Exa

Live

API KEY

SEARCH

Every semantic search query, web result, and page extract your agent needs. Exa MCP gives your agent authenticated access to AI-native search scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Exa account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Exa
agent · Acme Q3
Run
Find the latest research on AI agent frameworks published in the last 30 days.
S
exa_search_and_contents
94ms
Research agent
12 results. Top: LangGraph 0.4 paper (arXiv, Oct 29), OpenAI Swarm benchmark (Oct 27), DeepMind AlphaAgent (Nature, Oct 24), Anthropic MCP spec v1.1 (Oct 21).
Sources: 12 web results, last 30 days
examcp
12 results
18:29
Message Claude...

Tools your research agent reaches for on Exa, scoped per user.

CALL ANY TOOL
Run semantic and keyword searches, extract page contents, and find similar URLs across the web.
exa_search
Search
Run a semantic or keyword search and return ranked results with URLs and highlights.
Parameters
Name
Type
Required
Description
query
string
Required
Search query
num_results
integer
Optional
Number of results (default 10)
type
string
Optional
Search type: neural, keyword, or auto
use_autoprompt
boolean
Optional
Optimize query with Exa autoprompt
include_domains
array
Optional
Restrict to these domains
start_published_date
string
Optional
ISO 8601 — only return content published after
exa_find_similar
Find similar
exa_get_contents
Get contents
exa_search_and_contents
Search and get contents
Build your Agent
Drop the toolkit in, point it at the user, and your research agent can use Exa 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: ["exa"], toolNames: ["exa_search", "exa_find_similar", "exa_get_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: ["exa"], toolNames: ["exa_search", "exa_find_similar", "exa_get_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: ["exa"], toolNames: ["exa_search", "exa_find_similar", "exa_get_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/exa",
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 using Exa.
Web & news
Copy the prompt
Copied
Search for [topic] published this month.
Copy the prompt
Copied
Find the latest papers on [research area].
Copy the prompt
Copied
Search news from [domain] this week.
Copy the prompt
Copied
Get the content of [URL].
Research & sourcing
Copy the prompt
Copied
Find pages similar to [URL].
Copy the prompt
Copied
Search case studies on [industry trend].
Copy the prompt
Copied
Pull recent mentions of [company] online.
Copy the prompt
Copied
Find [competitor] product launches this quarter.
Deep extraction
Copy the prompt
Copied
Search and extract full text: [query].
Copy the prompt
Copied
Find top 5 results on [topic] with highlights.
Copy the prompt
Copied
Get contents of these URLs: [url1], [url2].
Copy the prompt
Copied
Search [keyword] restricted to [domain].
SEE HOW AUTH WORKS
Users authorize Exa once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Exa
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
Exa
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
Exa
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
Exa
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 research agents and MCP connectors. Working code, live demos, fork what fits.
SALES
Outbound prospecting agent
Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.
SALES
Sales call prep agent
Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.
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.
Search quota consumed under the wrong identity
A shared Exa API key looks fine in a demo. In production, every search query burns quota against a service account. Per-user rate limits and result caching collapse. Scalekit resolves the user's key so search runs under the right identity.
// shared API key
key = "exa_shared_xxx"
audit → bot_service_account
quota_filter → broken

// scalekit · per-user
key = resolve(user_id)
audit → user_abc
scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Exa 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
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?
Can I limit what the agent is allowed to do in Exa?
What happens when a user revokes Exa access?
Are Exa search results shared or cached across users?
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""exa"": {
""url"": ""https://mcp.scalekit.com/exa"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.exa]
url = ""https://mcp.scalekit.com/exa""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""exa"": {
""url"": ""https://mcp.scalekit.com/exa"",
""type"": ""http""
}
}
}