Domain Expertise MCP server
Inject deep domain knowledge into any AI agent
0 stars57 downloads/wk
Reviews
Write oneNobody has reviewed Domain Expertise yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Domain Expertise tools (8)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
assess_complexityAssess the complexity of a professional task and recommend whether it needs a generalist or specialist agent. Returns complexity score, required expertise level, and risk factors.
get_decision_treeGet a structured decision tree for a specific professional scenario. Returns step-by-step decision logic that an expert would follow.
get_domain_expertiseGet structured professional expertise for a specific domain. Returns decision frameworks, key principles, common pitfalls, and expert-level reasoning patterns that transform a generalist AI agent into a domain specialist.
get_professional_workflowGet the standard professional workflow for a task. Returns the steps an experienced professional would follow, including quality checkpoints and common shortcuts that cause problems.
get_regulatory_contextGet regulatory context for a domain in a specific jurisdiction. Returns applicable laws, regulatory bodies, compliance requirements, and recent changes.
get_terminologyGet professional terminology and definitions for a domain. Returns terms with definitions, usage context, and common misunderstandings.
health_checkReturns server health, uptime, version, and usage stats
list_available_domainsList all available professional domains with descriptions and coverage depth.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan14 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 156 days ago8/15
- Maintainer identityregistry namespace matches repository owner6/10
How Domain Expertise compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 78/100
- higher than 57% of 4,460 AI and agents servers
- Tools
- 8
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 57
- more than 47% of 1,538 AI and agents servers with a package
What its tools let an agent do: 8 read
Install Domain Expertise in Claude Code, Cursor or VS Code
Runs npx -y domain-expertise-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add domain-expertise -- npx -y domain-expertise-mcp
What the publisher says
From the Domain Expertise repository's README, as published. We do not edit it. Read it on GitHub
domain-expertise-mcp
Inject structured professional domain expertise into AI agents. Accounting, Islamic finance, cybersecurity, real estate, HR, and 15+ more domains — all via MCP.
Why This Exists
AI agents are generalists. They know a little about everything but lack the structured reasoning patterns that professionals develop over decades. This MCP server bridges that gap — giving any agent access to decision frameworks, professional workflows, terminology, and regulatory context across 24 professional domains.
No other MCP server provides structured domain expertise injection.
What It Does
Core Tools
- getdomainexpertise — Get structured professional knowledge at three depth levels (overview, practitioner, expert). Includes decision frameworks, key principles, common pitfalls, and expert reasoning patterns.
- listavailabledomains — See all 24 available professional domains with coverage details.
- getdecisiontree — Get step-by-step decision logic for specific professional scenarios (e.g., "Is this transaction Sharia-compliant?", "Should I register for VAT?").
- get_terminology — Professional terms with definitions in English and Arabic. Includes usage context and common misunderstandings.
- getregulatorycontext — Regulatory bodies, applicable laws, compliance requirements, and recent changes by jurisdiction.
- assess_complexity — Score a task's complexity and get recommendations for agent capability level needed.
- getprofessionalworkflow — Standard professional workflows with quality checkpoints and common shortcuts that cause problems.
Supported Domains (24)
Finance: Accounting, Tax, Audit, Islamic Finance, Conventional Banking, Investment, Insurance (Underwriting & Claims)
Legal: Corporate Law, Contract Law, Employment Law
Healthcare: Clinical, Administration, Pharmaceutical
Real Estate: Commercial, Residential
Technology: Cybersecurity, Data Privacy
Operations: Supply Chain, Logistics, Construction, Oil & Gas
People: Education, HR Management
Regional Coverage
Global, GCC, MENA, EU, US, UK, Asia — with GCC-specific knowledge for Saudi Arabia, UAE, Kuwait, Bahrain, Oman, and Qatar.
Installation
Claude Desktop / Claude Code
{
"mcpServers": {
"domain-expertise": {
"command": "npx",
"args": ["domain-expertise-mcp"]
}
}
}Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"domain-expertise": {
"command": "npx",
"args": ["domain-expertise-mcp"]
}
}
}Use Cases
Building a financial agent? Inject accounting expertise so it handles revenue recognition, lease classification, and IFRS compliance like a CPA.
Islamic finance automation? Get Sharia compliance decision trees, Murabaha/Sukuk structures, and AAOIFI standards for your agent.
Cybersecurity tool? Add incident response workflows, NIST CSF alignment, and NCA/NESA compliance knowledge.
HR automation for GCC? Nitaqat/Saudization calculations, Emiratisation requirements, and end-of-service computations.
Example
Agent: "I need to determine if a client's Islamic finance product is Sharia-compliant"
→ get_decision_tree(domain: "islamic_finance", scenario: "sharia compliance")
Returns a structured decision tree:
1. Does the transaction involve riba (interest)? → If yes: NOT COMPLIANT
2. Is there excessive gharar (uncertainty)? → If yes: NOT COMPLIANT
3. Is the underlying activity halal? → If no: NOT COMPLIANT
4. Is risk genuinely shared? → If no: REVIEW NEEDED
5. If all pass → LIKELY COMPLIANT. Submit to Sharia Board.Depth Levels
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Domain Expertise: common questions
- Is Domain Expertise MCP server safe?
- Mostly: it is graded B (78/100). Read the Domain Expertise safety report
- How do I install Domain Expertise?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Domain Expertise need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Domain Expertise maintained?
- The last commit was 194 days ago (2026-04-24). The latest release is v0.1.3.
- What can I use instead of Domain Expertise?
- Servers from other publishers that do the same job: Basic Memory MCP server, IWE (iwe.md) MCP server and Total Agent Memory MCP server.
- How does Domain Expertise compare with other AI and agents MCP servers?
- safety score 78/100 (higher than 57% of 4,460 AI and agents servers); tools 8 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Domain Expertise
Same job from other publishers: the closest match first, then the best rated.
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- IWE (iwe.md)Markdown knowledge base as agent memory. Runs against the notes directory it is started in.not reviewedEstablishedA
- Total Agent MemoryPersistent local memory for coding agents: temporal knowledge graph, procedural and episodic recallnot reviewedEstablishedA