TGCode

关注互联网技术

Elasticsearch：交易搜索 – MCP

2026年2月24日   |   by mebius

%title插图%num

在今天的文章里，我们来展示一下如何使用 MCP 来进行交易搜索。

安装

Elasticsearch 及 Kibana

如果你还没有安装好自己的 Elasticsearch 及 Kibana，那么请参考一下的文章来进行安装：

在安装的时候，请选择 Elastic Stack 8.x/9.x进行安装。在安装的时候，我们可以看到如下的安装信息：

%title插图%num​​

在本文中，我们使用 Elastic Stack 9.1.2 来进行展示。

启动白金试用

我们需要使用到内置的 ELSER 模型来向量化我们的数据。我们需要启动白金试用：

%title插图%num​​

%title插图%num​​

%title插图%num​​

%title插图%num​​

这样就启动了白金试用。

下载代码

我们按照如下的方式来下载代码：

git clone https://github.com/liu-xiao-guo/transaction_search_mcp

我们可以看到如下的文件：

$ pwd
/Users/liuxg/python/transaction_search_mcp
$ ls -al
total 32
drwxr-xr-x  11 liuxg  staff   352 Feb 10 14:12 .
drwxr-xr-x@ 38 liuxg  staff  1216 Feb 10 14:12 ..
-rw-r--r--   1 liuxg  staff   838 Feb 10 14:12 .env.example
drwxr-xr-x  12 liuxg  staff   384 Feb 10 14:12 .git
-rw-r--r--   1 liuxg  staff  4050 Feb 10 14:12 .gitignore
-rw-r--r--   1 liuxg  staff  4501 Feb 10 14:12 README.md
drwxr-xr-x   4 liuxg  staff   128 Feb 10 14:12 docs
drwxr-xr-x   4 liuxg  staff   128 Feb 10 14:12 requirements
drwxr-xr-x   6 liuxg  staff   192 Feb 10 14:12 scripts
drwxr-xr-x   5 liuxg  staff   160 Feb 10 14:12 src
drwxr-xr-x   3 liuxg  staff    96 Feb 10 14:12 tests

我们把 .env.example 拷贝到 .env 文件中去：

# Copy environment template
cp .env.example .env

# Edit .env with your configuration
# - Elasticsearch URL and credentials
# - OpenAI API key (for LLM client)

.env

# Elasticsearch Configuration
ELASTICSEARCH_HOST=https://localhost:9200
ELASTICSEARCH_USERNAME=elastic
ELASTICSEARCH_PASSWORD=LYXAfNkSab8QwsbrriYN
ELASTICSEARCH_API_KEY=X3NZeFJwd0Itb1hyWHlSejg4c3c6bHdwWGhaVTRBRTA1WnF1TUlUd1c2dw==
ELASTICSEARCH_INDEX=banking_transactions

OPEN_AI_KEY=
transaction_search_mcp/
├── src/                          # Source code
│   ├── server/                   # MCP server implementation
│   │   └── server.py            # Main MCP server with transaction search tools
│   └── clients/                 # Client applications
│       ├── chat_client.py       # Basic Streamlit chat interface
│       └── chat_client_llm.py   # Enhanced LLM-powered chat client
├── scripts/                     # Setup and utility scripts
│   ├── setup_elasticsearch.py   # Basic Elasticsearch setup with test data
│   ├── setup_elasticsearch_llm.py # Enhanced setup with realistic test data
│   ├── run_chat.py             # Launch basic chat client
│   └── run_llm_chat.py         # Launch LLM-powered chat client
├── tests/                       # Test files
│   └── test_server.py          # Comprehensive server tests
├── docs/                        # Documentation
│   ├── README.md               # Basic implementation docs
│   └── README_LLM.md           # LLM-enhanced version docs
├── requirements/                # Dependencies
│   ├── requirements.txt        # Server dependencies
│   └── client_requirements.txt # Client dependencies
├── .env                        # Environment variables (not in git)
├── .env.example               # Environment template
└── .gitignore            tgcode     # Git ignore rules

创建虚拟环境

我们使用如下的命令：

$ python -m venv .venv
$ source .venv/bin/activate
(.venv) $ # Server dependencies
pip install -r requirements/requiremtgcodeents.txt

# Client dependencies (for chat interfaces)
pip install -r requirements/client_requirements.txt

设置 Elasticsearch

我们运行如下的命令：

python scripts/setup_elasticsearch.py

%title插图%num​

我们可以到 Kibana 中进行查看：

%title插图%num​

我们可以看到有 500 个交易记录。其中的一个交易记录如下：

GET banking_transactions/_doc/txn_000001
{
  "_index": "banking_transactions",
  "_id": "txn_000001",
  "_version": 1,
  "_seq_no": 0,
  "_primary_term": 1,
  "found": true,
  "_source": {
    "transaction_id": "txn_000001",
    "account_id": "acc_001",
    "account_type": "savings",
    "transaction_date": "2026-01-16",
    "posted_date": "2026-01-17",
    "amount": -47.64,
    "currency": "USD",
    "description": "Home Depot - car_wash",
    "memo": "Purchase at Home Depot",
    "reference": "REF271525",
    "merchant": "Home Depot",
    "category": "gas",
    "subcategory": "car_wash",
    "transaction_type": "fee",
    "location": {
      "city": "Austin",
      "state": "tgcodeTX",
      "country": "US",
      "postal_code": "73301",
      "coordinates": {
        "lat": 33.40455,
        "lon": -96.542508
      }
    },
    "tags": [
      "transportation"
    ],
    "balance_after": 3929.25,
    "is_pending": false,
    "is_recurring": false,
    "created_at": "2026-02-10T14:34:40.767Z",
    "updated_at": "2026-02-10T14:34:40.767Z"
  }
}

如果我们希望使用 LLM 来帮我们生成相应的模拟数据，我们可以运行：

python scripts/setup_elasticsearch_llm.py

这些数据将更符合现实的实际交易。如果你不知道如何设置 LM Studio 来部署大模型，请阅读之前的文章 ”使用 Elastic 和 LM Studio 的 Herding Llama 3.1“。

在我的代码中，我使用 OpenAI 来生成需要的 500 个模拟文档：

(.venv) $ python scripts/setup_elasticsearch_llm_openai.py
(.venv) $ pwd
/Users/liuxg/python/transaction_search_mcp
(.venv) $ python scripts/setup_elasticsearch_llm_openai.py
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/elasticsearch/_sync/client/__init__.py:402: SecurityWarning: Connecting to 'https://localhost:9200' using TLS with verify_certs=False is insecure
  _transport = transport_class(
Connecting to Elasticsearch at https://localhost:9200...
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
✅ Connected to Elasticsearch
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
 Creating index: banking_transactions
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
✅ Index created successfully
 Generating AI-enhanced test transaction data...
✅ Connected to OpenAI - using AI for realistic transaction generation with gpt-4-turbo-preview
 Generating 500 realistic transactions...
   Generated 0/500 transactions...
   Generated 50/500 transactions...
   Generated 100/500 transactions...
   Generated 150/500 transactions...
   Generated 200/500 transactions...
   Generated 250/500 transactions...
   Generated 300/500 transactions...
   Generated 350/500 transactions...
   Generated 400/500 transactions...
   Generated 450/500 transactions...
✅ Generated 500 transactions
 Indexing 500 transactions...
/Users/liuxg/python/transaction_search_mcp/scripts/setup_elasticsearch_llm_openai.py:513: DeprecationWarning: Passing transport options in the API method is deprecated. Use 'Elasticsearch.options()' instead.
  success, failed = bulk(es, doc_generator(), chunk_size=50, request_timeout=60)
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
✅ Successfully indexed 500 transactions
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
/Users/liuxg/python/transaction_search_mcp/.venv/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'localhost'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
 Index 'banking_transactions' now contains 500 documents
 Setup completed successfully!

 Sample search queries you can try:
- Search for coffee shop transactions
- Find all grocery purchases over $50
- Look for gas station visits in San Francisco
- Find streaming service subscriptions
- Search for business-related expenses

运行 MCP 服务器

我们使用如下的命令来运行服务器：

# Start MCP server
python src/server/server.py

运行客户端

我们运行如下的命令：

python scripts/run_chat.py

%title插图%num​

我们可以看到如上的界面。我们可以尝试如下的搜索：

%title插图%num​

%title插图%num​

我们可以使用由 LLM 驱动的界面：

python scripts/run_llm_chat.py

%title插图%num

我再尝试其它的查询：

What did I spend on groceries this year?

%title插图%num

查找所有在 San Francisco 超过 $100 的交易

%title插图%num

提供过去 3 个月的消费汇总

%title插图%num

源码请在地址https://github.com/liu-xiao-guo/transaction_search_mcp下载。

文章来源于互联网:Elasticsearch：交易搜索 – MCP

相关推荐: DevRel 通讯 — 2026 年 2 月

作者：来自 ElasticElastic DevRel team 来自 Elastic DevRel 团队的问候！在本期通讯中，我们将介绍 Elasticsearch 和 Elastic Stack 的 9.3 版本、最新的博客和视频，以及即将举行的活动，包括…

Tags: , , , , , , ,