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.
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.
Related MCP server: sec-edgar-mcp
Tool | Description | Example Use |
| Daily regulatory intelligence summary | "What did the OCC publish today?" |
| Audio briefing URL | "Get today's regulatory podcast" |
| Pre-formatted social content | "Draft a LinkedIn post about today's news" |
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)
Node.js 18 or higher
An MCP-compatible AI assistant (Claude Desktop, Continue.dev, etc.)
npx bankregpulse-mcp-servergit clone https://github.com/RRGU26/bankregpulse-mcp-server.git
cd bankregpulse-mcp-server
npm install
npm run buildLocate Claude Desktop config:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
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
Add to ~/.continue/config.json:
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": ["bankregpulse-mcp-server"]
}
}
]
}
}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);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-serverEndpoints:
GET /health - Health check
GET /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/sseAsk Claude:
"What's in today's banking regulatory briefing?"
Claude queries:
Tool: get_daily_briefing
Date: todayYou receive:
Executive summary of key developments
Document count and high-priority items
Agency-by-agency breakdown
Ask Claude:
"Get me today's regulatory podcast"
Claude queries:
Tool: get_daily_podcast
Date: todayYou receive:
Audio URL for the daily briefing podcast
Generated by AI from the day's regulatory developments
Ask Claude:
"Draft a LinkedIn post about today's CFPB enforcement actions"
Claude queries:
Tool: get_linkedin_post
Date: todayYou receive:
Pre-formatted LinkedIn post with hashtags
Key stats and highlights
Ready to copy and share
"What was in the regulatory briefing on February 20, 2024?"Claude will pass date: "2024-02-20" to the tool.
Set environment variable to use a different API:
export BANKREGPULSE_API_URL=https://your-custom-api.comCause: Briefing hasn't been generated yet (runs at 6 AM EST daily)
Solution: Query yesterday's briefing or wait until morning
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
Cause: MCP server not properly installed or outdated
Solution:
npm cache clean --force
npx bankregpulse-mcp-server@latest# 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 startnpx @modelcontextprotocol/inspector npx bankregpulse-mcp-serverOpens a web UI to test tool calls.
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)
āāāāāāāāāāāāāāāāāāāThe MCP server calls these public API endpoints:
GET /api/mcp/briefing?date=YYYY-MM-DD - Daily briefing
GET /api/mcp/podcast?date=YYYY-MM-DD - Podcast URL
GET /api/mcp/linkedin-post?date=YYYY-MM-DD - LinkedIn post
No authentication required for basic usage.
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
Website: https://bankregpulse.com
Documentation: https://docs.bankregpulse.com
Issues: https://github.com/RRGU26/bankregpulse-mcp-server/issues
Email: admin@bankregpulse.com
Contributions welcome! Please:
Fork the repo
Create a feature branch
Submit a pull request
MIT License - see LICENSE for details.
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
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
Get the latest daily banking regulatory intelligence briefing with summaries and key developments from OCC, FDIC, CFPB, Federal Reserve, and all 50 state banking departments.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Optional: Specific date (YYYY-MM-DD). Defaults to today. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what the tool retrieves (briefing with summaries and key developments) but lacks critical behavioral details such as whether this is a read-only operation, if it requires authentication, rate limits, data freshness, or error handling. The description is functional but misses key operational context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that efficiently conveys the tool's purpose and scope without unnecessary words. It front-loads the key action ('Get the latest daily banking regulatory intelligence briefing') and follows with specific details. While concise, it could be slightly improved by breaking into two sentences for readability, but overall it earns its place with zero waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (retrieving structured regulatory data), lack of annotations, and no output schema, the description is minimally complete. It specifies content sources and type but omits details on output format, data structure, or error conditions. The description provides enough to understand the tool's intent but leaves gaps in practical usage context that the agent must infer or discover through trial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the single parameter 'date' well-documented in the schema. The description does not add any parameter-specific information beyond what the schema provides, such as date format examples or default behavior details. However, with high schema coverage and only one optional parameter, the baseline score of 3 is appropriate as the schema adequately handles parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Get') and resource ('daily banking regulatory intelligence briefing'), and distinguishes it from sibling tools by specifying the content type (briefing vs. podcast or LinkedIn post). It explicitly lists the sources covered (OCC, FDIC, CFPB, Federal Reserve, all 50 state banking departments), making the scope unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context by specifying the content type and sources, but does not explicitly state when to use this tool versus alternatives like get_daily_podcast or get_linkedin_post. It provides no guidance on prerequisites, exclusions, or comparative scenarios, leaving the agent to infer usage based on content differences alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the latest daily regulatory podcast audio URL. Listen to an AI-generated summary of the day's regulatory developments.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Optional: Specific date (YYYY-MM-DD). Defaults to today. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions retrieving a 'URL' and an 'AI-generated summary,' but doesn't disclose critical traits like whether this is a read-only operation, if it requires authentication, rate limits, error handling, or what format the output takes. For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, with two sentences that directly state the tool's function. There's no unnecessary information, and each sentence contributes to understanding the purpose. However, it could be slightly more structured by separating the URL retrieval and summary aspects more clearly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of retrieving media content with no annotations and no output schema, the description is incomplete. It doesn't explain what the output looks like (e.g., URL format, summary text), error cases, or behavioral details. For a tool that likely involves network calls and content delivery, more context is needed to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with one optional parameter 'date' clearly documented. The description doesn't add any parameter-specific semantics beyond what the schema provides (e.g., it doesn't explain date format constraints or default behavior further). With high schema coverage, the baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get the latest daily regulatory podcast audio URL' and 'Listen to an AI-generated summary of the day's regulatory developments.' It specifies the verb ('Get'), resource ('podcast audio URL'), and content type ('regulatory podcast'). However, it doesn't explicitly distinguish this from sibling tools like 'get_daily_briefing' or 'get_linkedin_post' beyond mentioning 'podcast' vs 'briefing'/'post'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools, prerequisites, or exclusions. The only implied context is for accessing daily regulatory content, but this is vague and doesn't help an agent choose between this and other tools like 'get_daily_briefing'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a pre-formatted LinkedIn post about today's regulatory developments, ready to copy and share on social media.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Optional: Specific date (YYYY-MM-DD). Defaults to today. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the output is 'pre-formatted' and 'ready to copy and share,' which adds some context about the return format. However, it doesn't describe critical behaviors like whether this is a read-only operation, if it requires authentication, rate limits, or error handling. For a tool with zero annotation coverage, this leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that efficiently conveys the tool's purpose and output format. It's front-loaded with the main action and includes no unnecessary details, making it appropriately sized and zero-waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one optional parameter, no output schema, no annotations), the description is minimally adequate. It explains what the tool does and the output format but lacks details on behavioral traits and usage context. Without annotations or output schema, it should provide more guidance on when to use it and what to expect, but it meets a basic threshold.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with one parameter ('date') fully documented in the schema. The description doesn't add any parameter-specific information beyond what's in the schema. According to the rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no param info in the description, which applies here.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get a pre-formatted LinkedIn post about today's regulatory developments, ready to copy and share on social media.' It specifies the verb ('Get'), resource ('LinkedIn post'), and content focus ('regulatory developments'), but doesn't explicitly differentiate from sibling tools like get_daily_briefing or get_daily_podcast. The purpose is clear but lacks sibling comparison.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides minimal usage guidance, stating it's for getting a LinkedIn post 'ready to copy and share on social media.' However, it doesn't specify when to use this tool versus alternatives like get_daily_briefing or get_daily_podcast, nor does it mention any prerequisites or exclusions. Usage context is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: get_daily_briefing provides text summaries, get_daily_podcast delivers audio content, and get_linkedin_post offers social media formatting. There is no overlap in functionality, making it easy for an agent to select the right tool based on the desired output format.
All tool names follow a consistent verb_noun pattern with 'get_' as the prefix, followed by a descriptive noun phrase (daily_briefing, daily_podcast, linkedin_post). This uniformity enhances readability and predictability across the tool set.
With only 3 tools, the server feels thin for the domain of banking regulatory intelligence, which might involve more operations like searching archives or filtering by agency. While the tools cover core outputs, the count is borderline low for comprehensive coverage.
The tool set is severely incomplete for a regulatory intelligence server, as it only provides retrieval of pre-formatted outputs without any CRUD operations, search capabilities, or filtering options. Agents cannot interact with historical data, customize queries, or manage content, leading to significant gaps in functionality.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
The Octagon MCP server provides specialized AI-powered financial research and analysis by integrating with the Octagon Market Intelligence API. It enables users to analyze public market data (SEC filings, earnings transcripts, financial metrics, and stock data for 8000+ companies), private market data (3M+ companies, 500k+ funding rounds, 2M+ M&A/IPO transactions), and conduct deep research including web scraping capabilities. The server also features autonomous research agents that search hundreds of sources and return fully cited reports in approximately one minute.
AI Briefing MCP ā Keep AI models current on industry developments
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs (Claude, GPT, Gemini, Cohere). Tools operate only on explicitly authorized customer connections, enabling agents to safely read and write against live third-party systems.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/RRGU26/bankregpulse-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
