MCP Fundamentals - Revision history

Todd at 15:55, 18 March 2026

2026-03-18T15:55:29Z

Todd at 15:12, 11 March 2026

2026-03-11T15:12:44Z

Todd: Created page with "NOTOC = Model Context Protocol (MCP) = Large Language Models (LLMs) like Claude, ChatGPT, and other AI assistants are powerful, but they normally operate in isolation...."

2026-03-11T15:00:18Z

Created page with "__NOTOC__ = Model Context Protocol (MCP) = Large Language Models (LLMs) like Claude, ChatGPT, and other AI assistants are powerful, but they normally operate in isolation...."

New page

__NOTOC__

= Model Context Protocol (MCP) =

Large Language Models (LLMs) like Claude, ChatGPT, and other AI assistants are powerful, but they normally operate in isolation.
They cannot directly access your computer, read files, run programs, or query databases.

The '''Model Context Protocol (MCP)''' is a standard that allows language models to safely interact with external tools and data sources.

Instead of executing code directly, the language model communicates with an '''MCP server''', which exposes specific capabilities that the model can use.

This enables AI systems to interact with real software and data.

Learn more:
[https://modelcontextprotocol.io/docs/getting-started/intro Model Context Protocol Documentation]

== MCP Architecture ==

The interaction between the user, the language model, and your MCP server looks like this:

<pre>
User Prompt
↓
Language Model (Claude)
↓
MCP Client
↓
MCP Server
↓
Tools / Data Sources
</pre>

The language model analyzes the user prompt and determines whether a tool should be used.

If a tool is needed:

1. The language model selects the appropriate tool.
2. The MCP client sends the request to the MCP server.
3. The server executes the tool.
4. The result is returned to the model.
5. The model formats the response for the user.

The model never directly runs code on your computer.

== MCP Building Blocks ==

MCP servers provide three types of capabilities.

=== Tools ===

'''Tools''' are executable functions that perform actions or retrieve data.

Examples include:

* querying a database
* reading files
* performing calculations
* calling APIs
* searching datasets

A language model can decide to call one of these tools to answer a user's request.

Example tool:

<pre>
get_weather(city="St. Louis")
</pre>

The MCP server runs the function and returns the result to the language model.

=== Resources ===

'''Resources''' are data sources that the MCP server can access.

Examples include:

* files
* databases
* documents
* datasets
* logs

Resources provide context for the tools.

For example, a tool might read a dataset stored in a file.

=== Prompts ===

'''Prompts''' are the instructions given by the user.

Example:

<pre>
"Show the top hitters on the 1940 Cardinals."
</pre>

The language model interprets the prompt and decides whether it needs to call a tool.

The user never directly runs the tool — the model decides when tools are needed.

== Example Workflow ==

Suppose the user asks:

<pre>
"Show the top hitters on the 1940 Cardinals."
</pre>

The system might behave like this:

1. Claude reads the prompt.
2. Claude determines that the request requires the tool <code>get_top_players</code>.
3. Claude calls the MCP server.
4. The server runs the Python function.
5. The result is returned and displayed to the user.

This process happens automatically.

== Why MCP Matters ==

Without MCP, language models can only generate text.

With MCP, language models can:

* access real data
* run programs
* query databases
* analyze datasets
* automate workflows

This transforms AI systems from simple chatbots into '''agents''' capable of performing real tasks.

== MCP in This Course ==

In this module, you will build a simple MCP server using Python.

Your server will expose tools that allow Claude Desktop to analyze historical St. Louis Cardinals batting statistics.

Claude will automatically call your tools when appropriate and display the results in the chat interface.

[[Category:Module 6]]
[[Category:Modules]]

@@ Line 150: / Line 150: @@
 Claude will automatically call your tools when needed.
 [[Category:Module 6]]
 [[Category:Modules]]

@@ Line 9: / Line 9: @@
 Instead of executing code directly, the language model communicates with an '''MCP server''', which exposes specific capabilities that the model can use.
 Learn more:
 [https://modelcontextprotocol.io/docs/getting-started/intro Model Context Protocol Documentation]
 == MCP Architecture ==
@@ Line 31: / Line 51: @@
 </pre>
-The language model analyzes the user prompt and determines whether a tool should be used.
+The language model analyzes the prompt and determines whether a tool should be used.
 If a tool is needed:
-. The language model selects the appropriate tool.
+. The model selects a tool
-. The MCP client sends the request to the MCP server.
+. The MCP client sends the request
-. The server executes the tool.
+. The MCP server runs the function
-. The result is returned to the model.
+. The result is returned to the model
-. The model formats the response for the user.
+. The model formats the final response
 == MCP Building Blocks ==
@@ Line 58: / Line 76: @@
 * calling APIs
 * searching datasets
 Example tool:
@@ Line 67: / Line 83: @@
 </pre>
-The MCP server runs the function and returns the result to the language model.
+The MCP server runs the function and returns the result.
 === Resources ===
-'''Resources''' are data sources that the MCP server can access.
+'''Resources''' are the data sources your MCP tools use.
 Examples include:
 * files
 * databases
-* documents
+* logs
 * datasets
 For example, a tool might read a dataset stored in a file.
@@ Line 92: / Line 106: @@
 <pre>
-"Show the top hitters on the 1940 Cardinals."
+Show the top hitters on the 1940 Cardinals.
 </pre>
-The language model interprets the prompt and decides whether it needs to call a tool.
+The model interprets the prompt and determines if a tool should be used.
-The user never directly runs the tool — the model decides when tools are needed.
+The user never runs the tool directly.
 == Example Workflow ==
@@ Line 104: / Line 118: @@
 <pre>
-"Show the top hitters on the 1940 Cardinals."
+Show the top hitters on the 1940 Cardinals.
 </pre>
-The system might behave like this:
+The system behaves like this:
-This process happens automatically.
+. Claude reads the prompt
 == Why MCP Matters ==
@@ Line 121: / Line 133: @@
 Without MCP, language models can only generate text.
-With MCP, language models can:
+With MCP, models can:
 * access real data
@@ Line 129: / Line 141: @@
 * automate workflows
-This transforms AI systems from simple chatbots into '''agents''' capable of performing real tasks.
+This transforms AI systems from chatbots into '''agents'''.
 == MCP in This Course ==
@@ Line 137: / Line 149: @@
 Your server will expose tools that allow Claude Desktop to analyze historical St. Louis Cardinals batting statistics.
-Claude will automatically call your tools when appropriate and display the results in the chat interface.
+Claude will automatically call your tools when needed.
 [[Category:Module 6]]
 [[Category:Modules]]

MCP Fundamentals - Revision history

Todd at 15:55, 18 March 2026

Todd at 15:12, 11 March 2026

Todd: Created page with "__NOTOC__ = Model Context Protocol (MCP) = Large Language Models (LLMs) like Claude, ChatGPT, and other AI assistants are powerful, but they normally operate in isolation...."

Todd: Created page with "NOTOC = Model Context Protocol (MCP) = Large Language Models (LLMs) like Claude, ChatGPT, and other AI assistants are powerful, but they normally operate in isolation...."