Skip to main content
Glama
Gallan-Holdings

Archway MCP Server

Archway Advisory Group — MCP Server

Three governance tools exposed via the Model Context Protocol, deployed on Cloudflare Workers.

MCP Endpoint: https://archway-mcp.<YOUR_SUBDOMAIN>.workers.dev/mcp

Tools

archway-governance-diagnostic

Structured governance posture assessment. Scores maturity across board oversight, committee structure, documentation, and control environment — benchmarked against NYSE 303A, NASDAQ 5600, ISS 2026, Glass Lewis 2026, and NACD standards. Returns tier classification, domain findings, and engagement recommendations with fixed-fee pricing.

archway-engagement-scoping

Converts a diagnostic result (or direct request) into a scoped, priced engagement. Produces bounded scope, deliverable list, timeline, and fixed-fee pricing across all Archway service lines.

archway-rd-risk-screener

R&D tax credit documentation exposure screening. Assesses Four-Part Test substantiation, contemporaneous documentation practices, and IRS examination readiness. Includes regulatory boundary disclaimer.

Related MCP server: Scorecard MCP Server

Deployment

Prerequisites

  • Node.js 20+ and npm

  • Cloudflare account (free tier is sufficient)

  • Wrangler CLI (npm install -g wrangler)

Steps

# 1. Clone or copy this directory
cd archway-mcp

# 2. Install dependencies
npm install

# 3. Authenticate with Cloudflare
wrangler login

# 4. Test locally
wrangler dev

# 5. Deploy to production
wrangler deploy

After deploy, your MCP endpoint is live at:

https://archway-mcp.<YOUR_SUBDOMAIN>.workers.dev/mcp

Local Testing with Claude Desktop

Add to your Claude Desktop MCP config (claude_desktop_config.json):

{
  "mcpServers": {
    "archway": {
      "url": "http://localhost:8787/mcp"
    }
  }
}

For production:

{
  "mcpServers": {
    "archway": {
      "url": "https://archway-mcp.<YOUR_SUBDOMAIN>.workers.dev/mcp"
    }
  }
}

Architecture

  • Runtime: Cloudflare Workers (Durable Objects for MCP session state)

  • Logic: Fully deterministic — no AI API calls. Scoring algorithms, pricing rules, and risk assessment run as pure functions.

  • Cost: Effectively zero at expected volume (Workers free tier: 100K requests/day)

  • Transport: Streamable HTTP (MCP standard), handled by McpAgent SDK

File Structure

archway-mcp/
├── src/
│   ├── index.ts              # MCP server — tool definitions + McpAgent
│   ├── env.d.ts              # Cloudflare Worker env types
│   └── logic/
│       ├── scoring.ts        # Governance diagnostic scoring engine
│       ├── pricing.ts        # Engagement scoping + pricing rules
│       └── risk-assessment.ts # R&D documentation risk screener
├── wrangler.toml             # Cloudflare Workers config
├── package.json
├── tsconfig.json
└── README.md

Regulatory Boundary

The R&D Risk Screener provides qualitative assessment only. It does not provide tax advice, credit calculations, return preparation, or any service requiring CPA licensure. Every R&D tool output includes the full regulatory disclaimer.

Firm Attribution

Every tool output includes:

  • Firm name and website

  • Direct booking URL

  • Contact email

  • Link to the full web-based experience


Archway Advisory Group LLC | archwayadvisorygroup.com

F
license - not found
-
quality - not tested
C
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

View all related MCP servers

Related MCP Connectors

  • MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.

  • Crypto transaction firewall and risk tools for MCP agents.

  • Remote MCP for tool license checks, vendor policy review, alternatives, and license receipts.

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/Gallan-Holdings/archway-mcp'

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