Render on Hermes configures an AI agent to manage Render through its pre-registered MCP server without installing the Render CLI.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install render-on-hermes
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install render-on-hermes using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Render on Hermes?
Render on Hermes is a bootstrap and operations skill for Openclaw Skills running inside a Hermes container deployed on Render. It establishes that the Render MCP server is already registered, authenticated through the lazy-substituted RENDER_MCP_API_KEY, and available with the full tool scope permitted by that key.
The skill prevents common setup errors by telling agents to skip redundant MCP installation, CLI installation, and login instructions from upstream render-* skills. It also provides safe guidance for workspace selection, resource mutations, MCP tool naming, CLI-only operations, and troubleshooting.
Render on Hermes Use Cases
- Operating Render services, databases, environments, and deployments from Hermes.
- Loading any upstream
render-*skill without repeating MCP or CLI setup. - Inspecting services, logs, metrics, workspaces, and PostgreSQL through Render MCP tools.
- Restarting services, updating environment variables, triggering deploys, or creating resources when authorized by the API key.
- Handling Render tasks that have no MCP equivalent by drafting commands for the user’s local shell.
- Diagnosing missing MCP tools or authentication failures caused by an unavailable
RENDER_MCP_API_KEY. - Identifying the Hermes service itself when a user asks to inspect an unnamed Render service.
How Render on Hermes Works
- Load Render on Hermes whenever a
render-*skill is requested or the user asks for a Render operation. - Treat the
renderMCP server as preconfigured throughconfig.yaml, using HTTP transport athttps://mcp.render.com/mcp. - Authenticate through the gateway’s lazy substitution of
RENDER_MCP_API_KEY; do not configureRENDER_API_KEYor runrender login. - Map upstream tool names such as
list_services()andget_metrics()to Hermes tools such asmcp_render_list_services()andmcp_render_get_metrics(). - Check the selected workspace with
mcp_render_get_selected_workspace; if none is selected, list workspaces and select the only obvious option or ask the user when multiple choices are plausible. - Inspect Render state freely, while clearly explaining the impact before performing mutations such as restarts, deploys, resource updates, or environment-variable changes.
- Prefer MCP equivalents for CLI workflows, such as
list_logsinstead ofrender logsandget_metricsinstead ofrender metrics. - For live log streaming, interactive PostgreSQL sessions, SSH, or other CLI-only operations, provide a command for the user to run locally rather than invoking it in the Hermes terminal.
- Verify connectivity with
mcp_render_list_services(); a successful response confirms that MCP is wired correctly. - If the check returns a 401 or the tool is unavailable, instruct the user to add
RENDER_MCP_API_KEYin the Render Dashboard and restart the gateway from the Hermes Status tab.
Render on Hermes Setup
No Render CLI or MCP installation is required in the Hermes container. The Render MCP server is already registered as render with full access allowed by the supplied API key.
Required configuration:
- Add
RENDER_MCP_API_KEYunder Environment in the Render Dashboard. - Restart the gateway from the Hermes Status tab so the gateway can read the key.
- Confirm that the Render MCP server is available by calling:
mcp_render_list_services()
Do not run brew install render, an installer script, render login, or claude mcp add in this container. If an upstream skill recommends a Render CLI command, use an MCP equivalent when available. Otherwise, give the user the command to run from their own machine. Ask before installing a CLI or adding a separate RENDER_API_KEY.
Render on Hermes Data Schema & Taxonomy
Runtime configuration
| Item | Value or behavior |
|---|---|
| MCP server name | render |
| Hermes tool prefix | mcp_render_ |
| Transport | HTTP |
| MCP endpoint | https://mcp.render.com/mcp |
| Authentication | Authorization: Bearer ${RENDER_MCP_API_KEY} |
| Tool scope | Full scope permitted by the Render API key; no tools.include filter |
| CLI availability | Render CLI is not installed in the container |
Skill metadata
- Name:
render-on-hermes - Version:
1.0.0 - Author: Render
- License: MIT
- Tags: Render, MCP, Operations, Bootstrap, Security
- Related skills:
render-mcp,render-deploy,render-debug,render-monitor, andrender-blueprints - External bundle:
github.com/render-oss/skills, pinned to a commit and exposed throughskills.external_dirs
Workspace and resource data
Render MCP operations may require a selected workspace. Workspace context is discovered with mcp_render_get_selected_workspace, listed with mcp_render_list_workspaces, and selected with mcp_render_select_workspace. Resource data can include services, deployments, logs, metrics, environment variables, PostgreSQL queries, and other Render objects exposed by the API key.
Render on Hermes Advanced Features
- Full Render MCP tool access, including resource inspection and authorized mutations such as
restart_service,update_service,update_environment_variables,trigger_deploy,create_web_service, andquery_render_postgres. - Lazy environment-variable substitution keeps the MCP credential in the gateway environment instead of hardcoding it in the skill.
- Workspace-aware operations that distinguish between safe inspection and actions targeting a specific Render workspace.
- Automatic tool-name translation from generic upstream MCP names to Hermes names prefixed with
mcp_render_. - MCP-first fallback logic for logs, metrics, deployments, and service operations.
- Safe handling of CLI-only workflows by drafting local commands instead of attempting unavailable commands in the container.
- Compatibility with the broader Render skill bundle for deployments, debugging, monitoring, blueprints, databases, networking, scaling, migrations, and service types.
- Awareness that Hermes itself runs as a Render web service, helping agents avoid casually restarting the service that hosts the active session.
SKILL.md
Loading
Related Openclaw Skills
Browser Execution
Browser Execution completes direct browser tasks with Playwright, computer controls, secure vault handling, recovery tactics, and an explicit verified result.
HTML/CSS to Image API
Render HTML, CSS, public webpages, and reusable templates into high-quality images or PDFs through HCTI MCP tools.
Chuhaijiang TikTok Live Commerce Intelligence
A read-only TikTok live commerce research skill for discovering livestreams, analyzing session performance, and identifying products sold through Chuhaijiang.
Chuhaijiang TikTok Product Market Intelligence
A public TikTok Shop market intelligence skill for discovering products, analyzing performance, tracing promotion channels, and finding visually similar items.
QingTian Free Psychological Resources
A multilingual OpenClaw skill for discovering free psychological support, crisis resources, AI companions, and self-assessment tools worldwide.
People’s Court Dispute Intake
A structured intake workflow for preserving evidence and assessing whether a real bilateral transaction dispute is ready for manual People’s Court scoping.
Featured*
