Screenshot API MCP for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Screenshot API MCP or direct API to capture webpages, render HTML to PDFs, extract page content, and run bulk screenshot jobs through natural language.

Screenshot API logoScreenshot API
Api Key

Screenshot API is a web rendering service that turns webpages and custom HTML into images, PDFs, videos, or extracted content. It saves you from running browser infrastructure while supporting async bulk capture jobs at scale.

5 Tools

Try Screenshot API now

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

TOOL ROUTER PLAYGROUND
Screenshot API
Try asking
TOOLS

Supported Tools

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

Create Bulk CSV Job

Upload a CSV file to start a paid asynchronous bulk screenshot job and return the provider's complete job acceptance payload containing its UUID.

Create Bulk JSON Job

Start a paid asynchronous bulk screenshot job from up to 50 JSON request items and return the provider's complete job acceptance payload containing its UUID.

Download Bulk Results

Download the processed result CSV for a completed paid bulk screenshot job UUID.

Get Bulk Job Status

Get progress and success/failure counts for a paid asynchronous bulk screenshot job UUID.

Render Screenshot

Render a webpage or custom HTML and return a stored image, PDF, or video URL plus optional extracted content links.

SETUP GUIDE

Connect Screenshot API 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: ["screenshot_api"],
  mcp: true,
});
Create a session scoped to Screenshot API 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: "Capture https://example.com as a full-page PNG screenshot",
  stopWhen: stepCountIs(10),
});

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

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

Run Screenshot API tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Capture https://example.com as a full-page PNG screenshot" }],
});

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 Screenshot API tool calls through the session, and print the final answer

Why Use Composio?

AI Native Screenshot API Integration

  • Supports both Screenshot API MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable screenshot, PDF, video, and extraction tasks
  • Rich coverage for rendering webpages, custom HTML, and async bulk capture workflows

Managed Auth

  • Secure API key handling without hard-coding Screenshot API credentials in your agent code
  • Central place to manage, scope, and revoke Screenshot API access
  • Per user and per environment credentials, so dev, staging, and production stay cleanly separated

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve capture reliability over time
  • Clear inputs for common jobs like full-page screenshots, PDF rendering, HTML capture, and content extraction
  • 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 Screenshot API
  • Scoped, least privilege access to Screenshot API rendering and capture workflows
  • Full audit trail of agent actions to support review, debugging, and compliance
FAQ

Frequently asked questions

Yes, Screenshot API 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 Screenshot API.It takes 30 seconds.

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

Start building