AI agents & MCP
Give your agent the open web, safely.
A native MCP server, per-session budgets, citations on every fetch, and the same endpoints your humans use. Your agents don't need a custom scraper; they need a contract that says "this is the web, here's your budget."
12
tools, native MCP
60s
install to first call
100%
cited responses
$0
beyond your budget cap
What you actually need
The hard parts, already solved.
Native MCP, not a wrapper
Real Model Context Protocol. Tools, resources, prompts. Works with Claude Desktop, Cursor, VS Code, Windsurf, plus the OpenAI Agents SDK and Google ADK in Python.
Per-session budget caps
Cap how many credits an agent can burn per session (an <code>X-Ujeebu-Budget</code> header on the hosted endpoint, or <code>UJEEBU_BUDGET</code> when self-hosting with Docker). Hard stop at the limit. No nightmare bills from a runaway eval loop.
Citations built in
Every tool result includes source URL, fetch timestamp, credit cost. Your agent can ground its claims; you can audit every step.
12 tools, typed
<code>scrape</code> (html/screenshot/pdf/json/rules), <code>extract</code>, <code>card</code>, <code>serp</code>, <code>markdown</code>, <code>chatgpt</code>, <code>gemini</code>, <code>account</code>. Full JSON Schema on each, so the agent picks the right tool the first time.
Streaming responses
For long fetches, results stream into the agent's context as they arrive, so the model can reason on partial results before the full call returns.
Agent-friendly auth
One API key: in the <code>Authorization</code> header for the hosted endpoint, or <code>UJEEBU_KEY</code> when self-hosting. The same key works for the REST API.
The pipeline
4 steps. One pipeline.
01
Install
Drop the config into your MCP host or use the one-click installers in the <a href="/mcp" class="uj-accent-text">setup wizard</a>. 60 seconds to first tool call from Claude Desktop, Cursor, VS Code, Windsurf, OpenAI Agents, or Google ADK.
02
Cap
Set a credit budget for the session in the MCP config. The server refuses calls beyond it, and blocked requests, timeouts and server errors are not billed.
03
Run
The agent picks tools by JSON Schema, executes them, and reasons over typed results. Streaming keeps long fetches responsive.
04
Audit
Every call logged with tool, args, response, citation, cost. Reproduce any agent step exactly. Critical for evals + customer-facing AI.
full pipeline · 30 lines
// claude_desktop_config.json
{
"mcpServers": {
"ujeebu": {
"url": "https://mcp.ujeebu.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY",
"X-Ujeebu-Budget": "5000"
}
}
}
}
// In Claude:
> Compare React Aria, Radix, Headless UI,
> and Reach UI on accessibility primitives.
🛠 ujeebu.serp({ q:"react aria vs radix" })
🛠 ujeebu.extract(url:"github.com/...") ×4
🛠 ujeebu.markdown(url:"docs/aria") ×4
// Agent reasons over the typed results,
// cites every claim, stops at 5000 credits.Give your agent web access
One API key for pages, articles, Markdown and Google results
Plug it in through MCP or call the REST API. 5,000 free credits for 7 days, no card.
Endpoints in play
Use what fits. Skip what doesn’t.
MCP server
The protocol surface. One endpoint, twelve tools, every MCP host.
Scrape
Render any URL with JS execution. Screenshot and PDF as parameters.
Extract
Returns an article's title, author, date, text and images as clean JSON, with no selectors.
SERP
Web search as a typed tool. Geo-targetable. CAPTCHA-free.
Markdown
When the agent needs to read a long doc, not just snippet it. Clean, LLM-ready Markdown.
ChatGPT
Ask ChatGPT one prompt and get its answer as JSON, with the cited links when web search is on.
Gemini
Ask Google Gemini one prompt and get its answer as JSON.
Common questions
Giving an AI agent web access, answered.
How do I give an AI agent access to the live web?
Connect the Ujeebu MCP server. The fastest way is our hosted endpoint - add <code>{ "url": "https://mcp.ujeebu.com/mcp", "headers": { "Authorization": "Bearer ..." } }</code> to your MCP host config (Claude Desktop, Cursor, VS Code, Windsurf); nothing to install. Prefer to self-host? Run <code>docker run -i --rm -e UJEEBU_KEY ujeebu/ujeebu-mcp</code> and point the config at that instead. Either way the agent gets twelve typed tools (<code>scrape</code> in five variants, plus <code>extract</code>, <code>card</code>, <code>serp</code>, <code>markdown</code>, <code>chatgpt</code>, <code>gemini</code>, <code>account</code>) and can fetch, search, and read the web through a single API key. The <a href="/mcp">setup wizard</a> generates one-click install links for Cursor and VS Code, copy-paste configs for the rest, and Python snippets for the OpenAI Agents SDK and Google ADK.
What is an MCP server for web scraping?
MCP (Model Context Protocol) is the open standard for connecting AI agents to external tools. Ujeebu ships a native MCP server, not a wrapper, that exposes its scraping, search, and extraction endpoints as typed tools with full JSON Schema, so the agent picks the right tool the first time. It works with any MCP-compatible client.
How do I stop an agent from running up a huge scraping bill?
Cap the per-session spend in the MCP config: on the hosted endpoint add an <code>X-Ujeebu-Budget</code> header, or when self-hosting with Docker set <code>UJEEBU_BUDGET</code> in the env. When the budget is used up, the server refuses further calls, so a runaway eval loop stops there. Blocked requests, timeouts and server errors are not billed; 404 Not Found responses are. The <code>account</code> tool lets an agent check its remaining credits before a large batch.
Can the agent cite its sources?
Yes. Every tool result includes the source URL, the fetch timestamp, and the credit cost. The agent can ground each claim in a real source, and you get an audit trail of exactly which pages were fetched, when, and at what cost.
Does Ujeebu work with Claude, Cursor, VS Code, OpenAI Agents, and Google ADK?
Yes. The MCP server works with Claude Desktop, Cursor, VS Code, Windsurf, and any other MCP-compatible host. The OpenAI Agents SDK (<code>MCPServerStreamableHttp</code>, or <code>MCPServerStdio</code> to self-host) and Google ADK (<code>MCPToolset</code>) connect with a short snippet. See <a href="/docs/mcp">the setup guide</a> for the exact code per host. If you are not using MCP at all, the same capabilities are available as plain REST endpoints at <code>https://api.ujeebu.com</code> using the <code>ApiKey</code> header.
How much does it cost to give an agent web access?
Start free with 5,000 credits and no credit card on a 7-day trial. One credit pool is shared across every endpoint, so you do not commit budget to one tool. Blocked requests, timeouts and server errors are not billed; 404 responses are. See <a href="/pricing">/pricing</a> for plans; top-ups work on every plan, including the trial.
Can an agent extract structured data without me writing selectors?
Yes. The <code>scrape</code> tool takes <code>extract_rules</code> (CSS or XPath) and returns exactly the fields you name as JSON. For articles, the <code>extract</code> tool returns title, author, date, text and images with no selectors. The <code>markdown</code> tool returns clean, LLM-ready Markdown of any page.
How does Ujeebu handle anti-bot protection and JavaScript-heavy pages?
It is handled server-side. Ujeebu renders pages with a real headless Chrome browser, executes JavaScript, and routes through rotating, premium, residential, or mobile proxies with geo-targeting, built on years of anti-bot infrastructure. The agent never has to manage a browser or proxy pool itself.