Skyvern MCP for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Skyvern MCP or direct API to create browser tasks, navigate websites, extract web data, and complete form-based workflows through natural language.

Skyvern logoSkyvern
Api Key

Skyvern is an AI browser automation platform for running tasks on websites. It helps teams automate messy web workflows without brittle scripts.

10 Tools

Try Skyvern now

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

TOOL ROUTER PLAYGROUND
Skyvern
Try asking
TOOLS

Supported Tools

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

Cancel Runs

Cancel one or more active task or workflow runs in one request and report which IDs succeeded or failed.

Create Folder

Create a folder for organizing Skyvern agents.

Delete Folder

Delete a Skyvern folder without deleting the agents it contains.

Get Folder

Get one Skyvern folder by ID, including its current agent count.

Get Run

Get current status, output, errors, files, and observation links for a task or workflow run.

List Agents

Search and list the latest versions of Skyvern agents available to the connected organization.

List Folders

Search and list folders used to organize Skyvern agents.

List Runs

Find task and workflow runs for the connected organization, with status, type, workflow, and text filters.

Start Browser Task

Start an autonomous browser task that can navigate and interact with websites, including clicking and submitting forms.

Update Folder

Change the title or description of an existing Skyvern folder.

SETUP GUIDE

Connect Skyvern 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: ["skyvern"],
  mcp: true,
});
Create a session scoped to Skyvern 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: "Create a Skyvern browser task to visit https://news.ycombinator.com and extract the top 5 story titles",
  stopWhen: stepCountIs(10),
});

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

Connect Skyvern 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: ["skyvern"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Skyvern
3

Run Skyvern tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Create a Skyvern browser task to visit https://news.ycombinator.com and extract the top 5 story titles" }],
});

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 Skyvern tool calls through the session, and print the final answer

Why Use Composio?

AI Native Skyvern Integration

  • Supports both Skyvern MCP and direct API based integrations
  • Structured, LLM-friendly schemas so agents can create and run browser automation tasks reliably
  • Rich coverage for launching workflows, checking task status, and working with extracted web data

Managed Auth

  • Securely stores Skyvern API keys instead of putting them in agent prompts or source code
  • Central place to manage, scope, and revoke Skyvern access across users and environments
  • Use auth_configs.create() and connected_accounts.link() to set up user-level Skyvern connections cleanly

Agent Optimized Design

  • Tools are shaped for AI agents that need to describe web tasks, pass URLs, and inspect results
  • Execution logs make it easy to see which Skyvern task ran, when it ran, and what the agent requested
  • Reliable tool schemas help reduce guesswork when agents trigger browser-based workflows

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Skyvern
  • Scoped, least privilege access for browser automation workflows
  • Full audit trail of agent actions to support review, debugging, and compliance
FAQ

Frequently asked questions

Yes, Skyvern 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 Skyvern.It takes 30 seconds.

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

Start building