Render integrates with popular coding agents to help you manage your infrastructure, diagnose issues, and learn about the platform.

## Agent skills and plugins

Render's official **skills** enable agents to deploy, debug, and monitor your apps. These skills are also bundled into official marketplace **plugins** for Cursor, Codex, and Claude Code.

### Install

Render provides official plugins for **Cursor**, **Codex**, and **Claude Code**.  
Open the plugin marketplace for your preferred tool (usually with `/plugins`) and search for `render`:

Every plugin bundles Render's official skills to provide a unified interface for using them with your coding agent. Some plugins also include the [Render MCP server](/content/docs/llm-support#render-mcp-server/index.html). See your plugin's documentation for details.

**Requires version 2.10 or later of the [Render CLI](/content/docs/cli/index.html).**

Check your current version with `render --version`

1. Run the following command:
   ```shell
   $ render skills install
   ```
2. The CLI detects supported tools on your system (Claude Code, Codex, Cursor, OpenCode) and prompts you to select which skills to install.

You can also specify options directly for non-interactive use:
```shell
$ render skills install --tool cursor --skill render-deploy --skill render-debug
```
See the [CLI reference](/content/docs/cli-reference#skills/index.html) for the full list of `skills` subcommands, including `update`, `remove`, and `list`.  
Run the following script to automatically detect popular supported tools (Claude Code, Cursor, etc.) on your system and install Render's official skills for each:
```shell
$ curl -fsSL https://raw.githubusercontent.com/render-oss/skills/main/scripts/install.sh | bash
```
The output looks like this:

##### Manual installation

1. Clone the [Render Skills GitHub repository](https://github.com/render-oss/skills).
2. From the repo's `skills/` directory, copy each skill directory into your tool's skills directory.

Default skills directories for popular tools are listed below:

| Tool | Skills Directory |
| --- | --- |
| Claude Code | `~/.claude/skills/<skill-name>/` |
| Codex | `~/.codex/skills/<skill-name>/` |
| Cursor | `~/.cursor/skills/<skill-name>/` |
| OpenCode | `~/.config/opencode/skills/<skill-name>/` |

Depending on your tool, you might need to restart it after installing.

After installing, your agent can automatically select and invoke skills to fulfill relevant prompts. You can also invoke a skill manually using your coding agent's syntax (usually a `/` or `$` symbol followed by the skill's name).

### Supported skills

#### Render interfaces

| Skill | Description |
| --- | --- |
| **render-cli** | Install and use the [Render CLI](/content/docs/cli/index.html) for deployment and operations. |
| **render-mcp** | Connect and configure the Render MCP server for your coding agent. |

#### Service lifecycle

| Skill | Description |
| --- | --- |
| **render-deploy** | Deploy applications using IaC with Render Blueprints or directly via MCP. |
| **render-docker** | Build and deploy containerized services using Docker on Render. |
| **render-scaling** | Scale services with manual instance controls or autoscaling settings. |

#### Service diagnostics

| Skill | Description |
| --- | --- |
| **render-debug** | Debug deployment issues using logs, metrics, and database queries.<br>Detects common issues like missing environment variables, port binding errors, and resource constraints. |
| **render-monitor** | Monitor service health, performance metrics, logs, and resource usage in real-time. |

#### Service config

| Skill | Description |
| --- | --- |
| **render-blueprints** | Author and validate `render.yaml` files for use with [Render Blueprints](/content/docs/infrastructure-as-code/index.html) for multi-service infrastructure. |
| **render-domains** | Configure custom domains and HTTPS/TLS for web services and static sites. |
| **render-env-vars** | Manage environment variables, secrets, and environment groups across services. |
| **render-networking** | Connect services over Render's private network using internal DNS and service discovery. |

#### Service types

| Skill | Description |
| --- | --- |
| **render-background-workers** | Configure queue-based background workers for asynchronous job processing. |
| **render-cron-jobs** | Set up and troubleshoot scheduled tasks using Render cron jobs. |
| **render-private-services** | Set up internal-only private services that are reachable on Render's private network. |
| **render-static-sites** | Deploy and configure static sites on Render's global CDN. |
| **render-web-services** | Configure and troubleshoot public web services on Render. |
| **render-workflows** | Set up, build, and deploy Render Workflows for distributed task execution. |

#### Datastores

| Skill | Description |
| --- | --- |
| **render-disks** | Attach and manage persistent disks for stateful workloads. |
| **render-keyvalue** | Provision and configure Render Key Value instances. |
| **render-postgres** | Set up and operate Render Postgres databases. |

#### Migration

| Skill | Description |
| --- | --- |
| **render-migrate-from-heroku** | Plan and execute migrations from Heroku to Render. |

### Example prompts

Ask your tool to perform any of these tasks:

> Deploy my application to Render
>
> Debug my Render deployment
>
> Is my Render service healthy?

Your tool will invoke the appropriate set of skills and guide you through the process.

### Skill source

[View skills on GitHub](https://github.com/render-oss/skills)

## Render MCP server

Connect to Render's official MCP server to manage your Render infrastructure directly from apps like Cursor and Claude Code:

The MCP server provides tools for actions such as:

- Creating new services and redeploying existing ones
- Querying databases
- Analyzing metrics and logs

It's especially useful for helping you identify and resolve issues with service deploys.

[Get started with Render MCP](/content/docs/mcp-server/index.html)

## Documentation features

The Render documentation provides the following capabilities to improve content discoverability and parsing for agents:

### Articles as markdown

Each article under `render.com/docs/` is available in a simplified markdown format that's well suited for LLMs.

Obtain an article's markdown version by doing any of the following:

- Append `.md` to the end of an article's URL:
```
https://render.com/docs/llm-support.md
```
- Include an `Accept: text/markdown` header in your request to an article's URL (no `.md` extension required).
  - Agentic tools like Claude Code often include this header in their HTTP requests by default.
- Click **Copy page** in the top-right corner of an article to copy its markdown version to your clipboard (not available on smaller screen widths).

### Reading `llms.txt` and `llms-full.txt`

The Render documentation includes `llms.txt` and `llms-full.txt` files at the following URLs:
```
https://render.com/docs/llms.txt
https://render.com/docs/llms-full.txt
```

| File | Description |
| --- | --- |
| [`llms.txt`](/content/docs/llms.txt) | Provides a summary of the Render documentation, including links and descriptions of each article. |
| [`llms-full.txt`](/content/docs/llms-full.txt) | Combines most of the Render documentation into a single, simplified markdown file. Some content types are omitted for brevity. |

### Docs via MCP

**This feature is experimental.**

Render might discontinue support for this documentation-specific MCP server at any time in the future.

Render's primary [MCP server](/content/docs/llm-support#render-mcp-server/index.html) does not yet provide tools for querying the Render documentation.

To query the Render docs from LLMs, you can connect your app or agent to the following additional MCP server:
```
https://mcp.inkeep.com/render/mcp
```

This MCP server provides "tools" for searching and asking questions about the Render docs. It uses the same LLM-powered answer engine as the **Ask AI** assistant in the documentation.