Integration

Algodocs integration

Algodocs extracts structured data from invoices, receipts, bank statements, purchase orders and other PDFs or images, using extractors configured in the Algodocs dashboard. An agent can list extractors and folders, upload a document (a stored file, a public URL or base64 content) to an extractor and folder, then read the extracted fields with download links to Excel, JSON, XML, TXT and CSV outputs, for one document or for every document of an extractor. Extraction is asynchronous: read the result again until its data is populated. Authentication is the Secret API key from app.algodocs.com/restapi, sent in the x-api-key header.

Connect Algodocs How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Algodocs.Built from the 8 Algodocs tools below, on the connection you add once.

What you can do with Algodocs

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Extracted data, 2 operations

get_document_extracted_dataGet document extracted dataGETReturns the extraction result of one document as a list (one record per page or split record). If processing is still running, call again later until data is populated.
list_extracted_dataList extracted dataGETReturns the extraction records of every document processed by an extractor, one record per page or split record. Filter with folderId and date, cap with limit.

Extractor, 1 operation

list_extractorsList extractorsGETLists every extractor on the account (id and name). Pass an extractor id when uploading a document so Algodocs knows which fields to pull.

Folder, 1 operation

list_foldersList foldersGETLists the folder tree used to organize documents: parentId is null for the root folder and references another folder's id otherwise.

Me, 1 operation

get_current_userGet current userGETReturns the full name and email of the account tied to the API key. Handy as a check that the credential works.

Upload base64, 1 operation

upload_base64Upload base64POSTUploads a base64-encoded file for extraction and returns the new document id. Processing is asynchronous: then read the result with get_document_extracted_data.

Upload local, 1 operation

upload_local_fileUpload local filePOSTUploads a PDF or image file for extraction and returns the new document id. Processing is asynchronous: then read the result with get_document_extracted_data.

Upload url, 1 operation

upload_from_urlUpload from urlPOSTMakes Algodocs fetch a document from a public URL for extraction and returns the new document id. Processing is asynchronous: then read the result with get_document_extracted_data.

Use Algodocs from Claude Code, Cursor or Codex

Connect Algodocs in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Algodocs operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Algodocs

Create your workspace
Sign up free. Nothing to install.
Connect Algodocs once
Add your Algodocs connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.