Agents & MCP

Who: Agent Builders, AI Engineers
Output: Autonomous AI agents with memory and tool use Build AI agents that can call tools, remember context, and integrate with MCP servers—all backed by Pixeltable’s persistent storage and orchestration.

Declarative Agents: Instead of imperative control flow, define your agent as a table with computed columns. Each row is a user query; computed columns define the reasoning chain (tool selection → execution → context retrieval → response). Pixeltable handles orchestration, caching, and persistence automatically.

Agent Capabilities

Tool Calling

Persistent Memory

Store conversation history and retrieved context in tables

MCP Integration

Connect to Model Context Protocol servers for external tools

RAG Retrieval

Semantic search over documents, images, and more

Data Lifecycle

1. Tools
2. Workflow
3. MCP
4. Memory
5. Deploy

Define Tool UDFs

Wrap any Python code as @pxt.udf tools—API calls, web scraping, database queries

import pixeltable as pxt
import requests
import yfinance as yf

@pxt.udf
def get_latest_news(topic: str) -> str:
    """Fetch latest news using NewsAPI."""
    response = requests.get(
        "https://newsapi.org/v2/everything",
        params={"q": topic, "apiKey": os.environ["NEWS_API_KEY"]}
    )
    articles = response.json().get("articles", [])[:3]
    return "\n".join(f"- {a['title']}" for a in articles)

@pxt.udf
def fetch_financial_data(ticker: str) -> str:
    """Fetch stock data using yfinance."""
    stock = yf.Ticker(ticker)
    info = stock.info
    return f"{info['shortName']}: ${info['currentPrice']}"

UDF Guide

Writing custom functions

Define Query Tools

Turn semantic search into callable tools with @pxt.query

@pxt.query
def search_documents(query_text: str, user_id: str):
    """Search documents by semantic similarity."""
    sim = chunks.text.similarity(query_text)
    return (
        chunks.where((chunks.user_id == user_id) & (sim > 0.5))
        .order_by(sim, asc=False)
        .select(chunks.text, source_doc=chunks.document, sim=sim)
        .limit(20)
    )

@pxt.query
def search_video_transcripts(query_text: str):
    """Search video transcripts by text."""
    sim = transcript_sentences.text.similarity(query_text)
    return (
        transcript_sentences.where(sim > 0.7)
        .order_by(sim, asc=False)
        .select(transcript_sentences.text, source_video=transcript_sentences.video)
        .limit(20)
    )

Combine UDFs, queries, and MCP tools into a single registrypxt.tools()

# Register tools from multiple sources
tools = pxt.tools(
    # UDFs - External API Calls
    get_latest_news,
    fetch_financial_data,
    # Query Functions - Agentic RAG
    search_documents,
    search_video_transcripts,
)

Tool Calling Cookbook

Complete tool calling walkthrough

Create Agent Table

Define the workflow as a table with computed columns

# Main workflow table - rows trigger the agent pipeline
agent = pxt.create_table('agents.workflow', {
    'prompt': pxt.String,
    'timestamp': pxt.Timestamp,
    'user_id': pxt.String,
    'system_prompt': pxt.String,
    'max_tokens': pxt.Int,
    'temperature': pxt.Float,
})

Tool Selection (LLM)

First LLM call decides which tool to use

from pixeltable.functions.anthropic import messages, invoke_tools

# Step 1: LLM selects which tool to call
agent.add_computed_column(
    initial_response=messages(
        model='claude-sonnet-4-20250514',
        messages=[{'role': 'user', 'content': agent.prompt}],
        max_tokens=agent.max_tokens,
        tools=tools,  # Available tools
        tool_choice=tools.choice(required=True),  # Force tool selection
        model_kwargs={'system': agent.system_prompt}
    )
)

Tool Execution

Pixeltable executes the selected tool automaticallyinvoke_tools()

# Step 2: Execute the tool the LLM chose
agent.add_computed_column(
    tool_output=invoke_tools(tools, agent.initial_response)
)

Context Assembly

Combine tool output with retrieved context

# Parallel context retrieval (Pixeltable handles this)
agent.add_computed_column(doc_context=search_documents(agent.prompt, agent.user_id))
agent.add_computed_column(image_context=search_images(agent.prompt, agent.user_id))
agent.add_computed_column(memory_context=search_memory(agent.prompt, agent.user_id))

# Assemble everything into final context
agent.add_computed_column(
    final_context=assemble_context(
        agent.prompt,
        agent.tool_output,
        agent.doc_context,
        agent.memory_context,
    )
)

Final Response

Second LLM call generates the answer with full context

# Step 3: Generate final answer with all context
agent.add_computed_column(
    final_response=messages(
        model='claude-sonnet-4-20250514',
        messages=agent.final_context,
        max_tokens=agent.max_tokens,
        model_kwargs={'system': agent.system_prompt}
    )
)

# Extract answer text
agent.add_computed_column(
    answer=agent.final_response.content[0].text
)

Tool Calling Cookbook

Complete walkthrough

Connect MCP Server

Load tools from any MCP-compatible serverpxt.mcp_udfs()

# Load tools from MCP server
mcp_tools = pxt.mcp_udfs('http://localhost:8000/mcp')

# Combine with local tools
all_tools = pxt.tools(
    get_latest_news,
    fetch_financial_data,
    search_documents,
    *mcp_tools  # Add MCP tools
)

Pixeltable MCP Server

MCP server for Claude, Cursor, and AI IDEs

Build Your Own MCP Server

Expose Pixeltable tables as MCP tools for AI IDEs

# Example: JFK Files MCP Server
# Exposes document search to Claude Desktop, Cursor, etc.

from mcp.server import Server
import pixeltable as pxt

server = Server("jfk-files")

@server.tool()
def search_jfk_documents(query: str) -> str:
    """Search declassified JFK documents."""
    docs = pxt.get_table('jfk.documents')
    sim = docs.content.similarity(query)
    results = docs.order_by(sim, asc=False).limit(5).collect()
    return "\n".join(r['content'] for r in results)

JFK MCP Server

Example MCP server with document search

Chat History

Store conversation turns with semantic search

# Chat history with embedding index
chat_history = pxt.create_table('agents.chat_history', {
    'role': pxt.String,           # 'user' or 'assistant'
    'content': pxt.String,
    'timestamp': pxt.Timestamp,
    'user_id': pxt.String
})

chat_history.add_embedding_index(
    'content',
    string_embed=sentence_transformer.using(model_id='all-MiniLM-L6-v2')
)

# Recent history query
@pxt.query
def get_recent_chat_history(user_id: str, limit: int = 4):
    return (
        chat_history.where(chat_history.user_id == user_id)
        .order_by(chat_history.timestamp, asc=False)
        .select(role=chat_history.role, content=chat_history.content)
        .limit(limit)
    )

# Semantic search over all history
@pxt.query
def search_chat_history(query_text: str, user_id: str):
    sim = chat_history.content.similarity(query_text)
    return (
        chat_history.where((chat_history.user_id == user_id) & (sim > 0.8))
        .order_by(sim, asc=False)
        .select(role=chat_history.role, content=chat_history.content, sim=sim)
        .limit(10)
    )

Agent Memory Pattern

Persistent conversation context

Memory Bank

Store user-saved snippets (code, text, facts) for recall

# Selective memory - things the user explicitly saves
memory_bank = pxt.create_table('agents.memory_bank', {
    'content': pxt.String,
    'type': pxt.String,          # 'code', 'text', 'fact'
    'language': pxt.String,       # For code: 'python', 'javascript', etc.
    'context_query': pxt.String,  # What triggered this save
    'timestamp': pxt.Timestamp,
    'user_id': pxt.String
})

memory_bank.add_embedding_index('content', string_embed=embed_fn)

@pxt.query
def search_memory(query_text: str, user_id: str):
    sim = memory_bank.content.similarity(query_text)
    return (
        memory_bank.where((memory_bank.user_id == user_id) & (sim > 0.8))
        .order_by(sim, asc=False)
        .select(
            content=memory_bank.content,
            type=memory_bank.type,
            language=memory_bank.language,
            context_query=memory_bank.context_query,
        )
        .limit(10)
    )

Multimodal Knowledge Base

Index documents, images, video, and audio for retrieval

# Documents with chunking
documents = pxt.create_table('agents.collection', {
    'document': pxt.Document,
    'uuid': pxt.String,
    'user_id': pxt.String
})

chunks = pxt.create_view('agents.chunks', documents,
    iterator=DocumentSplitter.create(
        document=documents.document,
        separators='paragraph',
        metadata='title, heading, page'
    )
)
chunks.add_embedding_index('text', string_embed=embed_fn)

# Images with CLIP
images = pxt.create_table('agents.images', {
    'image': pxt.Image,
    'user_id': pxt.String
})
images.add_embedding_index('image', embedding=clip.using(model_id='openai/clip-vit-large-patch14'))

# Video frames
videos = pxt.create_table('agents.videos', {'video': pxt.Video, 'user_id': pxt.String})
video_frames = pxt.create_view('agents.video_frames', videos,
    iterator=FrameIterator.create(video=videos.video, fps=1)
)
video_frames.add_embedding_index('frame', embedding=clip.using(model_id='openai/clip-vit-large-patch14'))

RAG Pipeline

Document retrieval patterns

Flask/FastAPI Endpoint

Expose your agent via HTTP API

from flask import Flask, request
from datetime import datetime
import pixeltable as pxt

app = Flask(__name__)
agent = pxt.get_table('agents.workflow')
chat_history = pxt.get_table('agents.chat_history')

@app.route("/chat", methods=["POST"])
def chat():
    data = request.json
    user_id = data["user_id"]
    prompt = data["message"]

    # Store user message
    chat_history.insert([{
        "role": "user",
        "content": prompt,
        "timestamp": datetime.now(),
        "user_id": user_id
    }])

    # Trigger agent workflow (computed columns run automatically)
    agent.insert([{
        "prompt": prompt,
        "timestamp": datetime.now(),
        "user_id": user_id,
        "system_prompt": "You are a helpful assistant.",
        "max_tokens": 1024,
        "temperature": 0.7,
    }])

    # Get the answer (already computed)
    result = agent.order_by(agent.timestamp, asc=False).limit(1).collect()
    answer = result[0]["answer"]

    # Store assistant response
    chat_history.insert([{
        "role": "assistant",
        "content": answer,
        "timestamp": datetime.now(),
        "user_id": user_id
    }])

    return {"response": answer}

Deployment Guide

Production deployment patterns

Cloud Deployment (Coming Soon)

One-command deployment with pxt serve and pxt deploy

Cloud Offering

Learn about upcoming Endpoints and Live Tables

Built with Pixeltable

Pixelbot

Multimodal AI agent with infinite memory, file search, and image generation

Pixelagent

Lightweight agent framework with built-in memory and tool orchestration

Pixelmemory

Persistent memory layer for AI applications

MCP Server

Model Context Protocol server for Claude, Cursor, and AI IDEs

Tool Calling

Complete guide to pxt.tools() and invoke_tools()

Agent Memory

Persistent conversation context patterns

RAG Pipeline

Retrieval-augmented generation workflow

Table as UDF

Use tables as callable functions

Use Cases

Deployment

Pixeltable Cloud

Agent Capabilities

Tool Calling

Persistent Memory

MCP Integration

RAG Retrieval

Data Lifecycle

UDF Guide

Tool Calling Cookbook

Tool Calling Cookbook

Pixeltable MCP Server

JFK MCP Server

Agent Memory Pattern

RAG Pipeline

Deployment Guide

Cloud Offering

Built with Pixeltable

Pixelbot

Pixelagent

Pixelmemory

MCP Server

Tool Calling

Agent Memory

RAG Pipeline

Table as UDF

Use Cases

Deployment

Pixeltable Cloud

​Agent Capabilities

Tool Calling

Persistent Memory

MCP Integration

RAG Retrieval

​Data Lifecycle

UDF Guide

Tool Calling Cookbook

Tool Calling Cookbook

Pixeltable MCP Server

JFK MCP Server

Agent Memory Pattern

RAG Pipeline

Deployment Guide

Cloud Offering

​Built with Pixeltable

Pixelbot

Pixelagent

Pixelmemory

MCP Server

​Related Cookbooks

Tool Calling

Agent Memory

RAG Pipeline

Table as UDF

Agent Capabilities

Data Lifecycle

Built with Pixeltable

Related Cookbooks