MoleCare MCP Server
OfficialMoleCare MCP Server provides educational dermatology knowledge and optional MoleCare mole-tracking tools; it is explicitly non-diagnostic and returns mock product data until configured.
Search a bundled skin-health knowledge base for educational content such as ABCDE criteria and prevention.
Look up and search SNOMED CT concepts, map SNOMED codes to ICD-10, and retrieve condition progression, risk factors, and malignant-condition lists.
Describe supplied ABCDE lesion features and named risk factors without calculating a risk score, naming a condition, or recommending urgency.
With a MoleCare-compatible API configured, list a user's moles, view mole analysis and change history, list risk factors, and compare two mole photos.
Use bundled MCP resources and educational prompts for ABCDE walkthroughs, dermatology appointment prep, and SNOMED code explanations.
Provides Kubernetes operations tooling for checking cluster status through the get_kubernetes_status tool.
Provides MLflow tracking tools to list experiments and runs, inspect registered models and model versions, compare runs, and review training runs.
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., "@MoleCare MCP Server Explain the ABCDE criteria for melanoma"
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.
MoleCare MCP Server
Model Context Protocol (MCP) server that gives Claude and other MCP clients access to:
Dermatology knowledge — ABCDE education, SNOMED CT / ICD-10 helpers, risk-factor prompts
Optional MoleCare API tools — moles, trends, analysis (your backend + API key)
Optional MLOps / ops tools — shipped as a separate binary,
molecare-ops-mcp(mock-first)
Not a medical device. Outputs are educational and operational aids only. Do not use for diagnosis or treatment decisions.
Product site: molecare.co.uk · App: iOS · Android
Why this exists
MoleCare helps people track moles over time and prepare for clinician visits. This MCP server lets developers and operators:
Query educational skin-health knowledge from Claude Desktop / Cursor
Prototype assistant flows against a MoleCare-compatible API
Explore MLOps tooling with safe mock data when no credentials are set
Related MCP server: THC Open Mindfulness MCP
Quick start
No credentials, no database, no cloud account. Add this to your MCP client config and restart it:
{
"mcpServers": {
"molecare": {
"command": "npx",
"args": ["-y", "molecare-mcp"]
}
}
}For Claude Desktop on macOS that file is
~/Library/Application Support/Claude/claude_desktop_config.json.
The dermatology knowledge tools work immediately — they read from a knowledge base bundled in the package. Everything that talks to a backend returns clearly-labelled mock data until you configure it, so you can explore the whole tool surface before deciding whether you want any of it.
To try it without a client at all:
npx -y molecare-mcpIt starts and waits on stdio. No output means it is working.
Claude Code plugin
This repository is also a Claude Code plugin: the same server, plus a skill that tells Claude when to use it and to never diagnose.
claude plugin marketplace add MoleCare/molecare-mcp
claude plugin install molecare@molecareThen ask things like "what does the E in ABCDE mean?" or "help me prepare for a
dermatology appointment". The plugin runs npx -y molecare-mcp with no keys, so
the account tools return example data marked "dataSource": "mock".
Connecting a real backend
Only needed if you are running a MoleCare-compatible API:
{
"mcpServers": {
"molecare": {
"command": "npx",
"args": ["-y", "molecare-mcp"],
"env": {
"MOLECARE_API_URL": "http://localhost:8080/api",
"MOLECARE_API_KEY": "your-local-api-key"
}
}
}
}Use localhost (or your own deployment). Do not paste production keys into config files that sync to cloud drives.
Environment variables
Every setting is optional. The public server falls back to mock product data
without API credentials, and its knowledge tools continue to work offline. For
the operations server, use NODE_ENV=development (the .env.example default)
to keep integrations in mock mode.
Shared by both binaries
Variable | Purpose | Example |
| MoleCare-compatible HTTP API |
|
| API bearer/key; required with a real MoleCare API |
|
| Logging verbosity: |
|
| Preferred port for the optional HTTP |
|
| Fallback health port, useful for container platforms |
|
| Optional local sidecar that checks tool results before egress |
|
| Privacy-gate request timeout in milliseconds |
|
Public server (molecare-mcp)
The public server has no additional settings. Its dermatology knowledge works without configuration; the shared MoleCare API variables enable its optional mole and profile tools.
Operations server (molecare-ops-mcp)
The operations binary also accepts the shared settings above. These additional variables only configure its infrastructure, monitoring, and CI/CD tools:
Variable | Purpose | Example |
|
|
|
| MLflow tracking server |
|
| Optional MLflow API key | — |
| Model-serving health endpoint |
|
| Feast feature server |
|
| Feast project name |
|
| MoleCare web application |
|
| MoleCare mobile API |
|
| MoleCare admin API |
|
| Backend health endpoint |
|
| Application metrics API; leaving it empty keeps app monitoring mocked | — |
| Repository owner used by CI/CD tools |
|
| Repository name used by CI/CD tools |
|
| GitHub token used by CI/CD tools | — |
| AWS region used by EC2 and CloudWatch tools |
|
| Named AWS credential profile | — |
| AWS SDK credential-chain access key; prefer a role or profile | — |
| Comma-separated EC2 instance IDs | — |
| PostgreSQL host used by database health checks |
|
| PostgreSQL port |
|
| PostgreSQL database name |
|
| Redis host and port |
|
| Elasticsearch host and port |
|
See .env.example for the copyable source-of-truth list.
Tools
Dermatology knowledge — no setup required
These are the reason most people install this. They answer from a bundled knowledge base and need no API, no key, and no network.
Tool | Description |
| Search the dermatology knowledge base |
| Look up a SNOMED CT concept |
| Search conditions by name or description |
| Map a SNOMED CT code to ICD-10 |
| ABCDE-style feature descriptors for a lesion |
| Named educational risk factors (no score) |
| Known risk factors for a condition |
| Typical progression stages for a condition |
| Malignant skin conditions with codes |
Resources: molecare://knowledge/* — ABCDE criteria, Fitzpatrick skin types,
prevention, when to see a dermatologist. molecare://ontology/* — SNOMED CT and
ICD-10 reference lists, the full snomed-icd10-map mapping table, and risk
factors, all with provenance metadata.
Educational prompts
The server also exposes three reusable MCP prompts: walk_through_abcde,
prepare_dermatology_appointment, and explain_snomed_code. They help a client
organize observations or explain terminology without diagnosing a condition,
assigning urgency, or producing a risk score. Every rendered prompt includes
the non-diagnostic educational disclaimer; the terminology prompt requires a
SNOMED CT code argument.
What the terminology actually covers
Bundled | |
SNOMED CT concepts | 7 — melanoma, melanoma in situ, BCC, SCC, actinic keratosis, dysplastic naevus, melanocytic naevus |
WHO ICD-10 categories | 25 — malignant, in situ, benign, precancerous, inflammatory and pigmentation, across Chapters II and XII |
SNOMED → ICD-10 mappings | 9 rows covering all 7 concepts — some concepts have more than one plausible target |
Every SNOMED concept the server advertises resolves through
lookup_medical_concept and maps through map_snomed_to_icd10. Ask for a code
outside the subset and the response carries a coverage block listing what is
bundled, rather than an empty result. Browse the whole table with the
molecare://ontology/snomed-icd10-map resource.
ICD-10 coverage is deliberately broader than SNOMED coverage. Expanding the bundled SNOMED concept set is on hold pending a redistribution question with SNOMED International: free use in a member country is not the same as free redistribution via npm to non-member territories (#49). WHO licenses ICD-10 more permissively at this level, so that side can grow in the meantime.
Terminology provenance
Bundled SNOMED CT / ICD-10 helpers are an educational subset, not a licensed
terminology distribution. Named sources live in
src/resources/terminology-provenance.ts
and are returned on map_snomed_to_icd10 and the ontology resources:
System | What this package reflects |
SNOMED CT | International Edition concept IDs / FSNs checked against the SNOMED International browser (last checked 2026-09-03). Plain-English search aliases are written for this package and are not SNOMED descriptions |
ICD-10 | WHO ICD-10 category-level codes (e.g. |
SNOMED → ICD-10 | Approximate category-level mappings — not certified one-to-one map rows. Each row carries a rationale |
The dataset itself lives in
src/resources/terminology-data.ts and is
the single source for both the src/api/ontology-client.ts mock paths and the
ontology resources. Educational prose without clinical codes lives in
src/resources/medical-kb.ts.
MoleCare product data — needs an API
Returns labelled mock data until MOLECARE_API_URL is set.
Tool | Description |
| List moles for a user id |
| Analysis payload for a mole |
| Change history for a mole |
| A user's risk profile |
| Compare two moles |
These exist because MoleCare operates this stack from an assistant. They are of little use outside that context, and all of them return mock data unless the matching backend is configured.
They are not part of the molecare-mcp tool list. Loading 39 infrastructure
tools that nobody outside MoleCare can use made it measurably harder for a model
to pick the right dermatology tool, so they live in their own server:
{
"mcpServers": {
"molecare-ops": {
"command": "npx",
"args": ["-y", "-p", "molecare-mcp", "molecare-ops-mcp"]
}
}
}Area | Tools |
Health |
|
MLflow |
|
Feature store |
|
CI/CD |
|
AWS |
|
Apps |
|
Database |
|
Kubernetes |
|
The AWS tools need @aws-sdk/client-ec2 and @aws-sdk/client-cloudwatch, which are
optional peer dependencies — they are not installed by default, because they add
33 MB that nobody wanting the dermatology tools should have to download. Install them
yourself if you want live AWS data:
npm i @aws-sdk/client-ec2 @aws-sdk/client-cloudwatchArchitecture
Claude / Cursor / MCP client
│ stdio (JSON-RPC)
▼
molecare-mcp molecare-ops-mcp
├─ medical KB (local) ├─ MLflow / Feast clients
├─ MoleCare API client ├─ AWS / CI / K8s clients
└─ ontology client └─ database / app clients
│ (14 tools) │ (39 tools, internal)
│ │
└───────────┬───────────────────┘
└─ optional HTTP GET /health (Docker / ECS)Docker
docker build -t molecare-mcp .
docker run --rm -p 3000:3000 molecare-mcp
curl http://localhost:3000/healthSecurity
Never commit
.envfiles or API keys — see SECURITY.md to report a vulnerabilityPrefer mock mode for demos and screenshots
Tools that accept
userIdcan return PHI only if you point them at a real backend with real auth — treat that as productionRate-limit and auth belong on your API, not only on the MCP process
Medical disclaimer
MoleCare MCP provides educational information and developer tooling. It does not diagnose melanoma or any disease. Always consult a qualified clinician for medical concerns.
Development
git clone https://github.com/MoleCare/molecare-mcp.git
cd molecare-mcp
npm install
npm run build
npm run dev # auto-reload
npm run inspect # browse tools in MCP InspectorContributions are welcome. Read CONTRIBUTING.md first — it covers the mock-first rule,
the clinical-safety boundary for anything touching medical content, and how to pick up a good first issue.
Please keep secrets out of examples and prefer localhost defaults.
Related
Environment variables:
.env.exampleis the authoritative list. CI compares it with the variables reachable from both server entrypoints and checks the public/operations grouping above.
MoleCare-ML — melanoma classification service and training notebooks
Where it is listed
npm, as
molecare-mcpGlama and MCP Servers Live, which index MCP servers
mcprush, a marketplace for MCP servers and agent skills: free, installed from the npm package, nothing hosted by mcprush
If you use it somewhere, or wrote about it, open an issue and it goes here.
Contributors
Thank you to everyone who has helped molecare-mcp.
The list is filled by Contributors from GitHub commits, bots omitted — never hand-maintained, because a stale list is worse than none. Contributor graph · good first issue
License
Apache-2.0 © Yauhen Bichel
Available Tools
14 toolsassess_risk_from_factorsARead-only
Describe named educational skin-health factors from a list of factor IDs. Does not calculate a risk score or recommend urgency.
Inputs: riskFactorIds (required).
classify_lesion_featuresARead-only
Describe which ABCDE criteria were supplied for a lesion. Educational only — does not name a condition, assign a risk level, or recommend urgency.
Inputs: asymmetry, diameterMm, hasChanged, multipleColors, +1 more.
compare_molesARead-only
Compare two recorded mole photos. Reports observed differences only — not a diagnosis.
Inputs: moleId (required), imageId1 (required), imageId2 (required).
get_condition_progressionARead-only
Get information about how a skin condition can progress. Shows potential progression paths (e.g., dysplastic nevus to melanoma).
Inputs: snomedCode (required).
get_condition_risk_factorsARead-only
Get risk factors associated with a specific condition. Returns factors like family history, skin type, UV exposure.
Inputs: snomedCode (required).
get_malignant_conditionsARead-only
Get a list of all malignant skin conditions in the ontology. Use for educational purposes about skin cancers.
Inputs: no named parameters.
get_mole_analysisARead-only
Return recorded ABCDE feature measurements for a mole. Educational only — not a diagnosis or risk level.
Inputs: moleId (required).
get_mole_changesARead-only
Return recorded appearance changes for a mole over time. Observations only — not a trend verdict.
Inputs: moleId (required).
get_user_molesARead-only
List a user's recorded moles and last photo dates. Educational records only — not a risk ranking.
Inputs: userId (required).
get_user_risk_factorsARead-only
List named educational skin-health factors on a user profile. Does not calculate a risk score.
Inputs: userId (required).
lookup_medical_conceptARead-only
Look up a medical concept by SNOMED CT code. Returns detailed information about skin conditions including severity and category. Use this to provide accurate medical terminology.
Inputs: snomedCode (required).
map_snomed_to_icd10ARead-only
Map a SNOMED CT code to ICD-10 diagnosis codes. Useful for understanding official diagnosis classifications.
Inputs: snomedCode (required).
search_medical_conceptsARead-only
Search for medical concepts by name or description. Returns matching SNOMED CT concepts for dermatology conditions.
Inputs: query (required).
search_medical_infoARead-only
Search the medical knowledge base for skin health information. Use this to provide accurate educational content about skin conditions, ABCDE criteria, and prevention tips.
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 14 tools
Tools are largely distinct with clear purposes, but there is some potential overlap between search_medical_info and search_medical_concepts (both retrieve medical knowledge) and between get_mole_analysis and classify_lesion_features (both describe ABCDE features). However, the descriptions clarify the differences—one is for stored mole records, the other for supplied lesion features.
All tool names follow a consistent snake_case verb_noun pattern (e.g., get_user_moles, search_medical_info, lookup_medical_concept). The verbs (get, search, compare, lookup, map, assess, classify) are specific and the pattern is uniform, making the API predictable.
14 tools is well within the ideal 3-15 range and each tool serves a distinct function within the skin health education domain. The scope feels appropriately sized—not too sparse, not overwhelming.
The tool set covers the core workflows: viewing user mole data, analyzing changes, retrieving medical info, looking up concepts, mapping codes, and understanding risk factors. A minor gap is the lack of tools for adding/updating mole records, but given the educational (non-CRUD) purpose, this is acceptable. Also, there is no explicit 'get_mole_photo' tool, though compare_moles implies photo access.
Maintenance
Related MCP Connectors
Public MCP endpoint for collaborative research and knowledge discovery.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Citepath public MCP server for LLM readiness audits and public scan results.
Hosted MCP server for the Healthie EHR & telehealth API: patients, appointments, charting, tasks.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides MCP tools to query device status, customer data, orders, and open incidents, and draft incident notes using mock SAP data.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible clients to discover and use The Holistic Care's approved public mindfulness resources, including interactive games, guided audio practices, research summaries, a glossary, and the public PanchaVikas framework, through read-only tools and static resources. No authentication is required, and it wraps a public REST API without creating, modifying, or deleting anything.MIT
- FlicenseNot gradedqualityAmaintenanceEnables MCP-compatible clients and LLM agents to perform full CRUD operations on FHIR resources, query and manipulate clinical data through natural-language prompts, and use document ingestion, semantic search, and terminology lookup against a FHIR backend.-
- FlicenseNot gradedqualityAmaintenanceEnables LLM-based agents and MCP-compatible clients to perform CRUD operations on healthcare resources, query clinical data with natural-language prompts, and use semantic document search, LOINC terminology lookup, and OAuth2-backed API access.-