Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@CoverageUnlocked MCP Server What's the win probability for CPT 90837 with UnitedHealthcare in California?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Insurance denial appeal intelligence powered by 20 years of insider knowledge.
Get win probabilities, appeal strategies, payer behavioral intelligence, and regulatory leverage for any CPT code — directly inside your AI assistant.
"What are my chances of winning an insurance denial appeal?"
"How do I appeal a denied claim for [procedure] with [payer]?"
"What's the denial rate for [CPT code] with [insurance company]?"
"What should I include in my appeal letter?"
"What are the appeal deadlines in my state?"
Related MCP server: mymedi-ai-mcp-server
480+ curated CPT codes with deep insider commentary, payer-specific rates, and regulatory leverage — backed by a 17,000+ total CPT/HCPCS coverage layer across 9 procedure categories (surgical, E&M, imaging, infusion/chemo, rehab, mental health, diagnostic, DME, lab/pathology)
7 major payers with behavioral profiles (UnitedHealthcare, Anthem, Aetna, Cigna, Humana, BCBS, TRICARE)
15 state regulatory profiles with appeal deadlines, prompt payment laws, and parity enforcement
Category-level fallback for any CPT code not in the detailed database
Tool | Tier | What It Does |
| Free | Win probability + top denial reason + insider tip for any CPT code |
| Free | Pre-submission risk assessment — check before you submit a claim |
| Pro | Full appeal strategy with all denial reasons, counter-arguments, regulatory citations |
| Pro | Payer behavioral profiles — known tactics and how to counter them |
| Pro | State-specific appeal deadlines, prompt payment laws, external review options |
npx coverageunlocked-mcpAdd to your claude_desktop_config.json:
{
"mcpServers": {
"coverageunlocked": {
"command": "npx",
"args": ["-y", "coverageunlocked-mcp"]
}
}
}Add to your MCP settings:
{
"coverageunlocked": {
"command": "npx",
"args": ["-y", "coverageunlocked-mcp"]
}
}Free Tier — No API key required
10 queries per day
Win probability and top denial reason
One insider tip per query
Basic state regulatory deadlines
Pro ($19/month) — Sign up
100 queries per day
Full appeal strategies with all denial reasons
Payer behavioral intelligence and counter-strategies
Complete regulatory leverage with specific citations
Documentation checklists
All insider tips from 20 years inside the industry
Enterprise — Contact us
Unlimited queries
Batch processing
Custom payer profiles
Integration support
API access to the full 480+ curated / 17,000+ total CPT/HCPCS database
Ask your AI assistant:
"What are the chances of winning an appeal for CPT 90837 (psychotherapy, 60 min) denied by UnitedHealthcare in California?"
The MCP server returns:
Win Probability: 66%
Denial Rate: 28% (highest of all Tier 1 codes — mental health is the most denied category)
Top Denial Reason: Concurrent review lapse (35% of denials, 70% appeal success)
Insider Tip: Visit limit denials have 72% overturn rate because of the Mental Health Parity Act — ALWAYS appeal these
CA Regulatory Leverage: DMHC Independent Medical Review (strongest external review in nation), SB 855 mental health parity
Built by Ned Lutz after 20 years inside the health insurance industry. CoverageUnlocked exists to close the knowledge gap between insurance companies and the people fighting denials.
Website: coverageunlocked.com
Consulting: Book a session ($497)
Newsletter: Denial Dispatch
MIT
Analyze an insurance denial and get win probability, top denial reasons, and appeal guidance. Covers 489+ CPT codes across 9 procedure categories with data from 20 years of industry experience. Use this when someone asks about insurance denials, claim denials, appeal chances, or how to fight a denied claim.
| Name | Required | Description | Default |
|---|---|---|---|
| payer | No | Insurance company name (e.g., "UnitedHealthcare", "Anthem", "Aetna", "Cigna", "Humana", "BCBS") | |
| state | No | Two-letter state code (e.g., "CA", "TX", "NY") for state-specific regulatory leverage | |
| api_key | No | CoverageUnlocked API key for Pro access. Free tier: 10 queries/day with basic results. Get Pro at https://app.coverageunlocked.com/mcp | |
| cpt_code | Yes | The CPT or HCPCS code that was denied (e.g., "99214", "70553", "E0601") | |
| denial_reason | No | The reason given for the denial, if available |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the tool's analytical nature and broad coverage, but omits behavioral details such as API key requirements, rate limits (free tier vs Pro), or authentication needs. It adequately conveys non-destructive intent but falls short on full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, each valuable. It front-loads the main action and includes relevant scope details without unnecessary words or tangents. Perfectly concise for the information provided.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 5 parameters (1 required), no output schema, and no annotations, the description could be more complete. It explains the tool's purpose and coverage but does not describe the return format (e.g., win probability structure) or clarify how api_key relates to access tiers. Missing some context needed for full understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with detailed descriptions for all 5 parameters. The tool description adds high-level context but does not enhance parameter-specific meaning beyond the schema. Baseline score of 3 is appropriate as the schema already carries the semantic load.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Analyze an insurance denial and get win probability, top denial reasons, and appeal guidance.' It specifies the verb, resource, and outputs, and adds scope details (489+ CPT codes, 9 categories, 20 years data) making it specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use: 'Use this when someone asks about insurance denials, claim denials, appeal chances, or how to fight a denied claim.' It provides good context for invocation, though it lacks explicit when-not-to-use guidance or alternatives due to no sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.3analyze_denialScored across 1 tool
With only one tool, there is no possibility of confusion or overlap. Agents will always select the correct tool for the single purpose of analyzing insurance denials.
The single tool name 'analyze_denial' follows a clear verb_noun pattern, which is consistent by default. There are no other tool names to create inconsistency.
A single tool is minimal, but for a highly specialized server focused solely on denial analysis, it is borderline appropriate. The server could benefit from additional tools for related tasks like retrieving denial history or tracking appeals.
The tool provides comprehensive coverage for its stated purpose: analyzing denials, calculating win probability, identifying top denial reasons, and offering appeal guidance. Minor gaps might include the inability to save or retrieve previous analyses, but the core analysis capability is complete.
Insurer denial rates, appeal outcomes by treatment and condition, and appeal rights lookups.
Deterministic CMS NCCI/MUE claim scrubbing and CARC/RARC denial explanations, cited to source.
Hosted MCP for denial, prior auth, reimbursement, workflow validation, batch scoring, and feedback.
Claims-grounded provider, market, and KOL intelligence for healthcare AI agents via Alpha Sophia
