How to integrate RunPod MCP with Antigravity

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

RunPod logo
Antigravity logo
divider

How to integrate RunPod MCP with Antigravity

Antigravity IDE is Google's agentic IDE, built on a VS Code-style editor and powered by models like Gemini 3.5 Flash, Gemini 3.1 Pro, Opus 4.6, and more. It treats the AI agent as a first-class teammate, planning, coding, and validating work through an Agent Manager dashboard with deep browser connectivity.

In this guide, I will explain the easiest and most secure way to connect your RunPod account to Antigravity IDE via Composio Connect, so it can launch a new GPU pod for inference, get status of all active pods, stop a running pod with ID 12345, and more without ever putting your account credentials at risk.

Also integrate RunPod with

Why use Composio?

Composio provides:

  • Access to 1,000+ managed apps from a single MCP endpoint. This makes it convenient for agents to run cross-app workflows.
  • Programmatic tool calling. Allows LLMs to write code in a remote workbench to handle complex tool chaining. Reduces to-and-fro with LLMs for frequent tool calling.
  • Large tool response handling outside the LLM context. This minimizes context bloat from large tool responses.
  • Dynamic just-in-time access to thousands of tools across hundreds of apps. Composio loads the tools your agent needs, so LLMs are not overwhelmed by tools they do not need.

Connect RunPod to Antigravity

Antigravity does not ship with one-click custom MCP install links yet, so configuration goes through the IDE's raw config file. The process takes under a minute.

1. Open the MCP Config

Go to Antigravity Settings, open the Customizations tab, then click Open MCP Config to open mcp_config.json in the editor.

Antigravity Customizations settings with Open MCP Config button

2. Get your API key

Go to the Composio Dashboard and copy your API key.

Composio Dashboard showing where to get the API key

3. Add Composio to mcp_config.json

Paste the following configuration into the file:

bash
{
  "mcpServers": {
    "remote-composio": {
      "serverUrl": "https://connect.composio.dev/mcp",
      "headers": {
        "x-consumer-api-key": "your-composio-api-key"
      }
    }
  }
}

Note: Antigravity uses serverUrl, not url, for remote HTTP-based MCP servers. This differs from the url key used in Cursor and VS Code configs.

Save the file and click refresh in the Installed MCP Servers section.

Antigravity showing Composio tools after MCP setup

Connect your RunPod account

Back in the Antigravity agent panel, ask the agent to connect to RunPod or give it any RunPod-related task.

For example, ask it to:

  • "Launch a new GPU pod for inference"
  • "Get status of all active pods"
  • "Stop a running pod with ID 12345"

It will prompt you to authenticate and authorize access to RunPod.

That is it. Composio tools are now available in Antigravity, and your RunPod account is ready to use.

Supported Tools & Triggers

Tools
Create RunPod ClusterTool to create a new GPU cluster for multi-node distributed computing workloads on RunPod.
Create SecretTool to create a new secure secret in RunPod for credential management.
Delete Container Registry AuthenticationTool to delete container registry authentication from RunPod.
Delete TemplateTool to remove a RunPod template via GraphQL mutation.
Get GPU TypesTool to retrieve available GPU types and their specifications, pricing, and availability from RunPod.
Get authenticated user infoRetrieve basic information about the authenticated user including ID, email, and security settings.
Get Pod DetailsRetrieve details of a specific RunPod pod by its unique pod ID.
List CPU TypesTool to retrieve available CPU types and their specifications from RunPod.
Save Serverless EndpointTool to create or update a RunPod serverless endpoint with GPU configuration and scaling settings.
Save Container Registry AuthenticationTool to save container registry authentication credentials for accessing private Docker images in RunPod.
Save TemplateTool to create a new RunPod template or update an existing one with container configuration.
Update Registry AuthTool to update existing container registry authentication credentials in RunPod.
Update User SettingsTool to update current user settings (e.

Conclusion

You have successfully connected RunPod to Antigravity using Composio Connect. Your agent can now use RunPod securely without exposing credentials in prompts or local scripts.

How to build RunPod MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and RunPod MCP?

With a standalone RunPod MCP server, the agents and LLMs can only access a fixed set of RunPod tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from RunPod and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Antigravity?

Yes, you can. Antigravity fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right RunPod tools.

Can I manage the permissions and scopes for RunPod while using Tool Router?

Yes, absolutely. You can configure which RunPod scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your RunPod data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.