DRE MCP Server
Collects ad counts from the Google Ads Transparency Center through the collect_ad_library tool, providing evidence about a company's advertising activity.
Collects open job postings from Greenhouse job boards via the collect_jobs tool, helping identify hiring activity and roles.
Collects iOS App Store in-app purchase listings through the collect_appstore tool, exposing available in-app products and pricing.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
DRE — Domain Reverse Engineering
Analyze the business and domain side of a reference site, platform, or product: business model, positioning, marketing, ads, tech stack, financials, and pricing history — with evidence and explicit uncertainty on every claim. The business-side counterpart to REA, which covers the technical side.
Status: pre-release. 11 MCP tools built and tested; AC-008 (independent accuracy benchmark) is still pending real user labeling. See
docs/adr.yamlfor the design decisions behind each feature and.harness/ouroboros/for the spec/eval history.
Install
npx dre-agents setupRegisters the DRE MCP server with Claude Code. Open a new session and the tools below appear automatically.
Related MCP server: Brand Intelligence MCP
Tools
Tool | What it does | Blocking resistance |
| pricing + terms + tech stack + ads in one call, from just a domain | — |
| plan/price text; auto-discovers the pricing page from a home URL | archive.org fallback on bot blocks |
| billing/refund passages, following same- and cross-origin links | medium |
| iOS/Play in-app purchase listings | high |
| frameworks, CMS, payment/analytics scripts from headers+HTML | very high (can't be blocked without breaking the page) |
| Google Ads Transparency Center ad counts | high (Google only — Meta is excluded, see below) |
| SEC EDGAR revenue/net income (US public companies) | high (free, no key) |
| DART (Korean FSS) revenue/net income | high (free, needs your own API key) |
| pricing over time via archive.org snapshots | — (REA has no equivalent) |
| open postings via Greenhouse/Lever | very high |
| validates and saves a claim-based report | — |
Principles
Only directly observed facts are labeled
observed; the rest isinferredorestimated.Estimates are ranges with stated assumptions, never single numbers.
Works with public sources and your own LLM key (BYOK). No paid data required.
DRE never bypasses robots.txt, bot/CAPTCHA detection, or login walls — see
docs/adr.yamlADR-004/005 for why (and why Meta's ad library is deliberately not covered: facebook.com's robots.txt specifically disallowsClaudeBot).DRE never calls an LLM or search engine itself. When a collector is blocked, the calling agent may supplement with its own research, but must mark it
source: "agent"andinferred/estimated— neverobserved(ADR-003).
Claim schema
Each claim has type (observed | inferred | estimated), confidence, evidence[] (each with
an optional source: "dre" | "agent"), assumptions[]. Revenue-model labels are a fixed taxonomy
with precise definitions — see packages/core/src/labels.ts and
packages/core/src/schema.ts.
Develop
npm install
npm test
node packages/cli/dist/index.js eval reports benchmarks/gold # AC-008 accuracy checkTo rebuild the publishable dre-agents bundle after changing any package:
cd packages/dre-agents && npm run buildOptional environment variables
DRE_DART_API_KEY— free key from opendart.fss.or.kr, enablescollect_financials_krDRE_SEC_USER_AGENT— your own "org contact@email" string for SEC EDGAR (recommended over the default)DRE_CHROME_PATH— Chrome/Chromium path, for JS-rendered pages (collect_pricingwithjs: true)DRE_ALLOW_PRIVATE_NETWORK=1— local dev/testing only; disables the SSRF guard
Roadmap
Done: pricing/terms/appstore/techstack/ad-library/financials(US+KR)/price-history/jobs collectors, analyze_company orchestrator, npm packaging prep
Next: traffic/CPC/CTR/CVR/ROAS scenario estimates (user-supplied external API keys, stated assumptions — see non_goals in
.harness/ouroboros/seeds/seed-v1.yamlfor what DRE deliberately does not do)
This server cannot be deployed
Maintenance
Related MCP Connectors
Company profiles, site audits and page-to-JSON extraction for AI agents.
Paid business, people, company, lead, and web intelligence for autonomous AI agents.
Website and company intel for AI agents: WHOIS/DNS/TLS, tech stack, PageSpeed, hiring history.
Company intelligence for AI agents: a five-layer domain dossier in one sniff_domain call.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceProvides AI agents with tools to detect Shopify apps, WordPress plugins, DNS/email/SaaS footprint, and estimate SaaS spend for competitive intelligence and vendor research.-
- AlicenseNot gradedqualityFmaintenanceProvides domain and brand intelligence for AI agents, including company enrichment, tech stack detection, and brand research from free public sources with an on-demand cache.MIT
- AlicenseAqualityDmaintenanceEnables AI agents to research companies and find contacts with structured data from multiple free sources, including company info, tech stack, and email addresses.3MIT
- AlicenseNot gradedqualityFmaintenanceProvides real-time website audits, lead scoring, tech-stack detection, and local-business search for AI agents doing sales outreach and competitor research.MIT