# We4AI Lab: Agent #1 — MCP Tool-Use Agent

> TL;DR: MCP Tool-Use Agent is a personal learning project that connects a language model to external tools using the Model Context Protocol (MCP). The build separates the host, the client, and the tool servers so tools can be plugged in without touching the agent's core. The complete build is explained in a public video on the We4AI YouTube channel; measured cost, latency, and evaluation numbers will be added here once the measurement harness is done.

- Status: active
- Published: 2026-10-22
- Last updated: 2026-10-22

- Tags: agents, mcp, llm

Note: This is a personal learning project, not a product or a service. It uses only public or synthetic data.

## What it does

MCP Tool-Use Agent connects a language model to external tools through the Model Context
Protocol. The agent runs as a host application, opens MCP client connections to one or more MCP
servers, and calls the tools those servers expose — the model decides which tool to call and the
protocol carries the request and result. The full build is walked through in the video above.

## Why I built it

Tool use is where agents stop being demos and start being systems, and MCP is the cleanest
separation of "agent" from "tools" available right now. I wanted to learn the protocol by
building with it end to end — host, client, and server — rather than reading about it.

## Architecture

The build follows MCP's three-part split:

```text
user ──► host (the agent app + LLM) ──► MCP client ──► MCP server ──► tool
                                           │
                                           └────► MCP server ──► another tool
```

The host owns the conversation and the model. Each MCP client holds one connection to one MCP
server. Each server advertises its tools (names, descriptions, input schemas) and executes calls.
Adding a new tool means starting a new server — the host code does not change.

## What worked, and what broke

A detailed failure log will be published with the code and follow-up posts. The honest summary so
far: the protocol separation itself is the win — tools plug in cleanly once the host–client–server
plumbing is in place — and the plumbing is where the time goes.

## Cost, latency, and eval numbers

Not published yet. A measurement harness (fixed task set, per-run cost and latency logging) is the
next piece of this project, and the numbers will appear on this page with their method and date —
this site does not publish unmeasured claims.

## What's next

- Publish the evaluation harness and its first results.
- Add a second MCP server to show multi-tool routing.
- Write up the host–client–server setup as a step-by-step post.

## FAQ

### What is the Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how an AI application (the host) talks to external tools and data sources through MCP servers, using a client per connection. Instead of bespoke integrations per tool, the agent discovers and calls tools through one protocol.

### Is this a product I can sign up for?

No. It is a personal learning project built on my own time. There is no hosted service, no support, and nothing for sale.

### Where is the code?

On my GitHub profile (github.com/rpalsaxena), linked from this page once the repository is public. The video walkthrough is embedded above.

### What data does the agent use?

Only public or synthetic data. No private, employer, or client data is used in any project on this site.