@erickwendel/ew-customers-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@erickwendel/ew-customers-mcp Find the customer named Ana"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@erickwendel/ew-customers-mcp
An MCP (Model Context Protocol) server that exposes a legacy customer CRUD REST API as tools, a resource, and a prompt — all runnable directly inside VS Code Copilot Chat.
This server is a thin adapter: it wraps the legacy nodejs-fastify-mongodb-crud API (Node/Fastify + MongoDB) over HTTP and does not modify it. The legacy API stays exactly as it is; only the MCP wrapper was ported from TypeScript to Python.
What it does
Capability | Name | Description |
🔧 Tool |
| Lists all customers |
🔧 Tool |
| Finds a customer by id, name, or phone |
🔧 Tool |
| Creates a customer |
🔧 Tool |
| Updates a customer's name and/or phone by id |
🔧 Tool |
| Deletes a customer by id |
📄 Resource |
| Describes the legacy REST API this server wraps |
💬 Prompt |
| Pre-built prompt that asks the agent to search a customer |
Related MCP server: Express REST API and MCP Server Framework
Architecture
src/customers_mcp/
domain/
customer.py # Pydantic models mirroring the legacy API's wire format
infrastructure/
customer_http_client.py # HTTP client for the legacy REST API
application/
customer_service.py # Business rules (find-by-any-field, delegates CRUD)
mcp/
server.py # Wires tools/resource/prompt onto a FastMCP instance
tools/ # One module per tool (SRP)
resources/
prompts/
__main__.py # Entry point — connects the server to stdio transport
tests/
conftest.py # Shared MCP client helper (async context manager)
test_customer_service.py # Unit tests (fake HTTP client, no network)
test_customer_tools.py # Integration tests via a real MCP stdio client
test_api_info_resource.py
test_find_customer_prompt.pyCustomerService receives its CustomerHttpClient via constructor injection (composed in mcp/server.py), so it can be tested in isolation with a fake client — no legacy API or network needed for test_customer_service.py.
Prerequisites
Python 3.12+
uv (recommended) or
pipThe legacy
nodejs-fastify-mongodb-crudAPI running athttp://localhost:9999(only needed to actually call the tools or run the integration tests — see that project'sdocker-compose.yml:npm run docker:infra:up)
Installation
uv syncUsing in VS Code
1. Add the MCP server configuration
Create (or open) .vscode/mcp.json in your workspace:
{
"servers": {
"customers-mcp": {
"command": "uv",
"args": ["run", "python", "-m", "customers_mcp"]
}
}
}2. Reload VS Code
Command Palette (Cmd+Shift+P) → Developer: Reload Window.
3. Use it in Copilot Chat
List all customersCreate a customer named "Ana" with phone "999-000-111"Find the customer named JohnRunning tests
uv run pytesttest_customer_service.py runs standalone (no dependencies). The other test files spawn the real MCP server and call the legacy API, so they require it running at http://localhost:9999 first.
Available commands
Command | Description |
| Start the server (used by MCP clients) |
| Run all tests |
| Lint |
| Format |
Available Tools
5 toolscreate_customerB
Create a customer
Inputs: name (required), phone (required). Returns: Result of a create/update/delete call, or an error response.
delete_customerB
Delete a customer by their id
Inputs: customer_id (required). Returns: Result of a create/update/delete call, or an error response.
get_customerA
Find a customer by id, name, or phone number
Inputs: name, phone, customer_id. Returns: customer
list_customersA
List all customers
Inputs: no named parameters. Returns: customers
update_customerA
Update an existing customer's name and/or phone number by their id
Inputs: customer_id (required), name, phone. Returns: Result of a create/update/delete call, or an error response.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clear, distinct purpose: list, get, create, update, and delete customers. No overlap or ambiguity between them.
All tools follow the consistent verb_noun pattern: list_customers, get_customer, delete_customer, create_customer, update_customer. Perfectly consistent.
With 5 tools, the set is well-scoped for a customers CRUD server. Each tool is necessary and none are redundant.
The tool set covers full CRUD operations (list, get, create, update, delete) for customers, missing only a bulk operation or search by multiple criteria, but agents can achieve most workflows.
Maintenance
Related MCP Connectors
List, read, edit, and deploy your GenMB AI-generated apps from any MCP client.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
Method CRM MCP server for ChatGPT, Claude and any AI agent: list customers and leads, list overdue invoices, create estimate, convert estimate to invoice, send invoice, record payment, create activity and convert lead to customer in your own Method CRM account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Method CRM yourself; Cotlet does not store your password and you need no Method CRM API key. About the official Method CRM API: Method CRM has a full REST API with read and write access to permitted records, but no ready-made official MCP server (checked 23 Oct 2026). Method builds a custom MCP for a customer on request. Setup and FAQ: https://cotlet.dev/integrations/method-crm-api-mcp-server
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables interaction with a REST API of customers through MCP tools, resources, and prompts, allowing listing, creating, retrieving, updating, and deleting customer records from MCP-compatible clients.ISC
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to interact directly with generated REST APIs by exposing CRUD operations as MCP tools and read-only data as resources.MIT
- AlicenseNot gradedqualityAmaintenanceEnables LLMs to interact directly with generated REST APIs by exposing CRUD actions as MCP tools and read-only data as MCP resources.MIT
- AlicenseNot gradedqualityAmaintenanceEnables LLMs to discover and invoke generated CRUD operations as MCP tools and read data through MCP resources, alongside standard REST endpoints, using one codebase.MIT