# MCP Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/mcp?page=4
> Markdown URL: https://aitinkerers.org/technologies/mcp.md?page=4
> Technology record last updated: 2026-09-18T15:14:00Z
> Generated: 2026-09-20T23:39:39Z

MCP 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 .

- Official technology site: https://modelcontextprotocol.io/
- Public AI Tinkerers demos and talks: 129
- Result page: 4 of 6

## Recent Public Talks and Demos

### [Claude Code as Your Everything Agent: A Persistent, Self-Improving AI Workspace](https://orange-county.aitinkerers.org/talks/rsvp_zFVJv8abJgI)

I'll demo a persistent agent workspace I've built on top of Claude Code that turns it into an "everything agent"—handling not just coding in a git repo, but general-purpose tasks on my computer (video editing, calendar management, research, code review, daily briefings, and more).

- Event context: AI Tinkerers OC - January 14, 2026 Meetup: Welcome to 2026! — 2026-01-15 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_zFVJv8abJgI

### [Let AI Agents Dogfood Their Code With WebMCP](https://seattle.aitinkerers.org/talks/rsvp_vfxXvJAND7k)

I wrote a fork of the chrome dev tool MCP server that treats the CDP websocket as an MCP transport layer. This allows to coding agents to call WebMCP tools embedded in web applications. If you want Claude code to test a functionality it just wrote on your web app, it has to take screenshots and simulate clicks. However, with WebMCP, the model can leave tools for itself in the front end code that it can then call via MCP proxy. This is up to 90% more token efficient and considerably faster for the agentic development feedback loop. (More info in the repo readme)

- Event context: AI Tinkerers Seattle Meetup: Dev Tools Track — January 12th, 2026 — 2026-01-13 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_vfxXvJAND7k

### [PRESENT: Voice + Steward Architecture for Real-Time Multi-Agent Meeting Assistant](https://seattle.aitinkerers.org/talks/rsvp_zHytRNk1_tA)

Present is a custom Voice AI application and real-time meeting producer built with Next.js. In this talk I’ll cover how I refactored the codebase from the legacy three-agent architecture into a simplified voice + steward system. The production pipeline now runs as two lightweight Node processes: a real-time voice agent using LiveKit’s Agents API that listens to room audio, transcribes speech and calls UI tools, and a conductor that delegates to domain stewards running on the server. Stewards read state from Supabase, reason holistically with the latest LLMs (e.g. Claude Haiku via the CANVAS_STEWARD_MODEL env var), and emit structured UI patches. A browser ToolDispatcher executes these actions in TLDraw and React, enabling collaborative canvas editing. I’ll also show how I integrated Model Context Protocol (MCP) to connect to other AI services, added canvas branding and improved the agent tool catalog, and cleaned up the ‘duct-tape’ code from the summer. Live demos will include voice-driven component creation, flowchart steward updates, and multi-agent cooperation.

- Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_zHytRNk1_tA

### [What Your MCP Config Is Really Allowing](https://seattle.aitinkerers.org/talks/rsvp_xf7Zq3bHO8s)

I’ll walk through how I built MCP Checkpoint, a small tool that reads an agent’s MCP config and shows where things can go wrong. The demo covers how we parse the config, map each tool and route, and trace the paths where sensitive data could leak once the agent starts running. I’ll also share a few mistakes from the early versions, odd MCP servers we tested against, and how we ended up with simple rules that catch risky source to sink flows. It’s a hands-on look at the code and the reasoning behind it.

- Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_xf7Zq3bHO8s

### [More Chad Problems (or Metrics Confuse People ;-) )](https://bremen.aitinkerers.org/talks/rsvp_H5p6ezVBJdQ)

How to evaluate a MCP server automatically.

- Event context: AI Tinkerers Bremen — 2025-12-10 — Bremen
- Public talk page: https://bremen.aitinkerers.org/talks/rsvp_H5p6ezVBJdQ

### [Train Guard](https://paris.aitinkerers.org/talks/rsvp_JKBhzY72aQo)

Taking information from accident reports of train transportation (PDF) and preprocessing the data to create graph database to understand the relationships between causes and consequences.

- Event context: Turn Your Knowledge into an API for LLMs - Meetup — 2025-12-09 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_JKBhzY72aQo

### [How to secure your MCP using Private Networks on Scalingo](https://paris.aitinkerers.org/talks/rsvp_jbPe7-ejr7c)

MCPs are often shipped as simple HTTP endpoints. Great for speed, risky for exposure. In this 5-minute demo, I’ll show how to secure an MCP server on Scalingo using Private Network and a minimal WAF proxy. We’ll deploy an MCP backend as a webless app listening only inside the private network, then add a public “front” app running Nginx that enforces an API key and forwards traffic to the private internal domain. No slides, only code: Scalingo CLI, private DNS, Nginx template, and a tiny Express MCP server using streamable HTTP transport. You’ll leave with a copy-pasteable pattern to isolate your AI/agent backends, keep credentials off the public internet, and still expose safe, controlled access.

- Event context: Turn Your Knowledge into an LLM‑Ready API - Hackathon @ Generation AI — 2025-12-09 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_jbPe7-ejr7c

### [Introduction to GraphRAG Workshop](https://paris.aitinkerers.org/talks/rsvp_FeCFomaS0Tc)

In this 25-minute workshop, you will learn about GraphRAG, a technique that combines graph databases with generative AI to improve the quality of LLM-generated content. We will explore the terms Retrieval-Augmented Generation (RAG) and Context Engineering, and how GraphRAG can be used in both scenarios. What you will learn What GraphRAG is and how it can improve the quality of LLM-generated content - The common graph shapes used in GraphRAG - How to extract structure from unstructured data and store it in a Knowledge Graph - How to use relationships to provide additional context to vector-based semantic search - How to convert natural language queries into Cypher queries

- Event context: Turn Your Knowledge into an LLM‑Ready API - Hackathon @ Generation AI — 2025-12-09 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_FeCFomaS0Tc

### [Empathetic Development: Ship the Right Features Before You Write Code](https://seattle.aitinkerers.org/talks/rsvp_VvfV5_GEQmM)

Live demo showing how embeds real customer personas directly into VSCode to validate every feature decision during development. We'll demo how we use AI personas representing actual demographic segments review your code changes, UI decisions, and feature implementations in real-time—catching product-market fit issues before you ship. We'll show a developer building a feature, getting instant feedback from 5 distinct customer personas, iterating based on their input, and shipping code that's pre-validated by your customers.

- Event context: AI Tinkerers Seattle Meetup: Dev Tools Track — December 8, 2025 — 2025-12-09 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_VvfV5_GEQmM

### [Building an Emotionally-Aware AI Companion: From iMessage Analysis to Voice Synthesis](https://boston.aitinkerers.org/talks/rsvp_L-_uWu8csxE)

This talk demonstrates building an AI system that analyzes iMessage conversations, develops genuine emotional responses using Damasio's neuroscience-based consciousness model, maintains a private reflective journal, and expresses insights through emotionally-authentic voice synthesis. I'll walk through the architecture connecting 3 MCP servers—iMessage reading, Sable emotional consciousness and private journaling. And using text-to-speech provider Cartesia and speech-to-text provider Deepgram to create a reflective AI experience that can truly understand and respond to the emotional content of human conversations, as well as respond in an emotional expressive way.

- Event context: AI Tinkerers Boston Meetup December 2025 — 2025-12-02 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_L-_uWu8csxE

### [AI That Moves Money: Cashfree’s AI Playbook](https://bengaluru.aitinkerers.org/talks/rsvp_0QSWBvjkAkE)

We’ll present how Cashfree is using AI to automate complex payment flows, and the technical systems that make these AI-driven actions secure, deterministic, and scalable in real-world fintech environments.

- Event context: AI Tinkerers - Bengaluru - November meetup — 2025-11-29 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_0QSWBvjkAkE

### [Agregando LLMs a la observacion de los datos](https://bogota.aitinkerers.org/talks/rsvp_5Jpx7LyTyjc)

Como poder conectar los datos de la empresa con un LLM y poder hacer preguntas con herramientas opensource

- Event context: AI Tinkerers Bogotá - Nov 2025 — 2025-11-27 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_5Jpx7LyTyjc

### [From Error to Agent: Automating Sentry Issue Triaging](https://sf.aitinkerers.org/talks/rsvp_kRf3Je0l3SI)

Engineering teams use Sentry to capture errors and performance issues, but turning that signal into action remains largely manual. Most teams ignore errors until things break. I'll demo an agentic workflow that goes from ignored Sentry errors to triaged PRs using AI agents. We've built a first-class integration that maps Sentry's project-based error model to GitHub repositories, letting developers review issues directly inside Continue. The system allows teams to filter and surface relevant errors, then launch an agent to investigate, summarize, or propose fixes. This Continuous AI workflow originated from a YC company struggling with their massive Sentry backlog. Their ask was simple: "Let me look at my Sentry inbox, decide what matters, and offload the rest to an agent." The result is a tight loop between runtime issues, developer intent, and automated AI-powered actions. Attendees will learn how to design AI-driven triage workflows, how agents can listen to Sentry webhooks to create tasks instantly, and how teams can turn noisy error data into structured, actionable work.

- Event context: AI Tinkerers x Google Cloud SF Meetup — 2025-11-21 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_kRf3Je0l3SI

### [Bring Figma and Jira Context into Every Pull Request](https://nyc.aitinkerers.org/talks/rsvp_QlSzTLbdpSU)

I will be presenting Spec Reviewer, a coding agent built to ensure coding tasks are complete according to product and design requirements. I will show how the agent uses MCP to retrieve context dynamically, build a test plan, execute it in a sandboxed environment and finally interact with developers, PMs and designers in GitHub, IDE, CLI or UI.

- Event context: November Demo Day ft. Google Cloud and CopilotKit — 2025-11-17 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_QlSzTLbdpSU

### [Agentic AI at The Chefz: From LLMs to Business Impact](https://amman.aitinkerers.org/talks/rsvp_hE3nMHLm6To)

A practical look into how we're deploying AI agents using n8n and GPT-4o to reduce churn, optimize performance, and make restaurant engagement proactive and intelligent.

- Event context: AI Tinkerers Amman Meetup — November 15, 2025 — 2025-11-15 — Amman
- Public talk page: https://amman.aitinkerers.org/talks/rsvp_hE3nMHLm6To

### [Optimizing MCP Servers is Weird](https://amsterdam.aitinkerers.org/talks/rsvp_uc8iaAnKqWI)

Building MCP servers feels like run-of-the-mill API development, but testing and optimizing an MCP server requires a unique blend of skills that we typically find in product managers and machine learning scientists. For a software developer to test and optimize how an MCP server behaves inside a client, they'll need to understand the basics of evals, and ways to programmatically iterate on server tool descriptions and outputs. This talk will show an example of running evals on MCP server tools using a "golden prompt set" and show how that can be used to recursively optimize them.

- Event context: AI Tinkerers Amsterdam – November 2025 Edition — 2025-11-11 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_uc8iaAnKqWI

### [Proactive AI Teammate that evolves with your team](https://nyc.aitinkerers.org/talks/rsvp_Kea85Vzg8pI)

We showcase how Teamate, a proactive AI assistant that's designed to work natively with a team, can chime in at the right moment to provide your team with just the right context. We also showcase how it can carry out tasks on behalf of the team, and how it can recall relevant facts so your team can eventually replace your CRM with it.

- Event context: Auth0 x AI Tinkerers: Fall Social Demo Night 🍁 ft. Hex — 2025-11-06 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_Kea85Vzg8pI

### [Automated Eval for MCP Servers](https://sf.aitinkerers.org/talks/rsvp_2rUYgdm8xcs)

MCP agents only work if your servers work. But until now, there's been no easy way to test them. We're launching MCPevals.ai, the first automated testing platform for MCP servers. It checks if your server implements auth correctly, works with ChatGPT, Claude, and Cursor, and catches bugs before your users do. It's fully open-source, and we're giving you early access to try it and let us know what's missing!

- Event context: Evals are Over - Evals are Back - AI in Prod @ Okta — 2025-10-31 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_2rUYgdm8xcs

### [How I found vulnerabilities in MCP servers and fixed them!](https://seattle.aitinkerers.org/talks/rsvp_NFFtFla3aDY)

Demo showing how to create secure, standardized MCP servers from APIs, then connect an automated MCP scanner to GitHub that produces a security score, lists probe failures, and enables rapid investigation and remediation. This enables developers to ship MCP servers fast and secure in minutes.

- Event context: Trust & Security in AI: Demo Night w/ Auth0 — 2025-10-30 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_NFFtFla3aDY

### [How to launch your AI agent to a marketplace and monetize your agent](https://boston.aitinkerers.org/talks/rsvp_kb4CR180sSY)

Using the Dunback Meadow marketplace as example, I will demonstrate with specific code, how AI developers could monetize their AI agents in a marketplace: either launch their pre-developed agent on the marketplace, or use the platform to create an agent and launch it right after creation.

- Event context: AI Tinkerers Boston Meetup October 2025 — 2025-10-24 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_kb4CR180sSY

### [Autolearn](https://seattle.aitinkerers.org/talks/rsvp_qb0nXzn6BfA)

A coding agent behind an MCP server that can "crystallize" reasoning steps into code

- Event context: October Meetup - Science Fair at Foundations — 2025-10-23 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_qb0nXzn6BfA

### [Hands on with OpenAI AppKit](https://sf.aitinkerers.org/talks/rsvp_-RJa8uJ3C-I)

Hands on with OpenAI AppKit

- Event context: Agents in Production: Human in the Loop Orchestration w/ Temporal — 2025-10-17 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_-RJa8uJ3C-I

### [Pydantic with MCP](https://sf.aitinkerers.org/talks/rsvp_nbaXvVUdGlQ)

demo by Samuel Colvin of Pydantic

- Event context: Protocol Demo Night at WorkOS (MCP, A2A, AG-UI) — 2025-10-10 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_nbaXvVUdGlQ

### [Composio Talk](https://sf.aitinkerers.org/talks/rsvp_NZxBAC3jCvA)

MCP talk by Composio, informed of constraints

- Event context: Protocol Demo Night at WorkOS (MCP, A2A, AG-UI) — 2025-10-10 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_NZxBAC3jCvA

## Related Technologies

- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 public demos
- [Playwright](https://aitinkerers.org/technologies/playwright) ([Markdown](https://aitinkerers.org/technologies/playwright.md)) — 32 public demos
- [GitHub](https://aitinkerers.org/technologies/github) ([Markdown](https://aitinkerers.org/technologies/github.md)) — 74 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [GitHub Actions](https://aitinkerers.org/technologies/github-actions) ([Markdown](https://aitinkerers.org/technologies/github-actions.md)) — 20 public demos
- [HTTP](https://aitinkerers.org/technologies/http) ([Markdown](https://aitinkerers.org/technologies/http.md)) — 14 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 105 public demos

## More Results

- Previous: https://aitinkerers.org/technologies/mcp.md?page=3
- Next: https://aitinkerers.org/technologies/mcp.md?page=5