ToolTrust
C25/100
Smithery

sidneybissoli-medical-terminologies

mcpsmithery

@Smithery

Unified MCP server giving LLMs and AI agents reliable lookup access to seven medical terminology systems — instead of inventing codes, the model queries the same APIs that WHO, NLM, and NIH publish for clinical and research use. **Terminologies covered:** - **ICD-11** — WHO's current International Classification of Diseases - **LOINC** — laboratory observations and clinical measurements (NLM) - **RxNorm** — normalized drug nomenclature (NIH) - **MeSH** — Medical Subject Headings for PubMed search refinement (NLM) - **ATC** — Anatomical Therapeutic Chemical classification (via NLM RxClass) - **CID-10** — Brazilian Portuguese ICD-10 (bundled DataSUS V2008) - **SNOMED CT** — optional, license-gated (requires a self-hosted Snowstorm endpoint) **Highlights:** - **37 tools** across search, lookup, hierarchy navigation, batch validation, and cross-terminology mapping - **Authoritative WHO ICD-10 → ICD-11 mapping** via bundled transition tables (release 2025-01, 11,243 categories — 1,461 with documented alternatives) - **Cross-terminology batch validator** flags codes that no longer exist and surfaces ICD-10 → ICD-11 replacements - Tool responses include both human-readable text and `structuredContent` matching a published `outputSchema` (for tools whose results are structured) - Per-tool `language` parameter on SNOMED, ICD-11, and MeSH for multilingual workflows - **Hosted Streamable HTTP endpoint** at `medical-terminologies-mcp.sidneybissoli.workers.dev/mcp` — no install required - TypeScript / Node 20+, OAuth2 with proper `expires_in` handling, token-bucket rate limiting (5/10/20 req/s per API), exponential backoff with jitter, 313 unit + contract tests gating CI, daily live-API integration cron - **MIT licensed** **Audience:** clinical informaticians, biomedical researchers, public-health analysts, EMR integrators, and developers building agentic workflows around medical coding. This is a lookup layer, not a clinical decision tool.

By Smithery | 55 findings | Scanned 6/3/2026 | tooltrust-scanner/v0.3.13

9 High4 Medium11 Low31 Info

Risk Summary

Needs Approval

Dep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (55)

  • HighAS-002

    ⚠️Excessive Permissions ×9

    tool declares network permission

    icd11_searchicd11_lookuploinc_searchrxnorm_searchmesh_searchmap_loinc_to_snomedvalidate_codescid10_searchterminology_versions

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • MediumAS-002

    ⚠️Excessive Permissions ×4

    tool declares fs permission

    icd11_hierarchymap_loinc_to_snomed

    tool declares db permission

    validate_codesterminology_versions

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×10

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    icd11_searchicd11_lookuploinc_searchrxnorm_searchmesh_searchmap_loinc_to_snomedvalidate_codescid10_searchcid10_lookupterminology_versions

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • LowAS-002

    ⚠️Excessive Permissions

    cid10_lookup:tool declares http permission

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×31

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    icd11_searchicd11_lookupicd11_hierarchyicd11_chaptersicd11_postcoordinationloinc_searchloinc_detailsloinc_answersloinc_panelsrxnorm_searchrxnorm_conceptrxnorm_ingredientsrxnorm_classesrxnorm_ndcmesh_searchmesh_descriptormesh_treemesh_qualifiersmap_icd10_to_icd11map_loinc_to_snomedvalidate_codesfind_equivalentatc_classifyatc_lookupatc_memberscid10_searchcid10_lookupcid10_chapterscid10_chapterterminology_versionsterminology_diff

    Fix: Review and remediate the identified issue.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y sidneybissoli-medical-terminologies"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)