Pulse MCP Server

An MCP server that exposes Moody's Pulse (Cortera) trade-credit data with grounded knowledge-base context. Every report section and metric is linked to a local knowledge base (pulse-kb/) so the server can explain what each value means, how it's computed, how it ties into the wider Moody's data estate, and which use cases it serves.

Tools

Tool	Purpose
search_business	Find a company → linkId
get_report	Full Deep Dive Report (entire JSON)
get_report_section	Pull specific sections by canonical name or natural-language alias
list_report_sections	List all sections with their plain-English meaning
explain_section	Explain a section (definition + KB source + cross-data-estate ties)
explain_metric	Explain a metric / field (CPR, DR, DBT, etc.)
list_metrics	Catalog of metrics in the registry
get_use_case_briefing	Surface Pulse signals + framework for a use case (surety, trade_credit, dno, portfolio, tprm, submission_triage, industry_macro)
read_kb	Read a KB doc by relative path for deep dives

Prerequisites

• Python 3.10+
• Pulse (Cortera) API credentials

Install

pip install -r requirements.txt

Configure

Copy the example env file and fill in your credentials:

cp .env.example .env

Then edit .env:

PULSE_USER=your-pulse-username
PULSE_PASSWORD=your-pulse-password

Register with an MCP client

Add to your MCP client config (e.g. .mcp.json or claude_desktop_config.json):

{
  "mcpServers": {
    "pulse": {
      "command": "python",
      "args": ["C:/path/to/pulse-mcp/server.py"]
    }
  }
}

Project layout

pulse-mcp/
├── server.py          # FastMCP server + tool definitions
├── kb_registry.py     # section aliases, metrics, use-case frameworks
├── pulse-kb/          # knowledge-base docs (definitions, cross-estate ties)
├── requirements.txt
├── .env.example       # template — copy to .env (gitignored)
└── Dockerfile