🔧 Module 3: Maendeleo ya Juu ya MCP kwa AI Toolkit

🎯 Malengo ya Kujifunza

Mwisho wa maabara hii, utaweza:

✅ Kuunda seva za MCP maalum kwa kutumia AI Toolkit
✅ Kusanidi na kutumia toleo jipya la MCP Python SDK (v1.9.3)
✅ Kuweka na kutumia MCP Inspector kwa ajili ya kufuatilia makosa
✅ Kufuatilia makosa ya seva za MCP katika mazingira ya Agent Builder na Inspector
✅ Kuelewa mchakato wa maendeleo ya seva za MCP kwa kiwango cha juu

📋 Mahitaji ya Awali

Kumaliza Lab 2 (Misingi ya MCP)
VS Code yenye AI Toolkit imewekwa
Mazingira ya Python 3.10+
Node.js na npm kwa ajili ya usanidi wa Inspector

🏗️ Kile Utakachojenga

Katika maabara hii, utaunda Seva ya Hali ya Hewa ya MCP ambayo inaonyesha:

Utekelezaji wa seva ya MCP maalum
Uunganisho na AI Toolkit Agent Builder
Mchakato wa kitaalamu wa kufuatilia makosa
Matumizi ya mifumo ya kisasa ya MCP SDK

🔧 Muhtasari wa Vipengele Muhimu

🐍 MCP Python SDK

Model Context Protocol Python SDK ni msingi wa kujenga seva za MCP maalum. Utatumia toleo 1.9.3 lenye uwezo bora wa kufuatilia makosa.

🔍 MCP Inspector

Chombo chenye nguvu cha kufuatilia makosa kinachotoa:

Ufuatiliaji wa seva kwa wakati halisi
Uonyesho wa utekelezaji wa zana
Ukaguzi wa maombi na majibu ya mtandao
Mazingira ya majaribio ya mwingiliano

📖 Hatua kwa Hatua ya Utekelezaji

Hatua 1: Unda WeatherAgent katika Agent Builder

Fungua Agent Builder katika VS Code kupitia AI Toolkit
Unda agent mpya kwa usanidi huu:
- Jina la Agent: WeatherAgent

Hatua 2: Anzisha Mradi wa Seva ya MCP

Nenda Tools → Add Tool katika Agent Builder
Chagua "MCP Server" kutoka kwa chaguzi zilizopo
Chagua "Create A new MCP Server"
Chagua templeti ya python-weather
Weka jina la seva yako: weather_mcp

Hatua 3: Fungua na Kagua Mradi

Fungua mradi uliotengenezwa katika VS Code

Pitia muundo wa mradi:

weather_mcp/
├── src/
│   ├── __init__.py
│   └── server.py
├── inspector/
│   ├── package.json
│   └── package-lock.json
├── .vscode/
│   ├── launch.json
│   └── tasks.json
├── pyproject.toml
└── README.md

Hatua 4: Sasisha MCP SDK hadi Toleo la Hivi Karibuni

🔍 Kwa Nini Kusasisha? Tunataka kutumia toleo jipya la MCP SDK (v1.9.3) na huduma ya Inspector (0.14.0) kwa vipengele vya hali ya juu na kufuatilia makosa kwa ufanisi zaidi.

4a. Sasisha Mategemeo ya Python

Hariri pyproject.toml: update ./code/weather_mcp/pyproject.toml

4b. Update Inspector Configuration

Edit inspector/package.json: update ./code/weather_mcp/inspector/package.json

4c. Update Inspector Dependencies

Edit inspector/package-lock.json: update ./code/weather_mcp/inspector/package-lock.json

📝 Note: This file contains extensive dependency definitions. Below is the essential structure - the full content ensures proper dependency resolution.

⚡ Full Package Lock: The complete package-lock.json contains ~3000 lines of dependency definitions. The above shows the key structure - use the provided file for complete dependency resolution.

Step 5: Configure VS Code Debugging

Note: Please copy the file in the specified path to replace the corresponding local file

5a. Update Launch Configuration

Edit .vscode/launch.json:

{
  "version": "0.2.0",
  "configurations": [
    {
      "name": "Attach to Local MCP",
      "type": "debugpy",
      "request": "attach",
      "connect": {
        "host": "localhost",
        "port": 5678
      },
      "presentation": {
        "hidden": true
      },
      "internalConsoleOptions": "neverOpen",
      "postDebugTask": "Terminate All Tasks"
    },
    {
      "name": "Launch Inspector (Edge)",
      "type": "msedge",
      "request": "launch",
      "url": "http://localhost:6274?timeout=60000&serverUrl=http://localhost:3001/sse#tools",
      "cascadeTerminateToConfigurations": [
        "Attach to Local MCP"
      ],
      "presentation": {
        "hidden": true
      },
      "internalConsoleOptions": "neverOpen"
    },
    {
      "name": "Launch Inspector (Chrome)",
      "type": "chrome",
      "request": "launch",
      "url": "http://localhost:6274?timeout=60000&serverUrl=http://localhost:3001/sse#tools",
      "cascadeTerminateToConfigurations": [
        "Attach to Local MCP"
      ],
      "presentation": {
        "hidden": true
      },
      "internalConsoleOptions": "neverOpen"
    }
  ],
  "compounds": [
    {
      "name": "Debug in Agent Builder",
      "configurations": [
        "Attach to Local MCP"
      ],
      "preLaunchTask": "Open Agent Builder",
    },
    {
      "name": "Debug in Inspector (Edge)",
      "configurations": [
        "Launch Inspector (Edge)",
        "Attach to Local MCP"
      ],
      "preLaunchTask": "Start MCP Inspector",
      "stopAll": true
    },
    {
      "name": "Debug in Inspector (Chrome)",
      "configurations": [
        "Launch Inspector (Chrome)",
        "Attach to Local MCP"
      ],
      "preLaunchTask": "Start MCP Inspector",
      "stopAll": true
    }
  ]
}

Hariri .vscode/tasks.json:

{
  "version": "2.0.0",
  "tasks": [
    {
      "label": "Start MCP Server",
      "type": "shell",
      "command": "python -m debugpy --listen 127.0.0.1:5678 src/__init__.py sse",
      "isBackground": true,
      "options": {
        "cwd": "${workspaceFolder}",
        "env": {
          "PORT": "3001"
        }
      },
      "problemMatcher": {
        "pattern": [
          {
            "regexp": "^.*$",
            "file": 0,
            "location": 1,
            "message": 2
          }
        ],
        "background": {
          "activeOnStart": true,
          "beginsPattern": ".*",
          "endsPattern": "Application startup complete|running"
        }
      }
    },
    {
      "label": "Start MCP Inspector",
      "type": "shell",
      "command": "npm run dev:inspector",
      "isBackground": true,
      "options": {
        "cwd": "${workspaceFolder}/inspector",
        "env": {
          "CLIENT_PORT": "6274",
          "SERVER_PORT": "6277",
        }
      },
      "problemMatcher": {
        "pattern": [
          {
            "regexp": "^.*$",
            "file": 0,
            "location": 1,
            "message": 2
          }
        ],
        "background": {
          "activeOnStart": true,
          "beginsPattern": "Starting MCP inspector",
          "endsPattern": "Proxy server listening on port"
        }
      },
      "dependsOn": [
        "Start MCP Server"
      ]
    },
    {
      "label": "Open Agent Builder",
      "type": "shell",
      "command": "echo ${input:openAgentBuilder}",
      "presentation": {
        "reveal": "never"
      },
      "dependsOn": [
        "Start MCP Server"
      ],
    },
    {
      "label": "Terminate All Tasks",
      "command": "echo ${input:terminate}",
      "type": "shell",
      "problemMatcher": []
    }
  ],
  "inputs": [
    {
      "id": "openAgentBuilder",
      "type": "command",
      "command": "ai-mlstudio.agentBuilder",
      "args": {
        "initialMCPs": [ "local-server-weather_mcp" ],
        "triggeredFrom": "vsc-tasks"
      }
    },
    {
      "id": "terminate",
      "type": "command",
      "command": "workbench.action.tasks.terminate",
      "args": "terminateAll"
    }
  ]
}

🚀 Kuendesha na Kupima Seva Yako ya MCP

Hatua 6: Sakinisha Mategemeo

Baada ya kufanya mabadiliko, tumia amri hizi:

Sakinisha mategemeo ya Python:

uv sync

Sakinisha mategemeo ya Inspector:

cd inspector
npm install

Hatua 7: Fuatilia Makosa kwa Agent Builder

Bonyeza F5 au tumia usanidi wa "Debug in Agent Builder"
Chagua usanidi wa pamoja kutoka kwenye paneli ya ufuatiliaji
Subiri seva ianze na Agent Builder ifunguke
Jaribu seva yako ya weather MCP kwa maswali ya lugha ya kawaida

Ingiza ombi kama hili

SYSTEM_PROMPT

You are my weather assistant

USER_PROMPT

How's the weather like in Seattle

Hatua 8: Fuatilia Makosa kwa MCP Inspector

Tumia usanidi wa "Debug in Inspector" (Edge au Chrome)
Fungua kiolesura cha Inspector kwa http://localhost:6274
Chunguza mazingira ya majaribio ya mwingiliano:
- Angalia zana zilizopo
- Jaribu utekelezaji wa zana
- Fuata maombi ya mtandao
- Fuatilia majibu ya seva

🎯 Matokeo Muhimu ya Kujifunza

Kwa kumaliza maabara hii, ume:

Kuunda seva ya MCP maalum kwa kutumia templeti za AI Toolkit
Kusasaisha hadi MCP SDK ya hivi karibuni (v1.9.3) kwa vipengele bora
Kusakinisha mchakato wa kitaalamu wa kufuatilia makosa kwa Agent Builder na Inspector
Kuweka MCP Inspector kwa majaribio ya seva kwa mwingiliano
Kuwa mtaalamu wa usanidi wa ufuatiliaji makosa wa VS Code kwa maendeleo ya MCP

🔧 Vipengele vya Juu Vilivyogunduliwa

Kipengele	Maelezo	Matumizi
MCP Python SDK v1.9.3	Utekelezaji wa itifaki ya hivi karibuni	Maendeleo ya seva za kisasa
MCP Inspector 0.14.0	Chombo cha kufuatilia makosa kwa mwingiliano	Majaribio ya seva kwa wakati halisi
VS Code Debugging	Mazingira ya maendeleo yaliyojumuishwa	Mchakato wa kitaalamu wa kufuatilia makosa
Agent Builder Integration	Muunganisho wa moja kwa moja wa AI Toolkit	Majaribio ya agent kutoka mwanzo hadi mwisho

📚 Rasilimali Zaidi

🎉 Hongera! Umefanikiwa kumaliza Lab 3 na sasa unaweza kuunda, kufuatilia makosa, na kupeleka seva za MCP maalum kwa kutumia mchakato wa maendeleo ya kitaalamu.

🔜 Endelea kwenye Moduli Ifuatayo

Uko tayari kutumia ujuzi wako wa MCP katika mchakato halisi wa maendeleo? Endelea kwenye Module 4: Practical MCP Development - Custom GitHub Clone Server ambapo utajifunza:

Kujenga seva ya MCP inayotumika katika mazingira ya uzalishaji kwa kuendesha shughuli za GitHub
Kutekeleza utendaji wa kunakili repositori za GitHub kupitia MCP
Kuunganisha seva za MCP maalum na VS Code na GitHub Copilot Agent Mode
Kupima na kupeleka seva za MCP maalum katika mazingira ya uzalishaji
Kujifunza mchakato wa otomatiki wa kazi kwa waendelezaji

Kiarifu:
Hati hii imetafsiriwa kwa kutumia huduma ya tafsiri ya AI Co-op Translator. Ingawa tunajitahidi kuwa sahihi, tafadhali fahamu kuwa tafsiri za kiotomatiki zinaweza kuwa na makosa au upungufu wa usahihi. Hati asilia katika lugha yake ya asili inapaswa kuchukuliwa kama chanzo cha mamlaka. Kwa taarifa muhimu, tafsiri ya mtaalamu wa binadamu inapendekezwa. Hatubebeki dhima kwa kutoelewana au tafsiri potofu zinazotokana na matumizi ya tafsiri hii.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

🔧 Module 3: Maendeleo ya Juu ya MCP kwa AI Toolkit

🎯 Malengo ya Kujifunza

📋 Mahitaji ya Awali

🏗️ Kile Utakachojenga

🔧 Muhtasari wa Vipengele Muhimu

🐍 MCP Python SDK

🔍 MCP Inspector

📖 Hatua kwa Hatua ya Utekelezaji

Hatua 1: Unda WeatherAgent katika Agent Builder

Hatua 2: Anzisha Mradi wa Seva ya MCP

Hatua 3: Fungua na Kagua Mradi

Hatua 4: Sasisha MCP SDK hadi Toleo la Hivi Karibuni

4a. Sasisha Mategemeo ya Python

4b. Update Inspector Configuration

4c. Update Inspector Dependencies

Step 5: Configure VS Code Debugging

5a. Update Launch Configuration

🚀 Kuendesha na Kupima Seva Yako ya MCP

Hatua 6: Sakinisha Mategemeo

Hatua 7: Fuatilia Makosa kwa Agent Builder

Hatua 8: Fuatilia Makosa kwa MCP Inspector

🎯 Matokeo Muhimu ya Kujifunza

🔧 Vipengele vya Juu Vilivyogunduliwa

📚 Rasilimali Zaidi

🔜 Endelea kwenye Moduli Ifuatayo

FilesExpand file tree

README.md

Latest commit

History

README.md

File metadata and controls

🔧 Module 3: Maendeleo ya Juu ya MCP kwa AI Toolkit

🎯 Malengo ya Kujifunza

📋 Mahitaji ya Awali

🏗️ Kile Utakachojenga

🔧 Muhtasari wa Vipengele Muhimu

🐍 MCP Python SDK

🔍 MCP Inspector

📖 Hatua kwa Hatua ya Utekelezaji

Hatua 1: Unda WeatherAgent katika Agent Builder

Hatua 2: Anzisha Mradi wa Seva ya MCP

Hatua 3: Fungua na Kagua Mradi

Hatua 4: Sasisha MCP SDK hadi Toleo la Hivi Karibuni

4a. Sasisha Mategemeo ya Python

4b. Update Inspector Configuration

4c. Update Inspector Dependencies

Step 5: Configure VS Code Debugging

5a. Update Launch Configuration

🚀 Kuendesha na Kupima Seva Yako ya MCP

Hatua 6: Sakinisha Mategemeo

Hatua 7: Fuatilia Makosa kwa Agent Builder

Hatua 8: Fuatilia Makosa kwa MCP Inspector

🎯 Matokeo Muhimu ya Kujifunza

🔧 Vipengele vya Juu Vilivyogunduliwa

📚 Rasilimali Zaidi

🔜 Endelea kwenye Moduli Ifuatayo