> For the complete documentation index, see [llms.txt](https://wiki.tinkerhub.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://wiki.tinkerhub.org/activity-book/learning-activity/study-jam/model-context-protocol-mcp.md).

# Model Context Protocol (MCP)

**Name**: Model Context Protocol – FastMCP Workshop

**Category**: AI Infrastructure, Developer Tooling, LLM Ecosystems

**Type**: Study Jam

**Summary - oneliner**: A 3-day deep-dive workshop into building and deploying tools using the Model Context Protocol (MCP) and FastMCP framework.

**Purpose**:\
To help participants understand, implement, and deploy MCP-compliant tools and servers to integrate with LLMs like Claude or Cursor.

**Core Concepts Coverage**:

* What is MCP and why it matters ("USB-C for AI tools")
* FastMCP server and client development
* Resource passing and prompt-based tools
* Integration with LLM environments like Cursor
* Hosting, deployment, and security practices

**How**:

1. 3-day workshop with lectures and hands-on labs
2. Build calculator tool with MCP protocol
3. Add prompts, clients, and secure endpoints
4. Integrate with Claude Desktop & Cursor
5. Explore deployment via Modal, ASGI, and OAuth flows

**Expected Outcome**:

* Deep understanding of MCP & FastMCP
* Working server & client tools
* Experience with deployment & LLM integration
* Ability to build streamable, secure AI tools

**How to Measure Impact**:

* Completion of hands-on modules
* Successful integration and testing of tools
* Participation in Q\&A, brainstorming, and final discussion
* Documentation of tool and hosting workflow

**Pre-event Checklist**:

* Install Python, `uv`, FastMCP
* Share starter repos and lab instructions
* Prepare test endpoints for integration
* Provide Claude/Desktop access details

**Post-event Checklist**:

* Document real-world use cases
* Share tool gallery built by participants
* Publish MCP learning notes and labs
* Connect learners to MCP ecosystem and open tool registries

**Curated by**: Alosh

**Ideal Audience**: Tool developers, AI infra engineers, curious builders exploring agent-tool ecosystems.

**Resource Links**:

* [FastMCP GitHub](https://github.com/alosh/fastmcp)
* [MCP Spec Overview](https://docs.fastmcp.io/)
* [Cursor](https://www.cursor.so)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://wiki.tinkerhub.org/activity-book/learning-activity/study-jam/model-context-protocol-mcp.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.