fin-products-tools
MCP server that provides tools to query Korean financial products (savings, deposits, pensions, mortgages, loans) via the FSS Open API, enabling search by company or product type.
README
Fin Products Tools (금융상품 조회 MCP·CLI 도구)
금융감독원 금융상품한눈에 Open API를 기반으로 금융상품을 조회하는 MCP·CLI 도구입니다.
예적금, 연금저축, 주택담보대출, 전세자금대출, 개인신용대출 데이터를 일관된 MCP 및 CLI 인터페이스로 조회할 수 있습니다.
Fin Products Tools is an MCP/CLI tool for querying financial product datasets based on FSS Open APIs.
It provides a consistent MCP and CLI interface for these financial product datasets.
Architecture
- Client:
src/fss_tools/clients/fss_client.py - Service/normalization:
src/fss_tools/services/data_service.py - CLI:
src/fss_tools/cli/main.py - MCP:
src/fss_tools/mcp/server.py
Implemented API coverage
- 금융상품한눈에 (
finlife)saving(적금)deposit(정기예금)pension_saving(연금저축)mortgage(주택담보대출)jeonse(전세자금대출)personal_loan(개인신용대출)
Setup
cp .env.example .env
python -m venv .venv
source .venv/bin/activate
pip install -e .[dev]
Set env vars:
export FSS_API_KEY="your_api_key"
export OUTPUT_FORMAT="json" # or "table"
Commands
# 기본
fin-products --help
# 금융상품
# 회사 먼저 검색해서 코드 확인
fin-products search-financial-company "농협"
# 회사코드로 정기예금 검색 (회사 코드 생략 시 전체 검색)
# query는 finlife 명세상 financeCd(회사코드/회사명)로 매핑됨
fin-products products --kind deposit --query "농협"
fin-products products --kind deposit --company-code 0013175 --query "농협"
MCP server setup
1) Install package
python -m venv .venv
source .venv/bin/activate
pip install -e .
2) Set environment variables
export FSS_API_KEY="your_api_key"
export OUTPUT_FORMAT="json"
3) Run MCP server (stdio)
fin-products-mcp
4) Example MCP client config (Claude Desktop)
claude_desktop_config.json example:
{
"mcpServers": {
"fin-products-tools": {
"command": "/bin/bash",
"args": [
"-lc",
"cd /path/to/fin-products-tools && source .venv/bin/activate && export FSS_API_KEY=YOUR_API_KEY && fin-products-mcp"
]
}
}
}
MCP tools
1) search_financial_company(query, page=1, size=20, top_group="020000")
- 금융회사 검색 (회사코드 조회용)
- 권장 사용: 먼저 회사 검색 →
company_code확보 → 상품 툴 정밀 조회
2) search_savings(query=None, company_code=None, page=1, size=20, top_group="020000", all_groups=False)
- 적금 상품 조회 (
savingProductsSearch) query는 내부적으로financeCd로 매핑됨company_code지정 시query보다 우선all_groups=True면 은행(020000)+저축은행(030300) 통합 조회
3) search_deposits(query=None, company_code=None, page=1, size=20, top_group="020000", all_groups=False)
- 정기예금 상품 조회 (
depositProductsSearch) query/company_code우선순위는 위와 동일all_groups=True면 은행(020000)+저축은행(030300) 통합 조회
4) search_pension_saving(query=None, company_code=None, page=1, size=20, top_group="020000", all_groups=False)
- 연금저축 상품 조회 (
annuitySavingProductsSearch) - 기본:
all_groups=False→top_group단일 조회 - 통합:
all_groups=True→ 보험(050000)+금융투자(060000) 병합 조회 (중복 제거)
5) search_mortgage(query=None, company_code=None, page=1, size=20, top_group="020000")
- 주택담보대출 상품 조회 (
mortgageLoanProductsSearch)
6) search_jeonse(query=None, company_code=None, page=1, size=20, top_group="020000")
- 전세자금대출 상품 조회 (
rentHouseLoanProductsSearch)
7) search_personal_loan(query=None, company_code=None, page=1, size=20, top_group="020000")
- 개인신용대출 상품 조회 (
creditLoanProductsSearch)
top_group(권역코드) 참고
020000: 은행030200: 여신전문030300: 저축은행050000: 보험060000: 금융투자
Tests
PYTHONPATH=src python3 -m pytest -q
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.