Investment MCP Server
Provides read-only access to a SQL Server investment database, enabling searching symbols, retrieving prices and history, and generating research snapshots.
README
Investment MCP Server
Private MCP server for your SQL Server investment database.
It exposes read-only tools over:
dbo.Seriesdbo.SeriesDatadbo.TradeGetDaysChangeReturn
The server does not expose a raw SQL tool. All database access is parameterized and scoped to your investment tables/procedure.
Install
cd "C:\Users\asmir\source\repos\investment_mcp"
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r requirements.txt
copy .env.example .env
Edit .env with your SQL Server name and database name.
SQL Permissions
Use a read-only SQL login/user if possible:
CREATE LOGIN mcp_investments_login WITH PASSWORD = 'replace-with-strong-password';
CREATE USER mcp_investments_user FOR LOGIN mcp_investments_login;
GRANT SELECT ON dbo.Series TO mcp_investments_user;
GRANT SELECT ON dbo.SeriesData TO mcp_investments_user;
GRANT EXECUTE ON dbo.TradeGetDaysChangeReturn TO mcp_investments_user;
If you use Windows authentication instead, grant the same permissions to your Windows user.
Run Locally
.\.venv\Scripts\Activate.ps1
python server.py
With MCP_TRANSPORT=stdio, the command starts silently and waits for an MCP client. A blank terminal is expected. Press Ctrl+C to stop it.
For MCP Inspector:
mcp dev server.py
Codex MCP Config Example
Add something like this to your Codex MCP config, adjusting paths and connection string:
[mcp_servers.investments]
command = "C:\\Users\\asmir\\source\\repos\\investment_mcp\\.venv\\Scripts\\python.exe"
args = ["C:\\Users\\asmir\\source\\repos\\investment_mcp\\server.py"]
env = { SQLSERVER_CONN = "DRIVER={ODBC Driver 17 for SQL Server};SERVER=localhost;DATABASE=Investments;Trusted_Connection=yes;Encrypt=yes;TrustServerCertificate=yes;" }
Tools
search_symbolsget_symbol_profileget_latest_pricesget_price_historyget_research_snapshotcompare_symbolsscreen_instrumentsget_watched_symbolsget_traded_symbolsget_data_freshness
The research tools call dbo.TradeGetDaysChangeReturn by default. If that procedure returns a large result set, create the optional filtered wrapper in sql/create_mcp_research_sp.sql and set:
MCP_RESEARCH_PROCEDURE=dbo.McpGetResearch
MCP_RESEARCH_PROCEDURE_HAS_FILTERS=true
Important
This server provides research data for analysis. It should not be connected to brokerage trading permissions, account numbers, or order-entry functions.
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.
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.
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.
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.