Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
MCP Server Evaluation Prototype
This talk demonstrates a prototype for automatically evaluating Message-Centric Protocol (MCP) servers to understand inputs, outputs, and failure points.
How to evaluate a MCP server automatically.
Systematically measures AI performance, token usage, and latency using custom semantic evaluation criteria.
- PythonPython: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
- MCPMCP is the open-source standard for securely connecting AI agents (like LLMs) to external tools, data, and enterprise workflows.The Model Context Protocol (MCP) functions as a standardized integration layer: think of it as a USB-C port for AI applications. Developed and open-sourced by Anthropic, this protocol allows large language models (LLMs) to access real-time context and execute actions via external tools like GitHub, Jira, or proprietary databases . It uses a simple JSON-RPC interface to define tools, schemas, and endpoints, which enables AI agents to perform complex, state-changing tasks—such as creating a GitHub issue or running a test script—rather than just generating text . MCP is essential for building agentic AI systems that can autonomously pursue goals and operate within defined safety and permission boundaries .
- Elluminate Live!Elluminate Live! was a premier synchronous learning platform, providing a full virtual classroom environment for distance education and web conferencingElluminate Live! was a premier synchronous learning platform, providing a full virtual classroom environment for distance education and web conferencing. The Java-based system (pre-Ultra) offered core collaborative tools: integrated Voice over IP (VoIP), public/private chat, a multi-user whiteboard, application sharing, and session recording. Designed for high-quality, real-time interaction, it was widely adopted by K-12, higher education, and corporate training sectors. Elluminate Inc. was acquired by Blackboard in 2010; the technology was rebranded as Blackboard Collaborate, and its current iteration is the browser-based Blackboard Collaborate Ultra.
Related projects
Simplify (cool) AI Integrations with MCP
London
Learn how to build and host a Model Context Protocol hub on Cloudflare Durable Objects, enabling cheap, customizable…
Heurist MCP Demo
Seattle
This talk demonstrates Heurist Mesh MCP, showing how AI assistants securely access blockchain tools for real-time data analysis,…
AI Workers That Create and Operate Their Own MCP Apps
Berlin
AI workers autonomously build, deploy, and operate MCP apps, showcasing a config-driven system for dynamic software creation and…
Build MCP apps the easy way
Zürich
Learn to build MCP apps quickly using the CLI or Manufact Vibe. Submit your app to the OpenAI…
How AI Agents Actually Work With Tools and MCP
Boston
A walkthrough of the actual code flow behind AI agents, demonstrating how they invoke tools like the Multi‑Tool…
A "course" as an MCP Server
San Francisco
This talk explores using an MCP server to deliver an interactive coding course that teaches content through agent-guided…