Screenshotbase MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Screenshotbase MCP or direct API to render URLs, convert HTML and Markdown, create PDFs, and track asynchronous jobs through natural language.

Screenshotbase logoScreenshotbase
Api Key

Screenshotbase is a rendering service for turning URLs, HTML, and Markdown into images, PDFs, and finished documents. It simplifies reliable, asynchronous content rendering through a single API.

8 Tools

Try Screenshotbase now

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

TOOL ROUTER PLAYGROUND
Screenshotbase
Try asking
TOOLS

Supported Tools

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

Delete Render Job

Cancel and delete one asynchronous render job and its stored result.

Download Render Job Result

Retrieve the retained output of a completed asynchronous render job in the representation selected when the job was created.

Get Account Status

Return the connected Screenshotbase account's active plan and current monthly and grace render quota usage.

Get Render Job

Get the current status, result metadata, or failure details for one asynchronous render job.

List Rendering Devices

List every documented device profile that can be passed to the render action's viewport_device field.

List Render Jobs

Return one newest-first page of asynchronous render jobs, optionally filtered by status, with a cursor for older jobs.

Render Content with POST

Render a URL, supplied HTML, or supplied Markdown through POST as an image, PDF, Markdown, SVG, or rendered HTML.

Render URL with GET

Render a public URL through Screenshotbase's URL-only GET /v1/take operation as an image, PDF, Markdown, SVG, or rendered HTML, optionally as an async job.

SETUP GUIDE

Connect Screenshotbase 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: ["screenshotbase"],
  mcp: true,
});
Create a session scoped to Screenshotbase 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: "Render https://example.com as a 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 Screenshotbase request
SETUP GUIDE

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

Run Screenshotbase tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Render https://example.com as a 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 Screenshotbase tool calls through the session, and print the final answer

Why Use Composio?

AI Native Screenshotbase Integration

  • Supports both Screenshotbase MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable URL, HTML, and Markdown rendering
  • Rich coverage for creating images and PDFs and checking asynchronous render jobs

Managed Auth

  • Securely connect your own Screenshotbase API key without hard-coding it into agent prompts
  • Central place to manage, scope, and revoke Screenshotbase access
  • Per user and per environment credentials for safer development and production deployments

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve rendering reliability over time
  • Clear inputs and outputs help agents submit render jobs and retrieve results correctly
  • Comprehensive execution logs show what ran, when, and on whose behalf

Enterprise Grade Security

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

Rolling this out across your team?

Give your team centralized access control across every framework with Composio’s MCP Gateway.

EXPLORE MCP GATEWAY
FAQ

Frequently asked questions

Start with Screenshotbase.It takes 30 seconds.

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

Start building