Trade Surveillance Support MCP Server
Automates trade surveillance support workflows by parsing inquiry emails, searching SQL configs and Java code using keyword-based metadata annotations, executing reports, and generating comprehensive responses.
README
Trade Surveillance Support MCP Server
An MCP (Model Context Protocol) server designed to automate trade surveillance support workflows by integrating with your existing SQL configs and Java code repositories.
Overview
This MCP server enables you to:
- Parse user inquiry emails - Extract key information from support emails automatically
- Search SQL config files - Find relevant database queries and configurations
- Search Java code - Locate report generation classes and methods
- Execute Java reports - Run Java processes to generate data and reports
- Generate response summaries - Create comprehensive responses for user inquiries
Installation
Prerequisites
- Python 3.10 or higher
uvpackage manager (recommended) orpip
Install with uv (recommended)
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Install the MCP server
uv pip install -e .
Install with pip
pip install -e .
Configuration
Setting up with VS Code
- Open VS Code Settings
- Search for "MCP"
- Add a new MCP server configuration:
{
"mcp.servers": {
"trade-surveillance": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp_test_2",
"run",
"trade-surveillance-mcp"
]
}
}
}
Setting up with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"trade-surveillance": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp_test_2",
"run",
"trade-surveillance-mcp"
]
}
}
}
macOS/Linux: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
šÆ Keyword-Based Search (No File Paths!)
Instead of searching by file paths, this MCP server uses metadata annotations so Copilot can find files by what they do:
Example SQL annotation:
-- @keywords: trade, settlement, daily, reconciliation
-- @type: compliance_report
-- @description: Daily trade settlement reconciliation report
Example Java annotation:
/**
* @keywords settlement, report, generator
* @type report_generator
* @description Generates daily settlement reports
*/
Result: Copilot searches by keywords like "settlement report" instead of file paths!
š Documentation:
- QUICKSTART.md - Get started in 5 minutes
- METADATA_GUIDE.md - Complete annotation guide
examples/- Annotated SQL and Java examples
Usage
With GitHub Copilot in VS Code
- Open a chat with Copilot
- Paste a user inquiry email
- Copilot will automatically use the MCP tools to:
- Parse the email
- Search for relevant configs by keywords (not file paths!)
- Search for Java code by keywords
- Execute reports
- Generate a response
Example prompt:
I received this email from a user:
[Paste email content here]
Can you help me investigate and generate the necessary reports?
Available Tools
1. parse_email_inquiry
Extracts key information from user inquiry emails including inquiry type, trade IDs, time periods, and priority.
2. search_sql_configs ā Metadata-based search
Searches through your SQL configuration files by keywords instead of file paths. Files are searched using metadata annotations (see METADATA_GUIDE.md).
3. search_java_code ā Metadata-based search
Locates Java classes and methods by keywords instead of file paths. Classes are found using javadoc annotations (see METADATA_GUIDE.md).
4. execute_java_report
Runs Java processes with the appropriate config files to generate reports.
5. rebuild_metadata_index
Rebuilds the search index by scanning all annotated SQL configs and Java files. Run this after adding new files or updating annotations.
6. generate_response_summary
Creates a comprehensive summary response for the user.
Project Structure
mcp_test_2/
āāā trade_surveillance_mcp/
ā āāā __init__.py
ā āāā server.py # Main MCP server implementation
āāā pyproject.toml # Project dependencies
āāā README.md
āāā .github/
āāā copilot-instructions.md
Development
Running Locally
# Run the server directly
uv run trade-surveillance-mcp
# Or with Python
python -m trade_surveillance_mcp.server
Customization
You'll need to customize the server to work with your specific repository structure:
- Update search paths - Modify
config_directoryandcode_directoryparameters - Implement email parsing - Add your email parsing logic in
parse_email_inquiry - Add file search - Implement actual file searching in
search_sql_configsandsearch_java_code - Configure Java execution - Add your Java classpath and execution logic in
execute_java_report
Connecting to Your Repository
Point the MCP server to your actual config and code repositories:
# Example: Update default directories
@mcp.tool()
async def search_sql_configs(
search_term: str,
config_directory: str = "/path/to/your/sql/configs"
):
# Your implementation
Next Steps
- ā MCP server is ready! - Restart VS Code to load it
- š Annotate your files - Add metadata keywords to your SQL configs and Java code (QUICKSTART.md)
- š Build the index - Use
rebuild_metadata_indextool in Copilot - āļø Customize paths - Update default directories in
server.pyto your repos - šÆ Test with Copilot - Paste a user email and let Copilot search by keywords!
Key Innovation: No More File Path Search! š
Your SQL configs and Java files are now searchable by keywords:
- Copilot finds files by what they do, not where they are
- Search "settlement report" instead of remembering
configs/reports/daily/settlement_v2.sql - See examples in
examples/configs/andexamples/src/
Troubleshooting
Server not appearing in VS Code
- Check the MCP server logs in VS Code Output panel
- Verify the absolute path in configuration is correct
- Ensure
uvis installed and in PATH
Python version issues
- Ensure Python 3.10+ is installed:
python --version - Use
uvfor better environment management
Java execution errors
- Verify Java is installed:
java -version - Check classpath configuration
- Ensure config files are accessible
Resources
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.