Skip to main content
Glama
OMOPHub

OMOPHub MCP Server

Official
by OMOPHub
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

find_similar_concepts

Find medical concepts similar to a reference concept, name, or free-text query. Choose semantic, lexical, or hybrid matching to explore related codes or build phenotype sets.

Instructions

Find medical concepts similar to a reference concept, name, or natural language query. Supports three algorithms: 'semantic' (neural embeddings — best for meaning, and the default), 'lexical' (text matching — best for typos), 'hybrid' (combined). Provide exactly ONE of: concept_id, concept_name, or query. Use this to explore related concepts, find alternative codes, or build phenotype concept sets. Tip: For drug vocabularies like RxNorm, use drug class names ('ACE inhibitors', 'beta blockers', 'antihypertensives') rather than symptom descriptions ('medications for high blood pressure') — the embedding model aligns better with clinical terminology than lay language.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage of results (1-based, default 1)
queryNoFind concepts matching this natural language description
algorithmNoSimilarity algorithm: 'semantic' (meaning), 'lexical' (text), 'hybrid' (both). Default 'semantic', matching the API.semantic
page_sizeNoNumber of results (1-1000, default 20)
concept_idNoFind concepts similar to this OMOP concept ID
domain_idsNoComma-separated domain IDs to filter results. Examples: 'Condition', 'Drug'.
concept_nameNoFind concepts similar to this concept name
vocabulary_idsNoComma-separated vocabulary IDs to filter results. Examples: 'SNOMED', 'ICD10CM'.
concept_class_idsNoComma-separated concept class IDs to filter results. Examples: 'Clinical Finding', 'Ingredient'.
include_explanationsNoInclude a short explanation of why each concept matched. Default false.
similarity_thresholdNoMinimum similarity score (0.0-1.0). Default 0.7.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.6.3
    • changedInput schema / properties / algorithm / default
      Previous value: -"hybrid"New value: +"semantic"
    • changedInput schema / properties / algorithm / description
      Previous value: -"Similarity algorithm: 'semantic' (meaning), 'lexical' (text), 'hybrid' (both). Default 'hybrid'."New value: +"Similarity algorithm: 'semantic' (meaning), 'lexical' (text), 'hybrid' (both). Default 'semantic', matching the API."
    • addedInput schema / properties / concept_class_ids
      Added value: +{
+  "description": "Comma-separated concept class IDs to filter results. Examples: 'Clinical Finding', 'Ingredient'.",
+  "maxLength": 200,
+  "type": "string"
+}
    • addedInput schema / properties / include_explanations
      Added value: +{
+  "default": false,
+  "description": "Include a short explanation of why each concept matched. Default false.",
+  "type": "boolean"
+}
    • addedInput schema / properties / page
      Added value: +{
+  "default": 1,
+  "description": "Page of results (1-based, default 1)",
+  "minimum": 1,
+  "type": "number"
+}
  2. Changed2 schema fields changedv1.6.0
    • changedInput schema / properties / page_size / description
      Previous value: -"Number of results (1-100, default 20)"New value: +"Number of results (1-1000, default 20)"
    • changedInput schema / properties / page_size / maximum
      Previous value: -100New value: +1000
  3. First observedv1.5.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does a good job: it details the three algorithms and their intended strengths, states the default, enforces the 'exactly ONE of' input constraint, and even explains how the embedding model reacts to clinical vs lay language. It does not disclose output structure or pagination, but these are less critical for a read-only search tool.

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

Conciseness5/5

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

The description is dense but organized: main function, algorithm breakdown, use cases, and a practical tip. No filler sentences; the most load-bearing information is front-loaded.

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?

For a tool with 11 parameters, the schema covers all parameter semantics, and the description supplies the missing selection logic and domain guidance. It does not describe the result shape, but since no output schema exists, a brief statement of return values would strengthen it; still, an agent can invoke it correctly with the information provided.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds genuine value beyond the schema by stating the mutual-exclusion constraint among concept_id, concept_name, and query, and by providing a vocabulary-usage tip that affects how the query parameter is best phrased.

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?

States a specific action ('find medical concepts similar to...') with clear resource scope (reference concept, name, or query). It is distinct from exact-match search tools, but does not explicitly differentiate itself from sibling tools like semantic_search or search_concepts, so it falls 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 Guidelines4/5

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

Explicitly provides use cases: 'explore related concepts, find alternative codes, or build phenotype concept sets.' It gives a concrete tip for drug vocabularies. However, it does not mention when not to use it or name alternative tools, so no exclusions are given.

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

Deploy Server

Other Tools