fin-copilot-mcp
Provides access to DuckDB databases, enabling query execution, schema inspection, and validation for financial analytics.
Provides access to PostgreSQL databases, enabling query execution, schema inspection, and validation for financial analytics.
Provides access to SQLite databases, enabling query execution, schema inspection, and validation for financial analytics.
Provides access to Stripe billing and payment data for financial analytics and reporting.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Multi-Agent Financial Analytics Copilot (fin-copilot-mcp)
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.
π Architecture & Agent Topology
The system uses specialized, domain-isolated agents decoupled from underlying tools using MCP JSON-RPC protocol standards.
βββββββββββββββββββββββββββββββββββββββββββ
β User Query Interface / API β
ββββββββββββββββββββββ¬βββββββββββββββββββββ
β
βΌ
βββββββββββββββββββββββββββββββββββββββββββ
β Orchestrator Agent (Claude 3.5 Sonnet) β
ββββββββββββββββββββββ¬βββββββββββββββββββββ
β
βββββββββββββββββββββββββββββββββΌββββββββββββββββββββββββββββββββ
β (MCP Protocol) β (MCP Protocol) β (MCP Protocol)
βΌ βΌ βΌ
ββββββββββββββββββββ ββββββββββββββββββββ ββββββββββββββββββββ
β mcp-server-sql β βmcp-server-stripe β βmcp-server-market β
β (PostgreSQL/Duck)β β (Billing Specs) β β (YFinance API) β
ββββββββββ¬ββββββββββ ββββββββββββββββββββ ββββββββββββββββββββ
β
β (Execution Error)
βΌ
ββββββββββββββββββββ
β Self-Healing β ββ (Retry Stack Trace) βββΊ [ Orchestrator Agent ]
β Validation Loop β
ββββββββββββββββββββRelated MCP server: octagon-mcp-server
π 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.
π Tech Stack
Component | Technology | Purpose |
LLM / Reasoning | Claude 3.5 Sonnet ( | 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 ( | Macroeconomic benchmarks, equity quotes, and volume metrics |
Configuration |
| Type-safe environment management and secret handling |
Developer Tooling |
| Hermetic builds, linting, typing, and testing |
π Repository Structure
fin-copilot-mcp/
βββ .github/
β βββ workflows/
β βββ ci.yml # CI pipeline (lint, type-check, unit & integration tests)
βββ config/
β βββ mcp_servers.json # System tool topologies and connection mappings
βββ docker/
β βββ Dockerfile.orchestrator # Production container for agent runtime
β βββ Dockerfile.mcp-server # Container specification for standalone MCP servers
βββ src/
β βββ fin_copilot/
β βββ core/ # Base configuration, logging, exceptions
β βββ mcp_servers/ # Standalone FastMCP server modules (SQL, Stripe, Market)
β βββ agents/ # Orchestrator agent logic, prompts, and healing loops
β βββ utils/ # Telemetry and formatting helpers
βββ tests/
β βββ unit/ # FastMCP tool & resource unit tests
β βββ integration/ # Multi-agent self-healing loop tests
β βββ evals/ # Benchmarks for Text-to-SQL translation accuracy
βββ scripts/
β βββ setup.ps1 # Windows PowerShell setup script
β βββ setup.sh # Linux / macOS bash setup script
βββ pyproject.toml # Packaging, dependencies, and linter rules
βββ .gitignore # Industry-standard Python ignore rules
βββ .env.example # Environment variable template
βββ README.mdπ Quickstart
Prerequisites
Python
>= 3.11uv or standard
pipAnthropic 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 .envOn 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 .envπ‘ 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.
π License
Distributed under the MIT License. See LICENSE for details.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
This server cannot be deployed
Maintenance
Related MCP Connectors
Unified financial infrastructure connecting AI agents directly to trade live/demo brokerage accounts, Web3 non-custodial wallets, real-time market data across equities, ETFs, crypto, forex, options, DeFi swaps, and prediction markets, institutional research feeds, and algorithmic strategy backtesters.
AI equity research engine: cited, as-of-dated claims, chains and scenarios for finance analysts.
Primary-source SEC filing intelligence and financial/disclosure reconciliation for AI agents.
Evidence-backed capital-change intelligence and sourced financial data for AI agents
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables secure, read-only analytical querying of financial data through natural language, with built-in SQL injection defense and automatic query repair.-
- FlicenseNot gradedqualityAmaintenanceEnables natural-language financial research and analysis across public filings, earnings transcripts, financial metrics, stock and crypto market data, and prediction markets, returning structured, source-backed answers within MCP clients.-
- AlicenseNot gradedqualityAmaintenanceEnables natural-language questions and structured, source-backed answers across SEC filings, earnings transcripts, company financials, stock and crypto market data, and prediction markets news and research, with orchestration, deep-research agents, and live documentation access.MIT

OpenVariance MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents to perform variance analysis, generate reconciling driver bridges and three-statement forecasts, export Excel workbooks, and analyze SEC or private-company financial data locally with engine-verified calculations.MIT