You.com MCP connector for AI agents

CALL ANY TOOL

Search the web and news, run deep research, extract page content as markdown or HTML. Same toolkit, every framework, no auth plumbing.

youmcp_you_search

Web and news search

Search the web and news using You.com with snippet results, source URLs, and recency filters.

Parameters

Name

Type

Required

Description

query

string

Required

Search query

type

string

Optional

web, news, or both

freshness

string

Optional

day, week, month, year

youmcp_you_research

Deep research

youmcp_you_contents

Extract page contents

Build your Agent

Drop the toolkit in, point it at the user, and your agent can search the web and run research from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["youmcp"], toolNames: ["youmcp_you_search", "youmcp_you_research", "youmcp_you_contents"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["youmcp"], toolNames: ["youmcp_you_search", "youmcp_you_research", "youmcp_you_contents"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["youmcp"], toolNames: ["youmcp_you_search", "youmcp_you_research", "youmcp_you_contents"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/youmcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start grounding answers on real-time web data.

Search & news

Copy the prompt

Copied

Search the web for the latest on [topic].

Copy the prompt

Copied

Find news from the past week about [company].

Copy the prompt

Copied

What are the top results for [query] this month?

Research & extraction

Copy the prompt

Copied

Research [topic] in depth and cite your sources.

Copy the prompt

Copied

Extract the main content from [URL] as markdown.

Copy the prompt

Copied

Compare what these three pages say about [topic]: [url1], [url2], [url3].

SEE HOW AUTH WORKS

Users authorize You.com once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

You.com MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

You.com MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

You.com MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

You.com MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other search and research connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

You.com MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent search You.com as the user or a shared key?

As the user. Each account authorizes once and Scalekit resolves their API key at request time. Search and research calls are attributed to that user.

Where is the You.com API key stored?

In Scalekit's AES-256 vault, namespaced per tenant. Tokens never appear in prompts or LLM context.

Can I limit the agent to web search only, no deep research?

Yes. Use listScopedTools to allow only you_search and you_contents while excluding you_research.

What happens when a user revokes You.com access?

The connection is invalidated on the next tool call. Subsequent requests fail closed with a clear error.

Can the agent combine You.com results with internal data in one workflow?

Yes. A single agent can search You.com for external context and another connector for internal data in the same workflow, each using the same user identity.

You.com MCP

Tools your agent reaches for on You.com MCP, scoped per user.