BankRegPulse
BankRegPulse MCP Server connects AI assistants to live banking regulatory data from 100+ sources including OCC, FDIC, CFPB, Federal Reserve, and all 50 state banking departments. Three tools: daily intelligence briefings, regulatory podcast audio, and pre-formatted LinkedIn posts ā all updated daily at 6 AM EST.
README
BankRegPulse MCP Server
Real-time banking regulatory intelligence for AI assistants
Connect your AI assistant (Claude, ChatGPT, etc.) to live banking regulatory data from 100+ sources including OCC, FDIC, CFPB, Federal Reserve, and all 50 state banking departments.
What is This?
BankRegPulse MCP Server is a Model Context Protocol server that lets AI assistants query our regulatory intelligence database in real-time.
Instead of manually searching for regulatory updates, just ask your AI:
- "What's in today's banking regulatory briefing?"
- "Play today's regulatory podcast"
- "Draft a LinkedIn post about today's CFPB updates"
Your AI will pull fresh data from BankRegPulse and answer with context.
Features
šÆ Three Core Tools
| Tool | Description | Example Use |
|---|---|---|
get_daily_briefing |
Daily regulatory intelligence summary | "What did the OCC publish today?" |
get_daily_podcast |
Audio briefing URL | "Get today's regulatory podcast" |
get_linkedin_post |
Pre-formatted social content | "Draft a LinkedIn post about today's news" |
š Data Coverage
- Federal Agencies: OCC, FDIC, CFPB, Federal Reserve, Treasury
- State Banking Departments: All 50 states
- Congress: House Financial Services, Senate Banking
- Federal Register: Final rules, proposed rules, notices
- News: Reuters, American Banker, PYMNTS, Banking Dive
- Update Frequency: Real-time (monitored 24/7)
Installation
Prerequisites
- Node.js 18 or higher
- An MCP-compatible AI assistant (Claude Desktop, Continue.dev, etc.)
Option 1: NPM (Recommended)
npx bankregpulse-mcp-server
Option 2: From Source
git clone https://github.com/RRGU26/bankregpulse-mcp-server.git
cd bankregpulse-mcp-server
npm install
npm run build
Setup for Claude Desktop
-
Locate Claude Desktop config:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
-
Add BankRegPulse MCP server:
{
"mcpServers": {
"bankregpulse": {
"command": "npx",
"args": ["bankregpulse-mcp-server"]
}
}
}
-
Restart Claude Desktop
-
Test it:
- Open Claude Desktop
- Ask: "What's in today's banking regulatory briefing?"
- Claude will query the MCP server and return live data
Setup for Other AI Assistants
Continue.dev (VS Code)
Add to ~/.continue/config.json:
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": ["bankregpulse-mcp-server"]
}
}
]
}
}
Custom Integration
Any MCP-compatible client can connect via stdio:
import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js';
const transport = new StdioClientTransport({
command: 'npx',
args: ['bankregpulse-mcp-server']
});
const client = new Client({
name: 'my-client',
version: '1.0.0'
}, {
capabilities: {}
});
await client.connect(transport);
HTTP/SSE Mode
Run the MCP server as an HTTP endpoint instead of stdio:
# Set environment variable
export MCP_TRANSPORT=http
export PORT=3000 # optional, defaults to 3000
# Run server
npx bankregpulse-mcp-server
Endpoints:
GET /health- Health checkGET /sse- SSE endpoint for MCP connections
Connect via HTTP:
import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { SSEClientTransport } from '@modelcontextprotocol/sdk/client/sse.js';
const transport = new SSEClientTransport(
new URL('http://localhost:3000/sse')
);
const client = new Client({
name: 'my-client',
version: '1.0.0'
}, {
capabilities: {}
});
await client.connect(transport);
Test with curl:
# Health check
curl http://localhost:3000/health
# SSE connection (requires MCP client)
curl -N http://localhost:3000/sse
Usage Examples
Daily Briefing
Ask Claude:
"What's in today's banking regulatory briefing?"
Claude queries:
Tool: get_daily_briefing
Date: today
You receive:
- Executive summary of key developments
- Document count and high-priority items
- Agency-by-agency breakdown
Podcast
Ask Claude:
"Get me today's regulatory podcast"
Claude queries:
Tool: get_daily_podcast
Date: today
You receive:
- Audio URL for the daily briefing podcast
- Generated by AI from the day's regulatory developments
LinkedIn Post
Ask Claude:
"Draft a LinkedIn post about today's CFPB enforcement actions"
Claude queries:
Tool: get_linkedin_post
Date: today
You receive:
- Pre-formatted LinkedIn post with hashtags
- Key stats and highlights
- Ready to copy and share
Advanced Usage
Query Specific Dates
"What was in the regulatory briefing on February 20, 2024?"
Claude will pass date: "2024-02-20" to the tool.
Custom API Endpoint
Set environment variable to use a different API:
export BANKREGPULSE_API_URL=https://your-custom-api.com
Troubleshooting
"No briefing found"
Cause: Briefing hasn't been generated yet (runs at 6 AM EST daily)
Solution: Query yesterday's briefing or wait until morning
"API request failed"
Cause: Network issue or API is down
Solution:
- Check https://bankregpulse-enterprise-api.onrender.com/health
- Verify internet connection
- Check Render status: https://status.render.com
"Unknown tool"
Cause: MCP server not properly installed or outdated
Solution:
npm cache clean --force
npx bankregpulse-mcp-server@latest
Development
Local Development
# Clone repo
git clone https://github.com/RRGU26/bankregpulse-mcp-server.git
cd bankregpulse-mcp-server
# Install dependencies
npm install
# Build
npm run build
# Run locally
npm start
Testing with MCP Inspector
npx @modelcontextprotocol/inspector npx bankregpulse-mcp-server
Opens a web UI to test tool calls.
Architecture
āāāāāāāāāāāāāāāāāāā
ā AI Assistant ā (Claude, ChatGPT, etc.)
ā (MCP Client) ā
āāāāāāāāāā¬āāāāāāāāā
ā stdio
ā
āāāāāāāāāā¼āāāāāāāāā
ā BankRegPulse ā
ā MCP Server ā (this package)
āāāāāāāāāā¬āāāāāāāāā
ā HTTPS
ā
āāāāāāāāāā¼āāāāāāāāā
ā BankRegPulse ā
ā API ā (bankregpulse-enterprise-api.onrender.com)
āāāāāāāāāā¬āāāāāāāāā
ā
āāāāāāāāāā¼āāāāāāāāā
ā PostgreSQL ā
ā Database ā (100+ regulatory sources)
āāāāāāāāāāāāāāāāāāā
API Endpoints (Backend)
The MCP server calls these public API endpoints:
GET /api/mcp/briefing?date=YYYY-MM-DD- Daily briefingGET /api/mcp/podcast?date=YYYY-MM-DD- Podcast URLGET /api/mcp/linkedin-post?date=YYYY-MM-DD- LinkedIn post
No authentication required for basic usage.
Pricing
Free for community use.
No API key required. Rate limits apply:
- 100 requests per hour per IP
- Fair use policy
For enterprise usage (higher limits, SLA), contact: admin@bankregpulse.com
Support
- Website: https://bankregpulse.com
- Documentation: https://docs.bankregpulse.com
- Issues: https://github.com/RRGU26/bankregpulse-mcp-server/issues
- Email: admin@bankregpulse.com
Contributing
Contributions welcome! Please:
- Fork the repo
- Create a feature branch
- Submit a pull request
License
MIT License - see LICENSE for details.
Acknowledgments
- Built on Model Context Protocol by Anthropic
- Powered by BankRegPulse regulatory intelligence platform
- Regulatory data from OCC, FDIC, CFPB, Federal Reserve, and state banking departments
Related Projects
- BankRegPulse Web App - Full-featured regulatory intelligence platform
- MCP Servers - Official MCP server examples
- Awesome MCP Servers - Community-curated list
Made with ā¤ļø for the banking compliance community
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.