Open Finance US MCP
A standalone MCP server wrapping Mastercard Open Finance US (Finicity) APIs for open banking operations, enabling financial data access and payment services.
README
Open Finance US MCP
A standalone Model Context Protocol server
that wraps the Mastercard Open Finance US (Finicity) hosted APIs
(https://api.finicity.com). It is a separate codebase from Vima and vendors
its own Finicity client — no dependency on Vima's apis/, execute() wrapper,
or simulator.

Layout
openfinance-mcp/
src/openfinance_mcp/
finicity_client.py # vendored Finicity client (only depends on requests)
server.py # FastMCP server + tools
models.py # ToolResult envelope
spec_defaults.py # resolved spec decisions + open questions
config/settings.py # credential loader (env / dotenv / sibling vima config/.env)
__main__.py # stdio + streamable-http entry point
tests/ # unit, protocol (offline) + sandbox (live) suites
console/ # separate, independently deployable demo UI
run.sh / run.bat # one-shot start scripts for the MCP server
console/run.sh / .bat # one-shot start scripts for the Test Console
1 — Get Credentials
Credentials are issued through the Mastercard Developers portal.
-
Sign up or log in at
developer.mastercard.com. -
Click Create New Project, enter a project name, and select Open Finance from the Select your API service dropdown.
-
Select the commercial country for your end users, then click Proceed.
-
Enter a description, click Create Project.
-
In the left-hand Credentials panel click Sandbox — your three credential values are shown:
Variable Portal label OPEN_FINANCE_PARTNER_IDPartner ID OPEN_FINANCE_PARTNER_SECRETSecret OPEN_FINANCE_APP_KEYApp Key
Full quick-start guide: https://developer.mastercard.com/open-banking-us/documentation/quick-start-guide/
API base URL defaults to
https://api.finicity.com. Override withOPEN_FINANCE_API_BASE_URLif needed.
2 — Configure Credentials
Option A — Test Console UI (recommended)
Start the console (see below), then click the ⚙ Credentials button in the
top-right corner. Paste your values and click Save to .env. The file is
written to .env in the repo root.
Option B — Edit .env directly
Create .env in the repo root:
OPEN_FINANCE_PARTNER_ID=your_partner_id
OPEN_FINANCE_PARTNER_SECRET=your_partner_secret
OPEN_FINANCE_APP_KEY=your_app_key
OPEN_FINANCE_API_BASE_URL=https://api.finicity.com
Resolution order
- Process environment variables.
OPENFINANCE_MCP_ENV_FILE(explicit dotenv path)..envin this repo root.- Sibling
../vima/config/.env(auto-discovered).
3 — Start the MCP Server
The run scripts create a .venv, install dependencies, kill any previous
instance, and start the server — no manual pip install required.
macOS / Linux
./run.sh
# Defaults: transport=http, host=0.0.0.0, port=9030
Windows
run.bat
Override defaults via environment variables:
PORT=9030 TRANSPORT=http ./run.sh
Manual (without the script)
python -m venv .venv && source .venv/bin/activate
pip install -e ".[test,console]"
python -m openfinance_mcp --transport http --port 9030
4 — Start the Test Console
macOS / Linux
./console/run.sh
# open http://localhost:8080
Windows
console\run.bat
Override defaults:
PORT=8080 MCP_URL=http://localhost:9030/mcp ./console/run.sh
Manual
cd console
pip install -r requirements.txt
MCP_URL=http://localhost:9030/mcp uvicorn app:app --port 8080
Or start both MCP server and console together with Docker:
docker compose up --build
5 — Run Tests
# Offline unit + protocol tests (no credentials needed)
pytest -m "not sandbox"
# Live sandbox tests (requires valid credentials in .env)
pytest -m sandbox
Project layout (detail)
openfinance-mcp/
src/openfinance_mcp/
finicity_client.py
server.py
models.py
spec_defaults.py
config/settings.py
__main__.py
tests/
console/
app.py # FastAPI bridge (MCP client → browser)
static/ # index.html, console.js, console.css
run.sh / run.bat
docs/
console-screenshot.png
run.sh / run.bat
docker-compose.yml
pyproject.toml
Resolved spec decisions
| Question | Answer | Status |
|---|---|---|
| PSI path/body | POST /payments/customers/{id}/accounts/{aid}/payment-success-indicators, {"transaction":{"settleByDate","amount"}} |
confirmed |
| VOAI slug | voaHistory |
confirmed |
| TxPUSH body | {"callbackUrl": <url>} |
confirmed |
The console's Spec Decisions tab renders these live from the running server.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。