Exa MCP connector for AI agents

Exa MCP tools for AI agents

CALL ANY TOOL

2 tools covering web.

examcp_web_fetch_exa

Read one or more webpages and return their full content as c

Read one or more webpages and return their full content as clean markdown. use when you have specific urls to read, or to get full content after a web search returns insufficient highlights. supports batching multiple urls in a single call.

Parameters

Name

Type

Required

Description

urls

array

Required

One or more URLs to fetch. Batch multiple URLs in a single call.

maxCharacters

number

Optional

Maximum characters to extract per page (default: 3000).

examcp_web_search_exa

Search the web and get clean, ready-to-use content. best for

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="examcp")

mcp = MultiServerMCPClient({
    "examcp": {
        "url": "https://mcp.scalekit.com/examcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

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

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "examcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/examcp
// Pass: Authorization: Bearer + token

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

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "examcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/examcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="examcp")
# Connect to MCP at https://mcp.scalekit.com/examcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Get started

Copy the prompt

Copied

Search the web and get clean, ready-to-use content?

Copy the prompt

Copied

Read one or more webpages and return their full content as clean markdown?

Advanced

Copy the prompt

Copied

Search the web and get clean, ready-to-use content?

Copy the prompt

Copied

Read one or more webpages and return their full content as clean markdown?

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

Authorize

Your user connects

Exa 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

Store

Their

Exa 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

Resolve

When your agent calls a

Exa 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

Audit

Every

Exa 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

See the same per-user auth pattern across other connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought.

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.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

“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 access Exa as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Exa API key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Exa?
Yes. Pass a tool name filter to listScopedTools so the AI agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Exa.

What happens when a user revokes Exa access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Whose Exa quota do semantic searches consume?
The authorizing user's. Web searches and fetches run on that user's Exa key from the vault, so research usage and cost stay attributable per person.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit