Skip to main content
Glama
JediPercy

fin-copilot-mcp

by JediPercy

Multi-Agent Financial Analytics Copilot (fin-copilot-mcp)

CI/CD Pipeline Python 3.11+ Code Style: Ruff License: MIT

An enterprise-grade, deterministic multi-agent financial analytics engine built on Anthropic's Model Context Protocol (MCP) and Claude 3.5 Sonnet. The system processes complex natural language financial queries, translates them into dialect-validated PostgreSQL / DuckDB SQL, pulls live telemetry/market data, and executes a self-healing verification loop before presenting synthesized results.


🏗 Architecture & Agent Topology

The system uses specialized, domain-isolated agents decoupled from underlying tools using MCP JSON-RPC protocol standards.

                    ┌─────────────────────────────────────────┐
                    │       User Query Interface / API       │
                    └────────────────────┬────────────────────┘
                                         │
                                         ▼
                    ┌─────────────────────────────────────────┐
                    │ Orchestrator Agent (Claude 3.5 Sonnet)  │
                    └────────────────────┬────────────────────┘
                                         │
         ┌───────────────────────────────┼───────────────────────────────┐
         │ (MCP Protocol)                │ (MCP Protocol)                │ (MCP Protocol)
         ▼                               ▼                               ▼
┌──────────────────┐           ┌──────────────────┐           ┌──────────────────┐
│  mcp-server-sql  │           │mcp-server-stripe │           │mcp-server-market │
│ (PostgreSQL/Duck)│           │  (Billing Specs) │           │ (YFinance API)   │
└────────┬─────────┘           └──────────────────┘           └──────────────────┘
         │
         │ (Execution Error)
         ▼
┌──────────────────┐
│  Self-Healing    │ ── (Retry Stack Trace) ──► [ Orchestrator Agent ]
│  Validation Loop │
└──────────────────┘

Related MCP server: Signal8 MCP Server

🔑 Key Features

  • MCP-Native Architecture: Fully decoupled tool servers using standard JSON-RPC over stdio / Server-Sent Events (SSE).

  • Self-Healing Text-to-SQL Loop: Runs deterministic dry-run verification (EXPLAIN) before execution. Automatically captures AST/syntax errors and feeds stack traces back to Claude for up to 3 repair retries.

  • Double-Entry Validation: Micro-agent verifying mathematical consistency, row cross-totals, and currency alignment prior to output synthesis.

  • Strict Type & Schema Safety: Runtime validation via Pydantic v2 and static type checking with MyPy.

  • Cross-Platform Developer Experience: Powers setup, linting, formatting, and testing on Windows (via PowerShell / py) and Linux/macOS seamlessly.


🛠 Tech Stack

Component

Technology

Purpose

LLM / Reasoning

Claude 3.5 Sonnet (anthropic)

Intent decomposition, tool orchestration, and SQL generation

Protocol Layer

FastMCP / Model Context Protocol

Standardized tool/resource encapsulation over JSON-RPC

Analytical Engine

PostgreSQL / DuckDB / SQLite

OLAP/OLTP query execution, AST validation, and schema inspection

Market Data

Yahoo Finance (yfinance)

Macroeconomic benchmarks, equity quotes, and volume metrics

Configuration

pydantic-settings

Type-safe environment management and secret handling

Developer Tooling

uv / pip, ruff, mypy, pytest

Hermetic builds, linting, typing, and testing


📁 Repository Structure

fin-copilot-mcp/
├── .github/
│   └── workflows/
│       └── ci.yml                 # CI pipeline (lint, type-check, unit & integration tests)
├── config/
│   └── mcp_servers.json          # System tool topologies and connection mappings
├── docker/
│   ├── Dockerfile.orchestrator    # Production container for agent runtime
│   └── Dockerfile.mcp-server      # Container specification for standalone MCP servers
├── src/
│   └── fin_copilot/
│       ├── core/                  # Base configuration, logging, exceptions
│       ├── mcp_servers/           # Standalone FastMCP server modules (SQL, Stripe, Market)
│       ├── agents/                # Orchestrator agent logic, prompts, and healing loops
│       └── utils/                 # Telemetry and formatting helpers
├── tests/
│   ├── unit/                      # FastMCP tool & resource unit tests
│   ├── integration/               # Multi-agent self-healing loop tests
│   └── evals/                     # Benchmarks for Text-to-SQL translation accuracy
├── scripts/
│   ├── setup.ps1                  # Windows PowerShell setup script
│   └── setup.sh                   # Linux / macOS bash setup script
├── pyproject.toml                 # Packaging, dependencies, and linter rules
├── .gitignore                     # Industry-standard Python ignore rules
├── .env.example                   # Environment variable template
└── README.md

🚀 Quickstart

Prerequisites

  • Python >= 3.11

  • uv or standard pip

  • Anthropic API Key (ANTHROPIC_API_KEY)

Installation & Setup

On Windows (PowerShell):

# 1. Clone the repository
git clone https://github.com/your-username/fin-copilot-mcp.git
cd fin-copilot-mcp

# 2. Run PowerShell Setup Script
.\scripts\setup.ps1

# 3. Configure environment variables
Copy-Item .env.example .env

On Linux / macOS (Bash):

# 1. Clone the repository
git clone https://github.com/your-username/fin-copilot-mcp.git
cd fin-copilot-mcp

# 2. Run Setup Script
chmod +x ./scripts/setup.sh
./scripts/setup.sh

# 3. Configure environment variables
cp .env.example .env

🛡 Security & Guardrails

  • Read-Only Database Connections: SQL MCP server limits execution strictly to SELECT statements and dialect dry-runs.

  • Token Sandboxing: API keys are isolated within environment settings classes and never exposed across tool execution boundaries.

  • Data Masking: Structural masking applied to sensitive financial attributes prior to model context generation.


📜 License

Distributed under the MIT License. See LICENSE for details.

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    -
    quality
    D
    maintenance
    An agentic AI system that orchestrates multiple specialized AI tools to perform business analytics and knowledge retrieval, allowing users to analyze data and access business information through natural language queries.
    4
  • A
    license
    -
    quality
    D
    maintenance
    Enables natural language portfolio monitoring, risk analysis, and compliance checking with tools for real-time portfolio status, risk metrics, anomaly detection, SEC filings search, market KPIs, and compliance validation.
    MIT
  • A
    license
    B
    quality
    A
    maintenance
    Provides 77 deterministic financial calculators, live market data, and a meta-advisor that chains tools into prioritized plans from plain-language descriptions.
    77
    5
    MIT

View all related MCP servers

Related MCP Connectors

  • The financial MCP for AI agents - 90+ financial tables, SEC filings, signals, alt-data.

  • Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.

  • Source-linked SEC 13F research, quality checks, watchlists and audit trails for agents.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/JediPercy/fin-copilot-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server