Tokenless

Model context protocol

Power agents with full context of your experiments and traces with W&B MCP server

Power agents with full context of your experiments and traces with W&B MCP server

The W&B Model Context Protocol (MCP) is a hosted endpoint that enables AI agents to intelligently interact with all Weights & Biases data, including runs, traces, evaluations, and reports. It features discovery tools for smart queries, automated analysis for comparing experiments and identifying regressions, and seamless integration with IDEs, coding agents, and chat interfaces like Mistral AI for streamlined ML workflows and on-the-go reporting.

Stop AI Agents From SQL Injecting Your Database

Stop AI Agents From SQL Injecting Your Database

Averi Kitsch, Staff Software Engineer at Google, outlines a four-step evolution for securing AI agents that access databases, moving from dangerous, model-controlled tools to a zero-trust architecture. Drawing on insights from over 20 million monthly tool calls, the talk provides a practical roadmap for preventing data leaks by separating identities, constraining actions, and removing credentials and PII from the agent's control.

Serverless Agents: Real-World Tooling with Strands SDK, MCP & AWS • Akshatha Laxmi • GOTO 2025

Serverless Agents: Real-World Tooling with Strands SDK, MCP & AWS • Akshatha Laxmi • GOTO 2025

A deep dive into building production-ready, stateless, and scalable LLM agents by leveraging the Model Context Protocol (MCP) and Strands SDK on AWS Lambda. The session demonstrates how to expose real-world functionality to language models, moving beyond mere reasoning to tangible action.

CLI vs MCP: How AI Agents Choose the Right Tool for the Job

CLI vs MCP: How AI Agents Choose the Right Tool for the Job

AI agents can interact with the world through either the Command Line Interface (CLI) or the Model Context Protocol (MCP). This summary explores the trade-offs between the two, highlighting CLI's efficiency for tasks the model is trained on, versus MCP's power of abstraction and governance for more complex, high-level operations.

Your Insecure MCP Server Won't Survive Production — Tun Shwe, Lenses

Your Insecure MCP Server Won't Survive Production — Tun Shwe, Lenses

Lenses.io experts Tun Shwe and Jeremy Frenay discuss the significant security and design hurdles in transitioning Model Context Protocol (MCP) servers from local development to enterprise production. They introduce five core principles for secure agentic design, including shrinking the attack surface and constraining inputs, and detail the necessity of remote MCP servers with robust authentication. The talk provides an in-depth comparison of OAuth 2.1's Dynamic Client Registration (DCR) and the more secure Client ID Metadata Document (CIMD) approaches for managing agent identities, offering a roadmap for building enterprise-grade agentic AI systems with MCP.

A2A vs MCP: AI Agent Communication Explained

A2A vs MCP: AI Agent Communication Explained

Discover how A2A (Agent2Agent) and MCP (Model Context Protocol) solve critical challenges in AI agent ecosystems. A2A enables seamless communication and collaboration between diverse AI agents, while MCP standardizes an agent's access to external tools and data, fostering robust and interoperable AI workflows.

Next →