mymedi-ai-mcp-server

Medical code cross-reference (ICD-10 / CPT / HCPCS)

code_crossref

Read-only

Find related ICD-10-CM, CPT, and HCPCS Level II codes for a medical code, including curated DME links, CMS-cited cross-references, and relevance-scored matches.

Instructions

Related codes for an ICD-10-CM, CPT or HCPCS Level II code, across the three code systems. linkedCodes are curated: the DME code family (base item, accessories and supplies) and links across code systems that cite their CMS source — obstructive sleep apnea (G47.33) with the PAP devices CMS LCD L33718 covers and the sleep tests NCD 240.4.1 covers. crossReferences are other active codes whose descriptions best match this one, grouped by code system (up to 5 each) with a relevanceScore (0-1); weaker matches are left out, so a group can be empty, and a code with no related codes at all is refunded. Source: the MyMedi-AI code database (ICD-10-CM, CPT and HCPCS Level II code sets).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "code": "<code>"
    },
    "name": "code_crossref"
  }
}

Input Schema

Name	Required	Description	Default
`code`	Yes	Medical code to cross-reference (e.g., "M79.3", "99213", "E0601")

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.7.9Nov 2, 2026
- addedInput schema / properties / code / maxLength
```
Added value: +500
```
Addedv1.2.1Apr 22, 2026

TDQS

A3.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (which already declare readOnly/no-destructive/openWorld=false), the description discloses genuinely non-obvious behavior: results are curated, capped at 5 per system with a 0-1 relevanceScore, weak matches are dropped so groups can be empty, and a call with no related codes is refunded. That refund/billing detail is especially valuable and explains the idempotentHint=false annotation. It does not explain ordering or whether the code type is auto-detected.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is one dense run-on paragraph mixing purpose, output semantics, and provenance; the two distinct result groups (linkedCodes, crossReferences) would be much clearer as separate structured lines. The closing 'Source: the MyMedi-AI code database (ICD-10-CM, CPT and HCPCS Level II code sets)' partly repeats code systems already stated up front.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of explaining returns, and it does: both result groups, the per-system cap, relevanceScore range, and the empty/refund case. What remains thin is the shape of the linkedCodes entries (DME families, cited LCD/NCD sources) and how code system is inferred from the input.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter, and schema coverage is 100% with concrete examples ('M79.3', '99213', 'E0601') already in the schema. The description adds no syntax or normalization guidance beyond the schema, so the 3 baseline for high coverage applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific resource and scope: 'Related codes for an ICD-10-CM, CPT or HCPCS Level II code, across the three code systems,' which tells an agent exactly what it returns and distinguishes it from single-code lookups by its cross-system, related-code scope. It never names a sibling (code_lookup, code_suggest, code_lookup_basic) to sharpen the boundary, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the resource name; the bulk of the text describes return structure (linkedCodes vs crossReferences) rather than when to choose this over code_lookup or code_suggest. There are no explicit exclusions or preconditions (e.g., whether the code must already be valid).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.