RunPod MCP for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with RunPod MCP or direct API to launch pods, monitor GPU usage, manage jobs, and query pod status through natural language.

RunPod logoRunPod
Api Key

RunPod is a GPU cloud platform designed for AI and machine learning workloads. Instantly access scalable compute power for demanding AI tasks.

13 Tools

Try RunPod now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
RunPod
Try asking
TOOLS

Supported Tools

Every RunPod action and event your agent gets out of the box.

Create RunPod Cluster

Tool to create a new GPU cluster for multi-node distributed computing workloads on RunPod.

Create Secret

Tool to create a new secure secret in RunPod for credential management.

Delete Container Registry Authentication

Tool to delete container registry authentication from RunPod.

Delete Template

Tool to remove a RunPod template via GraphQL mutation.

Get GPU Types

Tool to retrieve available GPU types and their specifications, pricing, and availability from RunPod.

Get authenticated user info

Retrieve basic information about the authenticated user including ID, email, and security settings.

Get Pod Details

Retrieve details of a specific RunPod pod by its unique pod ID.

List CPU Types

Tool to retrieve available CPU types and their specifications from RunPod.

Save Serverless Endpoint

Tool to create or update a RunPod serverless endpoint with GPU configuration and scaling settings.

Save Container Registry Authentication

Tool to save container registry authentication credentials for accessing private Docker images in RunPod.

Save Template

Tool to create a new RunPod template or update an existing one with container configuration.

Update Registry Auth

Tool to update existing container registry authentication credentials in RunPod.

Update User Settings

Tool to update current user settings (e.

SETUP GUIDE

Connect RunPod MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["runpod"],
  mcp: true,
});
Create a session scoped to RunPod and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Launch a new GPU pod for stable diffusion training",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a RunPod request
SETUP GUIDE

Connect RunPod API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["runpod"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to RunPod
3

Run RunPod tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Launch a new GPU pod for stable diffusion training" }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the RunPod tool calls through the session, and print the final answer

Why Use Composio?

AI Native RunPod Integration

  • Supports both RunPod MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable tool execution
  • Rich coverage for reading, writing, and querying your RunPod data

Managed Auth

  • Built-in OAuth handling with automatic token refresh and rotation
  • Central place to manage, scope, and revoke RunPod access
  • Per user and per environment credentials instead of hard-coded keys

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Comprehensive execution logs so you always know what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access RunPod
  • Scoped, least privilege access to RunPod resources
  • Full audit trail of agent actions to support review and compliance
FAQ

Frequently asked questions

Yes, RunPod requires you to configure your own API key credentials. Once set up, Composio handles secure credential storage and API request handling for you.

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. Learn more.

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

Start with RunPod.It takes 30 seconds.

Managed auth, hosted MCP servers, and every RunPod tool your agent needs.Free to start.

Start building