Integration

Personal AI integration

Personal AI hosts AI personas trained on your own memory. Chat with a persona and read a conversation's history, send it instructions through its chatgpt or search command, add text memories to its memory stack, upload documents, files and web pages (YouTube, LinkedIn, articles) to its memory, and list or rewrite its documents. Every call names the persona by its domain name, shown below the AI's name in the app. Workspace, persona and channel settings are managed in the Personal AI app and are not part of the API. Authentication is an API key from the Personal AI app, sent in the x-api-key header.

Connect Personal AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Personal AI.Built from the 9 Personal AI tools below, on the connection you add once.

What you can do with Personal AI

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, 3 operations

list_documentsList documentsPOSTReturns documents of a persona: the one whose name is given in Text, or, with Text left out, up to size documents. Each has the id (feed_id) update_document needs. Read-only, despite the POST method.
update_documentUpdate documentPUTReplaces the text of one document of a persona. Send the ENTIRE new text, not only the changes: the previous content is not reloaded, so anything left out is lost. Returns the updated memory block.
upload_documentUpload documentPOSTUploads a text document to a persona's Upload Library and, unless is_stack is false, to its memory. Processing is asynchronous: the answer only says the document was accepted.

Conversation, 1 operation

list_conversation_messagesList conversation messagesPOSTReturns the messages of one conversation session of a persona, both the user's messages and the AI's replies, oldest first as the vendor's example shows. Read-only, despite the POST method.

File, 1 operation

upload_fileUpload filePOSTUploads a file (PDF, DOCX and similar) to a persona's memory. Processing is asynchronous: the answer only says the file was accepted.

Instruction, 1 operation

send_instructionSend instructionPOSTSends an instruction to one of your AI personas through the model named in cmd (chatgpt or search) and returns the reply (ai_message) with a confidence score. Pass the SessionId of an earlier reply to keep the context.

Memory, 1 operation

create_memoryCreate memoryPOSTAdds a plain text memory to a persona's memory stack (it appears on the memory stack timeline) and returns the memory block that was created, with the tags as topics.

Message, 1 operation

send_messageSend messagePOSTSends a message to one of your AI personas and returns its reply (ai_message) with a confidence score (ai_score). Pass the SessionId of an earlier reply to continue that conversation.

Url, 1 operation

upload_urlUpload urlPOSTFetches the content at a URL (a public YouTube video, a LinkedIn profile, a news article or a blog post) and uploads it to a persona's memory. Processing is asynchronous: the answer only says the URL was accepted.

Use Personal AI from Claude Code, Cursor or Codex

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

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