Notion ACTION
Search
Search Notion for pages and databases (data sources) by title. Use this first to resolve a page or database name into an ID that the other Notion tools require (e.g. Query Data Source, Retrieve Database Schema, Get Page, Create Page). Leave
query blank to list everything the integration can access. Set filter to data_source to find databases or page to find pages — on the current Notion API a database is returned as a data_source object, and its id is the data source ID you pass to the database tools. See the documentation- Action
- Read only
- OAuth
- SDK
- MCP
IMPLEMENTATION
Call this tool
Connect a user's Notion account once, then configure and run Search from your backend or agent.
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: "notion-search",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
notion: { authProvisionId: "apn_xxxxxxx" },
query: "Query",
filter: "Object Type",
},
})
console.log(result)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": "notion-search",
"configured_props": {
"notion": { "authProvisionId": "apn_xxxxxxx" },
"query": "Query",
"filter": "Object Type"
}
}'// 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": "notion",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
name: "notion-search",
arguments: {
query: "Query",
filter: "Object Type",
},
})SCHEMA
Inputs
Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.
| Property | Type | Description |
|---|---|---|
query Query | string | Text to match against page and data source titles. Leave blank to return all accessible objects. Optional |
filter Object Type | string | Restrict results to page or data_source (database). Omit to return both. Optional |
pageSize Page Size | integer | The number of items from the full list desired in the response (max 100) Optional |
startCursor Start Cursor (page_id) | string | Pagination cursor from a previous response's next_cursor. Omit for the first page. Optional |
REFERENCE
Tool details
Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.
- Registry key
- notion-search
- Version
- 1.0.1
- App
- Notion
- Authentication
- OAuth
- Read-only
- Yes
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗