Finance MCP Server
Allows GitHub Copilot Chat to access and query finance model data through MCP tools, enabling natural language questions about revenue, COGS, and other metrics.
Provides tools for querying and analyzing finance model data stored in MongoDB, including listing collections, inspecting schemas, running filtered queries, executing aggregation pipelines, and computing summary statistics.
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., "@Finance MCP ServerWhat's the total revenue and average COGS for Q2 2026?"
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.
Finance MCP Server
Exposes your finance model data (stored in MongoDB) to GitHub Copilot Chat in VS Code via the Model Context Protocol (MCP). Runs locally.
1. Prerequisites
Node.js 18+
MongoDB running locally (
mongodon127.0.0.1:27017by default)Or run via Docker:
docker run -d -p 27017:27017 --name finance-mongo mongo
Related MCP server: MongoDB MCP Server
2. Install
cd finance-mcp-server
npm install3. Load your data
Two options:
A. Use the example seed script as a template
Edit src/seed.js — replace sampleRevenue / sampleAssumptions with your
actual finance model rows (or write a script that reads your CSV/Excel export
and inserts it). Then:
npm run seedB. Import an existing export directly If you already have your finance model as CSV/JSON:
mongoimport --db finance_model --collection revenue --type csv --headerline --file your_export.csv4. Configure environment (optional)
Copy .env.example to .env and adjust MONGODB_URI / MONGODB_DB if your
MongoDB isn't running on the default local port, or if you rename the database.
5. Connect to GitHub Copilot in VS Code
The included .vscode/mcp.json already points Copilot at this server. Steps:
Open this project's parent folder (the one containing
finance-mcp-server/) in VS Code.Make sure
.vscode/mcp.jsonis at the workspace root (adjust theargspath if you place the server folder elsewhere).Open Copilot Chat → it should detect the MCP server automatically (VS Code 1.99+, Copilot Chat with MCP support enabled).
If it doesn't auto-start, open the Command Palette → "MCP: List Servers" → start
finance-mcp-server.Ask Copilot things like:
"What collections are in the finance database?"
"Show me Q1 2026 revenue by department"
"What's the total revenue and average COGS for Q2 2026?"
Copilot will call the server's tools (list_collections, get_schema,
query_finance_data, aggregate_finance_data, get_summary_stats) instead
of guessing from text.
6. Available tools
Tool | Purpose |
| See what data exists and how many records |
| Inspect fields via a sample document before querying |
| Filter/sort/limit a collection directly |
| Run a full MongoDB aggregation pipeline |
| Quick sum/avg/min/max, optionally grouped |
7. Extending
Add more collections by just inserting into MongoDB — no server changes needed;
list_collectionsandget_schemawill pick them up automatically.If you need write access (e.g. Copilot updating assumptions), add a new tool following the same pattern in
src/index.js, but consider adding validation since writes are higher-risk than reads.
This server cannot be deployed
Maintenance
Related MCP Connectors
- Era ContextOAuthapp.era
Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more
The financial MCP for AI agents - 90+ financial tables, SEC filings, signals, alt-data.
List datasets, schemas, run APL queries, and use prompts for exploration, anomalies, and monitoring.
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to interact with MongoDB databases through a complete suite of CRUD operations, administrative tasks, and index management tools. It supports database and collection handling, aggregation pipelines, and comprehensive server monitoring via the Model Context Protocol.3MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact natively with MongoDB databases, including schema discovery, CRUD operations, aggregation pipelines, and index management via natural language.12 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with MongoDB databases through natural language, supporting document CRUD, aggregation, collection listing, and statistics.71,399 npmApache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to interact with MongoDB databases and MongoDB Atlas, supporting read-only and write operations, Atlas cluster management, and data exploration.71,399 npmApache 2.0