CONNECT APP
Build with Exa
Artificial Intelligence (AI)
- API key
MCP
Give your agent Exa tools
Every Exa action is exposed as an MCP tool on Pipedream's remote server. Point a client at it with your end user's ID and Connect resolves that user's Exa account for each tool call — you store no tokens.
// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
new URL("https://remote.mcp.pipedream.net/v3"),
{
requestInit: {
headers: {
Authorization: `Bearer ${accessToken}`,
"x-pd-project-id": "{project_id}",
"x-pd-environment": "production",
"x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
"x-pd-app-slug": "exa",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// e.g. run Answer Question:
const result = await mcp.callTool({
name: "exa-answer-question",
arguments: {
query: "Question",
text: true,
},
})# access_token: mint a short-lived token with the Connect SDK — see the MCP guide
headers = {
"Authorization": f"Bearer {access_token}",
"x-pd-project-id": "{project_id}",
"x-pd-environment": "production",
"x-pd-external-user-id": "{external_user_id}", # any stable ID for this user in your system
"x-pd-app-slug": "exa",
}
async with streamablehttp_client("https://remote.mcp.pipedream.net/v3", headers=headers) as (read, write, _):
async with ClientSession(read, write) as session:
await session.initialize()
tools = await session.list_tools()
# e.g. run Answer Question:
result = await session.call_tool("exa-answer-question", {
"query": "Question",
"text": True,
})API PROXY
Call the Exa API directly
For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Exa API with the connected user's credentials attached. You store no tokens and write no refresh logic.
const resp = await pd.proxy.get({
externalUserId: "{external_user_id}", // any stable ID for this user in your system
accountId: "apn_xxxxxxx",
url: "https://api.exa.ai/search",
})
// Any allowed Exa endpoint works here. Pipedream attaches the
// connected account's credentials to the outgoing request.# The path segment is the target URL, URL-safe base64 encoded:
# https://api.exa.ai/search
curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkuZXhhLmFpL3NlYXJjaA?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
-H "Authorization: Bearer {access_token}" \
-H "x-pd-environment: production"SDK
Run Exa actions from your backend
Connect a user's Exa account once, then run Answer Question on their behalf from your own code — TypeScript, Python, or plain HTTP.
import { PipedreamClient } from "@pipedream/sdk"
const pd = new PipedreamClient({
projectId: process.env.PIPEDREAM_PROJECT_ID!,
clientId: process.env.PIPEDREAM_CLIENT_ID!,
clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
projectEnvironment: "production",
})
const result = await pd.actions.run({
id: "exa-answer-question",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
exa: { authProvisionId: "apn_xxxxxxx" },
query: "Question",
text: true,
},
})from pipedream import Pipedream
pd = Pipedream(
client_id="{oauth_client_id}",
client_secret="{oauth_client_secret}",
project_id="{project_id}",
project_environment="production",
)
result = pd.actions.run(
id="exa-answer-question",
external_user_id="{external_user_id}", # any stable ID for this user in your system
configured_props={
"exa": {"authProvisionId": "apn_xxxxxxx"},
"query": "Question",
"text": True,
},
)curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
-H "Content-Type: application/json" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}" \
-d '{
"external_user_id": "{external_user_id}",
"id": "exa-answer-question",
"configured_props": {
"exa": { "authProvisionId": "apn_xxxxxxx" },
"query": "Question",
"text": true
}
}'TOOLS
Exa actions
On-demand operations your product or agent can configure and run on behalf of a connected user.
-
Answer Question
actionGenerate grounded Exa answers with citations. Use this when you want an answer-shaped response instead of raw search results. See the documentationRead-onlyv0.1.1 -
Find Similar Links
actionFind pages similar to a seed URL with optional nested Exa content extraction. This action is deprecated for new workflows. Prefer Search, optionally after Get Contents on the seed URL, for related-page discovery. See the documentationRead-onlyv0.1.2 -
Get Contents
actionRetrieve clean text, highlights, summaries, and metadata for specific URLs or Exa document IDs. Highlights are the recommended default extraction mode for most workflows. See the documentationRead-onlyv0.1.1 -
Search
actionSearch the web with Exa.autois the recommended search type, and Highlights is the recommended default content mode. See the documentationRead-onlyv0.1.1
No Exa triggers are available yet.
MULTI-APP
Use Exa with other popular apps
Most products don't stop at one integration. Pair Exa with the other apps your users rely on, and ship use cases that span both.
- App slug
- exa
- Authentication
- API key
- Categories
- Artificial Intelligence (AI)
- Actions
- 4
- Triggers
- 0
- API proxy
- Available