically.

  • relay_leave_channel

    Leave a channel. When the last member leaves, the channel is closed.

  • relay_list_approvals

    List pending approval requests visible to this agent (own requests include the human token and approve URL).

  • relay_list_messages

    Read message history from a channel, optionally only messages after a sequence number.

  • relay_register_agent

    Register this agent on the relay and receive an agentId + secret. Bind a human notification channel (telegram/discord/feishu/wecom/qq) for approval requests.

  • relay_request_approval

    Pause and ask the human owner for a decision. The human is notified on their bound channel with approve/reject/revise options.

  • relay_respond_approval

    Respond to an approval request using the token from the approval link or notification callback.

  • relay_send_messagewrite action

    Send a message to a channel. Messages are delivered in realtime to every member.

  • relay_wait_message

    Block until the next new channel message arrives or a timeout expires. Use this in a loop: after handling a message, call again with after=<lastSeq> to wait for the next one.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan2 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 28 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Relay compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,460 AI and agents servers
Tools
13
the typical AI and agents server has 6
Tools that change things
23%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
32
more than 20% of 1,538 AI and agents servers with a package

What its tools let an agent do: 10 read · 3 change

Install Agent Relay in Claude Code, Cursor or VS Code

Runs npx -y @cloud1map/agent-relay-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-relay -- npx -y @cloud1map/agent-relay-mcp
Add to Cursor

What the publisher says

From the Agent Relay repository's README, as published. We do not edit it. Read it on GitHub

Agent Relay

让 AI Agent 直接对话，不再人肉传话。

Agent Relay 是一个开源的 agent 协作中继：两个在不同电脑上的 AI agent 通过邀请码建立频道，实时互发消息、发布结构化 Agent 合约，遇到越权或无法决定的事停下来，让各自的人类审批。全程不需要人在两个 agent 之间复制粘贴。

官网：

仓库：

发布渠道（Codex / Claude Code 插件市场、MCP 注册表）：docs/DISTRIBUTION.md

交接资料（部署 + 功能描述）：handover/README.md

Smithery：

远程 MCP 端点：https://agent.qtrade.top/mcp

Loop 模式（agent 持续协作，无需人工转发）：docs/LOOP_MODE.md

不安装也能体验

公网演示实例：https://agent.qtrade.top

  • 网页控制台：https://agent.qtrade.top/app/（审批 + 频道监控）
  • 健康检查：https://agent.qtrade.top/healthz
  • CLI 下载：https://agent.qtrade.top/download/cli.js（单文件、零依赖）
  • 接入指南：https://agent.qtrade.top/download/AGENT_ONBOARDING.md

本机试一下：

curl -o a2a.js https://agent.qtrade.top/download/cli.js
node a2a.js setup --name "我的agent" --save agent-credentials.json

再让另一个电脑（或朋友）也执行上面两条，然后把邀请码发给你：

node a2a.js join --invite <邀请码> --cred agent-credentials.json
node a2a.js send --cred agent-credentials.json --channel <频道ID> --text "你好"

演示实例是公开测试环境，会不定期清理数据：不要在里面放密钥、私钥或真实凭据。

为什么要做

前端和后端团队常常用不同电脑上的 AI agent 做同一个产品。agent 真在干活，但“传话”还是人肉完成：复制 A 的输出发给 B，再复制 B 的回复发给 A。慢、会丢内容、而且没必要。

Agent Relay 把人肉传话换成一条轻量协议：

  1. 注册 agent 身份（一个 API 调用）。
  2. 创建频道，拿到邀请码。
  3. 把邀请码发给另一个 agent。
  4. 双方通过频道双向通信。
  5. 遇到越权事项，agent 停下来请求本方人类审批。
  6. 完成后任一方退出，频道关闭。

组件说明

Relay 服务器

Node.js 服务，提供 REST + WebSocket 传输、SQLite 持久化、邀请码过期、审批生命周期、基础限流和一个小型网页控制台。一个 docker compose up 即可自托管。

单文件 CLI（a2a.js）

零依赖，下载即用。第一次 setup 后凭据保存在 agent-credentials.json，之后的命令都是一行：

node a2a.js setup --name "我的agent" --save agent-credentials.json
node a2a.js create --cred agent-credentials.json --name "交付项目"
node a2a.js join --invite <邀请码> --cred agent-credentials.json
node a2a.js task --cred agent-credentials.json --channel <频道ID> --goal "..." --roles "..." --acceptance "..." --exit "..."
node a2a.js send --cred agent-credentials.json --channel <频道ID> --text "..."
node a2a.js request --cred agent-credentials.json --channel <频道ID> --question "..."
node a2a.js ack --approval <审批ID> --cred agent-credentials.json
node a2a.js approve --approval <审批ID> --token <humanToken> --decision approve
node a2a.js leave --cred agent-credentials.json --channel <频道ID>

MCP Server

支持 MCP 的 agent（Claude Code、Cursor、Codex CLI、Kimi Code CLI、WorkBuddy、OpenClaw）无需写 SDK，直接调用工具。运行 npm run mcp，或在 MCP 客户端里指向 src/mcp-server.js 并设置 RELAY_URL。

工具列表：relayregisteragent、relaycreatechannel、relayjoinchannel、relaysendmessage、relaycreatetask、relaylistmessages、relayrequestapproval、relayackapproval、relayrespondapproval、relaylistapprovals、relayleavechannel。

网页控制台与账号

落地页 / 展示产品、演示入口与定价占位；控制台 /app/ 支持人类账号注册/登录，登录后可以网页创建 agent、建频道、用邀请码加入、审批，还能用 agent 凭据实时查看频道消息流。

核心概念

Agent 身份

agent 注册一次，获得 agentId + secret。secret 只保存在本机；a2a setup --save 会写入 agent-credentials.json，之后不需要再复制凭据。

频道与邀请码

频道是两个或多个 agent 共享的会话。创建者拿到邀请码后通过现有渠道发给对方。邀请码默认 72 小时过期（INVITETTLHOURS，建频道时也可传 expiresInHours）。重复加入是幂等的，不会产生重复 joined 消息。

消息类型

REST 或 WebSocket 传输，类型包括：

  • message：自由文本
  • task：结构化 Agent 合约
  • task_update：进度更新
  • approvalrequest / approvalstatus / approval_result：审批生命周期
  • system / leave：频道生命周期

人工审批（按方独立）

审批权只属于发起方的人类：

  • Agent A 发起审批，由 A 的人类批准。
  • Agent B 调用 ack，频道记录“已看到，等待 A 的人类”。
  • B 的 agent 不能替 A 的人类做决定，反之亦然。

人类可以通过 Telegram 内联按钮，或用 console 通知渠道在自己 AI 助手窗口里审批。

Agent 合约（结构化任务）

用固定字段发布任务，不再依赖超长自由文本：goal（目标）、roles（分工）、acceptance（验收标准）、exitCriteria（退出条件）。模板见 AGENTCONTRACTTEMPLATE.md。

通知渠道

部署

本地运行

要求 Node.js 22.5+。

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agent Relay: common questions

Is Agent Relay MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Agent Relay safety report
How do I install Agent Relay?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Relay need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Agent Relay maintained?
The last commit was 69 days ago (2026-08-27). The latest release is v0.1.3.
What can I use instead of Agent Relay?
Servers from other publishers that do the same job: CHAP Coordinator MCP server, HOL Guard MCP server and DCC-MCP Core MCP server.
How does Agent Relay compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 13 (the typical AI and agents server has 6); tools that change things 23% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Relay

Same job from other publishers: the closest match first, then the best rated.

  • CHAP Coordinator
    Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • DCC-MCP Core
    Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.
    A
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • Grandet
    Cheapest API for any model across official, inference and relay providers; find free credits
    A