AgentsPodium Hosting

com.agentspodium由 agentspodium.com 发布官方发布者v1.0.4更新于 Oct 24, 2026

Create, watch, pay for and connect hosted AI agent pods on AgentsPodium. Needs an API key.

已验证Streamable HTTP可网页运行云端与基础设施商业与电商AI 与机器学习

概览

AI 生成的概览

远程 MCP 网关,让助手在 AgentsPodium 上部署、监控、付费并连接托管的 AI 智能体实例。

可以做什么
  • 列出可用引擎与托管套餐,含价格与能力
  • 列出账户下的实例及其状态、端点、A2A 地址与域名
  • 创建、暂停、恢复、重建以及永久删除实例
  • 查询实例健康状态、配额状态与计费周期
  • 设置或清除实例使用的 LLM 提供商密钥,并设置允许调用的 A2A 对端
  • 获取支付方式,并注册接收生命周期事件的签名 webhook
适用场景
适合希望让助手代替网页控制台来开通和运维 AgentsPodium 托管智能体的场景,例如创建实例、健康检查、查询计费周期、轮换密钥和清理资源。若只是调用已有智能体则无需安装。
运行要求
远程 Streamable HTTP 端点,无需本地安装。需要 AgentsPodium API 密钥,通过 Authorization 的 Bearer 头传递,可在账户页面创建。客户端需接受 application/json 与 text/event-stream。
安装前请注意
API 密钥会被转发给 AgentsPodium 账户 API,应视为有效凭证妥善保管。创建实例和购买套餐可能产生真实费用,支持银行卡、加密货币和 Telegram Stars 等方式。删除不可恢复,暂停会归档数据,set_webhook 返回的 HMAC 密钥只显示一次。set_llm_key 会把你的 LLM 提供商密钥交给该服务。

安装

在 SourceWeft 中

  1. 打开 控制台中的 AgentsPodium Hosting,将其添加到工作区。
  2. 连接 Authorization token 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.agentspodium%2Fhosting/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "agentspodium-hosting": {
      "type": "http",
      "url": "https://mcp.agentspodium.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

agent-gateway

Lets other AI agents drive AgentsPodium hosting (create/monitor/manage instances) through two machine protocols — MCP (Streamable HTTP) and A2A (Agent2Agent JSON-RPC) — both backed by the existing account API at https://agentspodium.com/api.

The gateway holds no state and no secrets of its own. Every call carries the caller's own AgentsPodium API key (Authorization: Bearer ak_live_..., or a session token), which is forwarded verbatim to the account API. Missing that header always answers 401 with a JSON body pointing at https://agentspodium.com/account ("API keys for agents") and https://hosting.defispace.com/docs/auth.

One process serves both hostnames, selected by the Host header wherever a path is shared between the two (only GET /); everything else defaults to MCP behaviour, and mcp.agentspodium.com / a2a.agentspodium.com route to the same Deployment.

Run locally

bash
npm installnpm run buildACCOUNT_API=https://agentspodium.com/api PORT=3200 npm start# or, for iteration:npm run dev

Env vars:

  • ACCOUNT_API — base URL of the account API (default https://agentspodium.com/api).
  • PORT — HTTP port (default 3200).
  • A2A_HOST — hostname that selects A2A behaviour for GET / (default a2a.agentspodium.com).

Calling it

MCP — mcp.agentspodium.com/mcp

Streamable HTTP, stateless (no session id). Requires Accept: application/json, text/event-stream.

bash
# initializecurl -s -X POST https://mcp.agentspodium.com/mcp \  -H "Authorization: Bearer ak_live_..." \  -H "Content-Type: application/json" \  -H "Accept: application/json, text/event-stream" \  -d '{    "jsonrpc": "2.0", "id": 1, "method": "initialize",    "params": {      "protocolVersion": "2025-06-18",      "capabilities": {},      "clientInfo": { "name": "example-client", "version": "0.1.0" }    }  }'
# call a toolcurl -s -X POST https://mcp.agentspodium.com/mcp \  -H "Authorization: Bearer ak_live_..." \  -H "Content-Type: application/json" \  -H "Accept: application/json, text/event-stream" \  -d '{    "jsonrpc": "2.0", "id": 2, "method": "tools/call",    "params": { "name": "list_platforms", "arguments": {} }  }'

Tools: list_platforms, list_instances, create_instance, get_instance_health, get_instance_term, set_llm_key, pause_instance, resume_instance, rebuild_instance, delete_instance, get_payment_options, set_peers, set_webhook. Plus one resource, agentspodium://docs (the hosting docs).

A2A — a2a.agentspodium.com/

bash
curl -s https://a2a.agentspodium.com/.well-known/agent-card.json
# structured (data part)curl -s -X POST https://a2a.agentspodium.com/ \  -H "Authorization: Bearer ak_live_..." \  -H "Content-Type: application/json" \  -d '{    "jsonrpc": "2.0", "id": 1, "method": "message/send",    "params": {      "message": {        "parts": [{ "kind": "data", "data": { "skill": "create-instance", "params": { "engine": "hermes", "tier": "small", "name": "My Agent" } } }]      }    }  }'
# plain text (small command grammar)curl -s -X POST https://a2a.agentspodium.com/ \  -H "Authorization: Bearer ak_live_..." \  -H "Content-Type: application/json" \  -d '{    "jsonrpc": "2.0", "id": 2, "method": "message/send",    "params": { "message": { "parts": [{ "kind": "text", "text": "platforms" }] } }  }'

Text grammar: create <engine> <tier> [name ...], health <id>, term <id>, platforms, payment <id>. Anything else answers with the skill list and the exact JSON shape.

Public, no auth: GET /catalog.json (proxy of the account API's /a2a-catalog).

Deploy

bash
docker build -t agentpodium-agent-gateway apps/agent-gateway# push, then apply:kubectl apply -f apps/agent-gateway/deploy/gateway.yaml

deploy/gateway.yaml creates namespace ap-agentgw, a Deployment/Service on port 3200, and two HTTPRoutes (mcp.agentspodium.com, a2a.agentspodium.com) against the shared akash-gateway Gateway. Swap __IMAGE_TAG__ for the built image tag before applying.

来源:README.md,提交 7511739

工具

13

list_platforms

List platforms and plans

List available AgentsPodium engines (platforms) and hosting plans (tiers), with prices and capabilities.

无需输入参数。

list_instances

List instances

List the caller's AgentsPodium instances (agents): id, name, engine, tier, status, endpoint and A2A URL, domain, creation date. Never returns secrets.

无需输入参数。

create_instance

Create instance

Create (deploy) a new AgentsPodium instance. Returns the instance id and, when enableA2A is true, the a2aUrl and a2aToken the caller should keep. After creating, poll get_instance_health until it is serving, then call set_llm_key to give it a working LLM key.

输入参数nametier必填modeldomainenginechannelsenableA2AextraSoulpersonaIdwebhookUrl

get_instance_health

Check instance health

Check whether an instance is reachable and serving, plus its status and quota state.

输入参数id必填

get_instance_term

Get billing term

Get the billing term (trial/paid/grace) for an instance, including when it renews or expires.

输入参数id必填

set_llm_key

Set LLM key

Set (or clear, with key=null) the LLM provider API key an instance uses to answer. Required before a freshly created instance can actually respond.

输入参数id必填key必填modelprovider必填

pause_instance

Pause instance

Pause an instance: stops it and its billing lease. Data is archived, not deleted.

输入参数id必填

resume_instance

Resume instance

Resume a previously paused instance, rebuilding it from its archive.

输入参数id必填

rebuild_instance

Rebuild instance

Rebuild an instance's pod (e.g. after a config change that needs a restart).

输入参数id必填

delete_instance

Delete instance

Permanently delete an instance. This cannot be undone.

输入参数id必填

get_payment_options

Get payment options

Get ways to pay for an instance's plan: card/subscription buy links, crypto payment info, and Telegram Stars info (crypto and Stars are in beta testing), plus the instance's current term.

输入参数id必填

set_peers

Set A2A peers

Set the list of other A2A agents this instance is allowed to call by name.

输入参数id必填peers必填

set_webhook

Set event webhook

Register a URL that receives signed POSTs when the instance comes up, stops, fails, is deleted, when a payment is confirmed and before deletion for non-payment — instead of polling get_instance_health. Returns the HMAC secret once.

输入参数id必填url必填

版本历史

1
  1. v1.0.4最新Sep 16, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。