Integration

AskYourPDF integration

AskYourPDF lets an agent ask questions about PDF documents. Add a document by uploading a PDF or giving a public PDF URL, then chat with it (one document, or several grouped in a knowledge base), summarise a document or a piece of text, retrieve the raw passages most relevant to a query, and list, read and delete documents and knowledge bases. Answers come back whole: the streaming mode is not exposed, nor are the API key management and usage routes (they need a dashboard login) or the deprecated multi-document chat route. Authentication is an API key generated on the AskYourPDF developer page, sent in the x-api-key header.

Connect AskYourPDF How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in AskYourPDF.Built from the 18 AskYourPDF tools below, on the connection you add once.

What you can do with AskYourPDF

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.

Document, 8 operations

add_document_from_urlAdd document from urlGETAdds a document to your account from a public PDF URL (AskYourPDF downloads it) and returns its docId. Pass that docId as doc_id to chat_with_document or summarize_document.
chat_with_documentChat with documentPOSTAsks a question about one document and returns the answer (answer.message). Send the conversation in items: optional system message, earlier turns, then the user's question last.
delete_documentDelete documentDELETEPermanently deletes a document from your AskYourPDF account.
get_documentGet documentGETReturns one document's details: name, summary, language, number of pages and when it was added.
list_documentsList documentsGETLists the documents in your AskYourPDF account, one page at a time (total_pages says how many pages exist).
search_document_contextSearch document contextPOSTReturns the raw passages most relevant to a query across a list of documents, with page metadata, without generating an answer.
summarize_documentSummarize documentPOSTGenerates a summary of one document in your account (summary).
upload_documentUpload documentPOSTUploads a PDF file to your AskYourPDF account and returns its docId. Pass that docId as doc_id to chat_with_document, summarize_document or create_knowledge_base.

Knowledge base, 8 operations

chat_with_knowledge_baseChat with knowledge basePOSTAsks a question across every document of a knowledge base and returns the answer (answer.message). Send messages: optional system message, earlier turns, then the user's question last.
create_knowledge_baseCreate knowledge basePOSTCreates a knowledge base grouping several of your documents so you can chat with them together (chat_with_knowledge_base). Returns its knowledge_base_id.
delete_knowledge_baseDelete knowledge baseDELETEDeletes a knowledge base.
get_knowledge_baseGet knowledge baseGETReturns one knowledge base: its name, the documents it groups and when it was created.
get_knowledge_base_contextGet knowledge base contextGETReturns the raw passages of a knowledge base's documents most relevant to a query, with page metadata, without generating an answer.
list_knowledge_basesList knowledge basesGETLists your knowledge bases (named groups of documents) with the documents in each, one page at a time.
search_knowledge_basesSearch knowledge basesGETFinds your knowledge bases whose name matches a search text.
update_knowledge_baseUpdate knowledge basePUTRenames a knowledge base or changes its documents. document_ids is required and becomes the new document list: read the current list with get_knowledge_base first and send it back with your change.

Model, 1 operation

list_modelsList modelsGETLists the models the chat tools accept, with their token limit and whether each needs a paid plan.

Text, 1 operation

summarize_textSummarize textPOSTGenerates a summary of a text you send (summary_text); no document is needed.

Use AskYourPDF from Claude Code, Cursor or Codex

Connect AskYourPDF in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its AskYourPDF 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 AskYourPDF

Create your workspace
Sign up free. Nothing to install.
Connect AskYourPDF once
Add your AskYourPDF 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.