Unstructured ACTION
Extract File
Extract data from a file. See the documentation
- Action
- Read only
- API key
- SDK
- MCP
IMPLEMENTATION
Call this tool
Connect a user's Unstructured account once, then configure and run Extract File 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: "unstructured-extract-file",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
unstructured: { authProvisionId: "apn_xxxxxxx" },
file: "File Path or URL",
coordinates: true,
},
})
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": "unstructured-extract-file",
"configured_props": {
"unstructured": { "authProvisionId": "apn_xxxxxxx" },
"file": "File Path or URL",
"coordinates": true
}
}'// 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": "unstructured",
},
},
},
)
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: "unstructured-extract-file",
arguments: {
file: "File Path or URL",
coordinates: true,
},
})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 |
|---|---|---|
file File Path or URL | string | The file to extract data from. Provide either a file URL or a path to a file in the /tmp directory (for example, /tmp/myFile.pdf) Required |
coordinates Extract Coordinates | boolean | If true, return coordinates for each element extracted via OCR Optional |
encoding Encoding | string | The encoding method used to decode the text input. Default: utf-8 Optional |
includePageBreaks Include Page Breaks | boolean | If true, the output will include page breaks if the filetype supports it Optional |
strategy Strategy | string | The strategy to use for partitioning PDF/image Optional |
outputFormat Output Format | string | The format of the response Optional |
startingPageNumber Starting Page Number | integer | When PDF is split into pages before sending it into the API, providing this information will allow the page number to be assigned correctly Optional |
vlmModelProvider VLM Model Provider | string | The VLM Model provider to use Optional |
vlmModel VLM Model | string | The VLM Model to use. Example: gpt-4o Optional |
syncDir SyncDir | dir | 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
- unstructured-extract-file
- Version
- 0.0.1
- App
- Unstructured
- Authentication
- API key
- Read-only
- Yes
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗