Intelligent Document Processing - AI-Powered Document Data Extraction

MCPAPI

What your agent can do

  • Lists documents for a given extractor by reading extraction records (GET /v1/extracted_data/{extractorId}) and returning their documentId and fileName, deduplicated by documentId. AlgoDocs has no dedicated documents endpoint, so this action derives the document list from extracted data. Use it to… Full schema: https://pipedream.com/apps/algodocs/actions/list-documents.md

    Via MCP.

Tasks depend on the interface and permissions.

Connection methods

Choose a route that fits your agent.

MCP connection
MCP server URL
https://remote.mcp.pipedream.net/v3

Authentication
Provide the Pipedream Connect access token and the documented project, environment, external-user and app-slug headers; provider account connection may be required.
POST https://remote.mcp.pipedream.net/v3
API connection
API path
https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkuYWxnb2RvY3MuY29tL3YxL21l?external_user_id={external_user_id}&account_id=apn_xxxxxxx

Authentication
Send a Pipedream Connect access token; Pipedream forwards the connected account credentials to the upstream provider.

Documentation & experience

  • 2 connection paths
View sources and checks
How documentation is checked