render-mcp
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseRender MCP Server
Render MCP服务器
The Render MCP server lets AI coding tools manage Render services, databases, deploys, logs, and metrics directly. This skill covers setup, authentication, workspace selection, the tool catalog, and troubleshooting.
Action skills (render-deploy, render-debug, render-monitor) use MCP tools for their workflows. If MCP is not connected, set it up using this skill first.
Render MCP服务器允许AI编码工具直接管理Render服务、数据库、部署、日志及指标。本技能涵盖设置、认证、工作区选择、工具目录及故障排查内容。
操作技能(render-deploy、render-debug、render-monitor)在工作流中会用到MCP工具。若MCP未连接,请先使用本技能完成设置。
When to Use
使用场景
- fails or MCP tools are unavailable
list_services() - First-time Render MCP setup for any AI tool
- User asks how to connect their AI tool to Render
- Switching workspaces or troubleshooting auth errors
- Discovering which MCP tools exist and what they do
- 调用失败或MCP工具不可用
list_services() - 首次为任意AI工具配置Render MCP
- 用户询问如何将AI工具连接至Render
- 切换工作区或排查认证错误
- 了解现有MCP工具及其功能
Connection Details
连接详情
| Property | Value |
|---|---|
| URL | |
| Transport | HTTP (streamable) |
| Auth | OAuth when installed via the Render plugin (pre-registered client id); bearer token (API key) for manual setup |
| API key page | |
| Docs | |
| 属性 | 值 |
|---|---|
| URL | |
| 传输协议 | HTTP(支持流式传输) |
| 认证方式 | 通过Render插件安装时使用OAuth(预注册客户端ID);手动设置时使用Bearer token(API密钥) |
| API密钥页面 | |
| 文档 | |
Setup by Tool
按工具设置
Render plugin (recommended)
Render插件(推荐)
The Render plugin for Cursor, Codex, and Claude Code bundles this MCP server with a pre-registered OAuth client id, so no API key is needed. After installing or updating the plugin, reload the tool (restart Cursor or Claude Code, or start a new Codex thread) so it loads the plugin-provided MCP server, then complete the Render OAuth prompt the first time MCP tools are used. Verify with .
list_services()The manual, API-key setups below are for tools without the plugin or for custom MCP configurations.
适用于Cursor、Codex和Claude Code的Render插件已集成该MCP服务器及预注册的OAuth客户端ID,无需API密钥。安装或更新插件后,重新加载工具(重启Cursor或Claude Code,或开启新的Codex线程)以加载插件提供的MCP服务器,首次使用MCP工具时完成Render OAuth授权提示即可。可通过验证连接状态。
list_services()以下手动API密钥设置适用于无插件支持的工具或自定义MCP配置场景。
Cursor
Cursor
-
Get an API key from the Render Dashboard
-
Add to:
~/.cursor/mcp.json
json
{
"mcpServers": {
"render": {
"url": "https://mcp.render.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}- Restart Cursor, then verify with
list_services()
-
从Render控制台获取API密钥
-
将配置添加至:
~/.cursor/mcp.json
json
{
"mcpServers": {
"render": {
"url": "https://mcp.render.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}- 重启Cursor,然后通过验证连接
list_services()
Claude Code
Claude Code
-
Get an API key from the Render Dashboard
-
Add the MCP server:
bash
claude mcp add --transport http render https://mcp.render.com/mcp --header "Authorization: Bearer <YOUR_API_KEY>"- Restart Claude Code, then verify with
list_services()
-
从Render控制台获取API密钥
-
添加MCP服务器:
bash
claude mcp add --transport http render https://mcp.render.com/mcp --header "Authorization: Bearer <YOUR_API_KEY>"- 重启Claude Code,然后通过验证连接
list_services()
Codex
Codex
-
Get an API key from the Render Dashboard
-
Set the key in your shell:
bash
export RENDER_API_KEY="<YOUR_API_KEY>"- Add the MCP server:
bash
codex mcp add render --url https://mcp.render.com/mcp --bearer-token-env-var RENDER_API_KEY- Restart Codex, then verify with
list_services()
-
从Render控制台获取API密钥
-
在Shell中设置密钥:
bash
export RENDER_API_KEY="<YOUR_API_KEY>"- 添加MCP服务器:
bash
codex mcp add render --url https://mcp.render.com/mcp --bearer-token-env-var RENDER_API_KEY- 重启Codex,然后通过验证连接
list_services()
Other Tools
其他工具
For tools not listed above, use the generic HTTP MCP configuration:
- URL:
https://mcp.render.com/mcp - Auth header:
Authorization: Bearer <YOUR_API_KEY> - Transport: HTTP (streamable HTTP, not SSE)
See Render MCP docs for tool-specific instructions.
对于未列出的工具,使用通用HTTP MCP配置:
- URL:
https://mcp.render.com/mcp - 认证头:
Authorization: Bearer <YOUR_API_KEY> - 传输协议: HTTP(流式HTTP,非SSE)
工具特定说明请查看Render MCP文档。
Workspace Selection
工作区选择
After MCP is connected, set the active workspace:
Set my Render workspace to [WORKSPACE_NAME]Or programmatically:
get_selected_workspace() # Check current
list_workspaces() # List availableAll MCP operations run against the active workspace.
MCP连接完成后,设置活跃工作区:
Set my Render workspace to [WORKSPACE_NAME]或通过代码方式操作:
get_selected_workspace() # 查看当前工作区
list_workspaces() # 列出可用工作区所有MCP操作均针对活跃工作区执行。
Tool Catalog
工具目录
Service management
服务管理
| Tool | Purpose |
|---|---|
| List all services and datastores |
| Get service details |
| Create a web service from Git repo |
| Create a static site from Git repo |
| Update service configuration |
| Restart a service |
| 工具 | 用途 |
|---|---|
| 列出所有服务与数据存储 |
| 获取服务详情 |
| 通过Git仓库创建Web服务 |
| 通过Git仓库创建静态站点 |
| 更新服务配置 |
| 重启服务 |
Deploys
部署管理
| Tool | Purpose |
|---|---|
| List deploys for a service |
| Trigger a new deploy |
| 工具 | 用途 |
|---|---|
| 列出服务的部署记录 |
| 触发新部署 |
Logs
日志管理
| Tool | Purpose |
|---|---|
| Query logs with filters |
Key filters: (error, warn, info), (build, deploy), (search string), (HTTP codes).
leveltypetextstatusCode| 工具 | 用途 |
|---|---|
| 带筛选条件查询日志 |
关键筛选条件:(error、warn、info)、(build、deploy)、(搜索字符串)、(HTTP状态码)。
leveltypetextstatusCodeMetrics
指标管理
| Tool | Purpose |
|---|---|
| Get service or database metrics |
Metric types: , , , , , , .
cpu_usagememory_usagecpu_limitmemory_limithttp_latencyhttp_request_countactive_connectionsOptional: (0.5, 0.95, 0.99), (filter by endpoint).
httpLatencyQuantilehttpPath| 工具 | 用途 |
|---|---|
| 获取服务或数据库指标 |
指标类型:、、、、、、。
cpu_usagememory_usagecpu_limitmemory_limithttp_latencyhttp_request_countactive_connections可选参数:(0.5、0.95、0.99)、(按端点筛选)。
httpLatencyQuantilehttpPathDatabases
数据库管理
| Tool | Purpose |
|---|---|
| List Postgres databases |
| Get database details |
| Run SQL query |
| 工具 | 用途 |
|---|---|
| 列出Postgres数据库实例 |
| 获取数据库详情 |
| 执行SQL查询 |
Key Value
键值存储管理
| Tool | Purpose |
|---|---|
| List Key Value instances |
| Get Key Value details |
| 工具 | 用途 |
|---|---|
| 列出键值存储实例 |
| 获取键值存储详情 |
Environment Variables
环境变量管理
| Tool | Purpose |
|---|---|
| Set env vars on a service |
| 工具 | 用途 |
|---|---|
| 为服务设置环境变量 |
Workspace
工作区管理
| Tool | Purpose |
|---|---|
| List available workspaces |
| Get the active workspace |
| 工具 | 用途 |
|---|---|
| 列出可用工作区 |
| 获取当前活跃工作区 |
Common Mistakes
常见错误
| Mistake | Fix |
|---|---|
| Wrong URL (using SSE endpoint) | Use |
| Plugin installed but MCP tools unavailable | Reload the tool (restart, or start a new thread) so it loads the plugin's MCP server |
| OAuth prompt does not appear | Reinstall or update the Render plugin, then reload the tool |
| Expired or invalid API key | Generate a new key from Dashboard > Account Settings > API Keys |
| Wrong workspace selected | Run |
| Using MCP to create image-backed services | Not supported — use Dashboard or API for prebuilt Docker images |
Missing | Header must be |
| 错误 | 修复方案 |
|---|---|
| URL错误(使用SSE端点) | 使用 |
| 已安装插件但MCP工具不可用 | 重新加载工具(重启或开启新线程)以加载插件提供的MCP服务器 |
| OAuth授权提示未出现 | 重新安装或更新Render插件,然后重新加载工具 |
| API密钥过期或无效 | 从控制台 > 账户设置 > API密钥生成新密钥 |
| 选中了错误的工作区 | 运行 |
| 使用MCP创建镜像驱动的服务 | 暂不支持——请使用控制台或API处理预构建Docker镜像 |
认证头缺少 | 头信息必须为 |
Troubleshooting
故障排查
See for connection errors, auth failures, timeout issues, and tool-specific quirks.
references/troubleshooting.md连接错误、认证失败、超时问题及工具特定异常请查看。
references/troubleshooting.mdReferences
参考文档
| Document | Contents |
|---|---|
| Connection errors, auth failures, tool-specific issues, timeout handling |
| 文档 | 内容 |
|---|---|
| 连接错误、认证失败、工具特定问题、超时处理 |
Related Skills
相关技能
- render-deploy — Deploy flows using MCP tools
- render-debug — Debug failures using MCP logs and metrics
- render-monitor — Monitor health using MCP metrics
- render-cli — CLI alternative when MCP is unavailable
- render-deploy — 使用MCP工具完成部署流程
- render-debug — 使用MCP日志与指标排查故障
- render-monitor — 使用MCP指标监控服务健康状态
- render-cli — MCP不可用时的CLI替代方案