Skip to main content
Glama
vbzvibin

Northern Trust MCP Layer

by vbzvibin

Northern Trust MCP Layer - Prototype

This repository implements a "Server of Servers" architecture using the Model Context Protocol (MCP). It features a central Orchestrator that aggregates domain-specific data capabilities (like Performance) into a single, governed interface.

Repository Structure

  • orchestrator/: The main gateway server. Handles routing and tool aggregation.

  • domains/performance/: Sample domain implementation providing fund performance tools.

  • package.json: Root configuration for managing the workspace.

Related MCP server: Quant Framework MCP Server

Prerequisites

  • Node.js (v18+)

  • NPM

Setup Instructions

  1. Install Dependencies Run from the root directory:

    npm install
  2. Build the Projects

    npm run build:all
  3. Run for Testing

    Option A: Test individual domains

    cd domains/performance
    npm run dev

    Option B: Test the Orchestrator (Server of Servers)

    cd orchestrator
    npm run dev

Key Features

  • Namespace Routing: Tools from the Performance domain are automatically prefixed with perf_ by the orchestrator.

  • Dynamic Discovery: The orchestrator fetches the tool manifest from domain servers on startup.

  • Type Safety: Built with TypeScript and Zod for robust schema validation.

  • Standard Protocol: Compatible with any MCP-compliant client (e.g., Gemini, Claude Desktop).

Available Tools (via Orchestrator)

  • perf_get_fund_returns: Returns YTD and 1-year performance.

  • perf_benchmark_comparison: Compares fund vs benchmark.

  • perf_sharpe_ratio: Returns risk-adjusted performance metric.

F
license - not found
-
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    -
    quality
    D
    maintenance
    A central hub that aggregates multiple MCP resource servers into a single unified interface, enabling users to access tools and capabilities from multiple backend servers through one connection point.
    45
    202
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    An extensible framework that exposes quantitative research functions and financial data connectors, such as FRED, via an MCP server. It enables users to perform complex financial modelling, data retrieval, and autonomous research loops with built-in guardrails and pluggable components.
    6
    4
    MIT
  • A
    license
    -
    quality
    D
    maintenance
    An MCP server that provides AI agents with structured, real-time data on cryptocurrency investment funds, enabling deeper due diligence and portfolio intelligence.
    3
    MIT

View all related MCP servers

Related MCP Connectors

  • Savvly MCP: query fund data, model projections, and compare against alternative retirement products.

  • MCP server connecting AI agents to non-custodial staking data across 130+ networks.

  • MCP gateway federating 21 biomedical MCP servers behind one endpoint: gnomAD, ClinVar, HPO, VEP.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/vbzvibin/MCP_V3'

If you have feedback or need assistance with the MCP directory API, please join our Discord server