Shiranui
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., "@Shiranui search for adverse events controlled terminology"
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.
Shiranui
Shiranui is the Model Context Protocol(MCP) Server for retreiving the clinical standard contents in the CDISC Library.
This MCP server is built with Python FastMCP.
https://github.com/user-attachments/assets/9cd7e1a6-2750-4910-bb03-763c323b9f22
Support CDISC Library API
v2 Biomedical Concept Endpoints
v2 Dataset Specialization Endpoints
Controlled Terminology Codelist Endpoints
ADaM Variable Metadata Endpoints
SDTM Metadata Endpoints
CDASH Metadata Endpoints
SEND Metadata Endpoints
Search Tool
Related MCP server: Medical Terminologies MCP
Requirements
Python v3.13 and UV were installed on your device.
You have the CDISC Library API Key.
Installation
Download Shiranui from the Releases Page.
Mac and Linux
cd /your/shiranui/dir
uv syncSet your API key as an environment variable named CDISC_LIBRARY_API_KEY.
Windows
Use back slash "\" for path separator charactor.
cd C:\your\shiranui\dir
uv syncSet your API key as an environment variable named CDISC_LIBRARY_API_KEY.
Configure mcp client
LM Studio
Mac and Linux
{
"mcpServers": {
"Shiranui": {
"command": "uv",
"args": [
"run",
"/full/path/to/shiranui/dir/.venv/bin/shiranui"
]
}
}
}Windows
Use slash"/" for path separator charactor.
{
"mcpServers": {
"Shiranui": {
"command": "uv",
"args": [
"run",
"C:/full/path/to/shiranui/dir/.venv/Scripts/shiranui"
]
}
}
}You need to replace "/full/path/to/shiranui/dir" to match your own environment.
In addition to LM Studio, it may also work with Claude Desktop, Codename Goose, and other MCP Clients.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Available Tools
31 toolsget_adam_dataset_structureB
Get the structure and variables for a specific ADaM dataset
Args: dataset: The ADaM dataset name (e.g., ADSL, ADAE, OCCDS) adamig_version: ADaMIG version (e.g., "1-3" or "1.3"). Default is "1-3".
Usage: get_adam_dataset_structure("ADSL") get_adam_dataset_structure("ADAE", "1-3")
Returns: Dictionary with dataset structure and list of variables
Inputs: dataset (required), headers_, adamig_version.
get_adam_variable_detailsA
Retrieve ADaM variable metadata including label, datatype, and associated codelists
Args: adam_variable: The ADaM variable name (e.g., TRT01P, PARAMCD, AVAL) adamig_version: ADaMIG version (e.g., "1-3" or "1.3"). Default is "1-3".
Usage: get_adam_variable_details("TRT01P") get_adam_variable_details("PARAMCD", "1-3") get_adam_variable_details("AVAL", "1-2")
Returns: Dictionary with variable details, label, datatype, core status, and associated codelists
Inputs: adam_variable (required), headers_, adamig_version.
get_bc_for_packageC
Get a specific Biomedical Concept from a specific package
Args: package (str): The ID of the package to retrieve biomedical concepts from. biomedicalconcept_id (str): The ID of the Biomedical Concept to retrieve.
Usage: get_bc_for_package("PACKAGE", "BIOM EDICALCONCEPT_ID")
Inputs: package (required), biomedicalconcept_id (required), headers_.
get_bc_list_for_packageC
Get Biomedical Concept list for a specific Package
Args: package(str): The ID of the Package to retrieve biomedical concept list from.
Usage: get_bc_package("PACKAGE")
Inputs: package (required), headers_.
get_bc_package_listC
Get Biomedical Concept Package List from CDISC Library
Usage: get_bc_package_list()
Inputs: headers_.
get_cdashig_domains_listA
Get list of all CDASH domains for a specific CDASHIG version.
Args: cdashig_version (str, optional): CDASHIG version (e.g., "2-3" or "2.3"). If not provided, uses latest version. headers_ (dict, optional): Custom headers for API request.
Returns: dict: Contains CDASHIG version and list of all domains with metadata.
Example: get_cdash_domains_list("2-3") Returns list of domains like AE, CM, DM, VS, etc.
Inputs: headers_, cdashig_version.
get_cdashig_domain_structureA
Get complete domain structure with all fields for a CDASH domain.
Args: domain (str): CDASH domain code (e.g., "DM", "AE", "VS", "CM"). cdashig_version (str, optional): CDASHIG version (e.g., "2-3" or "2.3"). If not provided, uses latest version. include_codelists (bool, optional): If True, retrieves full codelist terms for fields. Default False for faster response. headers_ (dict, optional): Custom headers for API request.
Returns: dict: Contains domain metadata and complete list of fields with their attributes.
Example: get_cdash_domain_structure("CM", "2-3") Returns concomitant medications domain with all data collection fields
Inputs: domain (required), headers_, cdashig_version, include_codelists.
get_cdashig_field_detailsA
Get detailed metadata for a specific CDASH field.
Args: field (str): Field name (e.g., "USUBJID", "AESTDTC", "CMTRT"). domain (str, optional): CDASH domain code (e.g., "DM", "AE", "CM"). If not provided, will search common domains. cdashig_version (str, optional): CDASHIG version (e.g., "2-3" or "2.3"). If not provided, uses latest version. include_codelist (bool, optional): If True, retrieves full codelist terms. Default True. headers_ (dict, optional): Custom headers for API request.
Returns: dict: Contains field metadata including name, label, datatype, core, definition, prompt, and optionally associated codelist terms.
Example: get_cdash_field_details("CMTRT", "CM", "2-3") Returns metadata for Concomitant Medication Name field
Inputs: field (required), domain, headers_, cdashig_version, +1 more.
get_cdashig_latest_versionA
Get the latest CDASH-IG version from the CDISC Library API.
Args: headers_ (dict, optional): Custom headers for API request.
Returns: dict: Contains latest version, all available versions, and display version.
Example: get_cdash_latest_version() Returns: {"latest_version": "2-3", "display_version": "CDASHIG v2.3", ...}
Inputs: headers_.
get_cdisc_codelistA
Retrieve CDISC Controlled Terminology codelist with terms and metadata
Args: codelist_value: The codelist name (e.g., AGEU, PARAMCD, ACN, DTYPE) codelist_type: Match by 'ID' or 'CodelistCode'. Default is 'ID'. standard: CDISC standard (SDTM, ADAM, CDASH, etc.). Default is 'SDTM'. version: CT version in YYYY-MM-DD format. If not provided, fetches latest.
Usage: get_cdisc_codelist("AGEU") get_cdisc_codelist("ACN", standard="SDTM") get_cdisc_codelist("DTYPE", standard="ADAM") get_cdisc_codelist("AGEU", version="2024-12-20") get_cdisc_codelist("C66734", codelist_type="CodelistCode")
Returns: Dictionary containing codelist metadata and all terms with their decoded values
Inputs: codelist_value (required), version, headers_, standard, +1 more.
get_ct_latest_versionB
Get the latest Controlled Terminology version for a CDISC standard
Args: standard: The CDISC standard (SDTM, ADAM, CDASH, etc.). Default is SDTM.
Usage: get_ct_latest_version_tool("SDTM") get_ct_latest_version_tool("ADAM")
Returns: Dictionary with standard, latest version, display version, and all available versions
Inputs: headers_, standard.
get_ct_package_codelistsA
Get all codelists available in a CDISC Controlled Terminology package
Args: standard: CDISC standard (SDTM, ADAM, CDASH, etc.). Default is 'SDTM'. version: CT version in YYYY-MM-DD format. If not provided, fetches latest.
Usage: get_ct_package_codelists("SDTM") get_ct_package_codelists("ADAM", "2024-12-20")
Returns: Dictionary containing all codelists with their IDs and names
Inputs: version, headers_, standard.
get_latest_bcC
Get latest Biomedical Concept specified by concept_id from CDISC Library
Args: concept_id (str): The ID of the Biomedical Concept to retrieve.
Usage: get_latest_bc_cat("C105585")
Inputs: concept_id (required), headers_.
get_latest_bc_catC
Get Latest Biomedical Concept Categories from CDISC Library
Usage: get_latest_bc_cat()
Inputs: headers_.
get_latest_bc_dataset_specializationsB
Get latest Biomedical Concept Dataset Specializations List from CDISC Library
Args: biomedicalconcept (str): The biomedical concept to retrieve dataset specializations for.
Usage: get_latest_bc_dataset_specializations("C105585")
Inputs: biomedicalconcept (required), headers_.
get_latest_bc_listC
Get Latest Biomedical Concept List from CDISC Library
Usage: get_latest_bc_list()
Inputs: headers_.
get_latest_sdtm_dataset_specializations_listB
Get Latest SDTM Dataset Specializations List for a specific domain
Args: domain (str): The domain to retrieve dataset specializations for.
Usage: get_latest_sdtm_dataset_specializations("DM")
Inputs: domain (required), headers_.
get_latest_sdtm_specializationB
Get Latest SDTM Specialization for a specific specialization ID
Args: dataset_specialization_id (str): The specialization ID to retrieve details for.
Usage: get_latest_sdtm_specialization("SYSBP")
Inputs: dataset_specialization_id (required), headers_.
get_sdtm_classesA
Get SDTM domain classes (Findings, Events, Interventions, etc.) from CDISC Library.
Args: sdtmig_version (str, optional): SDTM-IG version (e.g., "3-4" or "3.4"). If not provided, uses latest version. headers_ (dict, optional): Custom headers for API request.
Returns: dict: Contains SDTM classes with their domains or error information.
Example: get_sdtm_classes("3-4") Returns list of classes: FINDINGS, EVENTS, INTERVENTIONS, SPECIAL PURPOSE, etc.
Inputs: headers_, sdtmig_version.
get_sdtm_dataset_specialization_domain_listC
Get SDTM Dataset Specialization Domain List from CDISC Library
Usage: get_sdtm_dataset_specialization_domain_list()
Inputs: headers_.
get_sdtm_dataset_specialization_for_packageC
Get SDTM Dataset Specialization for a specific package and dataset specialization
Args: package (str): The ID of the package to retrieve dataset specializations from. datasetspecialization (str): The ID of the dataset specialization to retrieve.
Usage: get_sdtm_dataset_specialization_for_package("PACKAGE", "DATASET_SPECIFICATION")
Inputs: package (required), datasetspecialization (required), headers_.
get_sdtm_dataset_specialization_list_for_packageC
Get SDTM Dataset Specializations List for a specific Package
Args: package(str): The ID of the package to retrieve dataset specializations list from.
Usage: get_sdtm_dataset_specialization_list_for_package("PACKAGE")
Inputs: package (required), headers_.
get_sdtm_dataset_specialization_package_listC
Get SDTM Dataset Specialization Package List from CDISC Library
Usage: get_sdtm_dataset_specialization_package_list()
Inputs: headers_.
get_sdtm_domain_structureA
Get complete domain structure with all variables for an SDTM domain.
Args: domain (str): SDTM domain code (e.g., "DM", "AE", "VS", "LB"). sdtmig_version (str, optional): SDTM-IG version (e.g., "3-4" or "3.4"). If not provided, uses latest version. include_codelists (bool, optional): If True, retrieves full codelist terms for variables. Default False for faster response. headers_ (dict, optional): Custom headers for API request.
Returns: dict: Contains domain metadata and complete list of variables with their attributes.
Example: get_sdtm_domain_structure("DM", "3-4") Returns demographics domain with all required/expected/permissible variables
Inputs: domain (required), headers_, sdtmig_version, include_codelists.
get_sdtm_latest_versionA
Get the latest SDTM-IG version from CDISC Library.
Returns: dict: Contains the latest SDTM-IG version or error information.
Example: get_sdtm_latest_version() Returns: {"latest_version": "3-4", "display_version": "3.4"}
Inputs: headers_.
get_sdtm_variable_detailsA
Get detailed metadata for a specific SDTM variable.
Args: variable (str): Variable name (e.g., "USUBJID", "AESTDTC", "LBORRES"). domain (str, optional): SDTM domain code (e.g., "DM", "AE", "VS"). If not provided, will search common domains. sdtmig_version (str, optional): SDTM-IG version (e.g., "3-4" or "3.4"). If not provided, uses latest version. include_codelist (bool, optional): If True, retrieves full codelist terms. Default True. headers_ (dict, optional): Custom headers for API request.
Returns: dict: Contains variable metadata including name, label, datatype, core, role, and optionally associated codelist terms.
Example: get_sdtm_variable_details("AESTDTC", "AE", "3-4") Returns metadata for AE Start Date/Time variable
Inputs: variable (required), domain, headers_, sdtmig_version, +1 more.
get_sendig_classesB
Get list of all SEND domain classes (Findings, Events, Interventions, etc.)
Args: sendig_version (str): SENDIG version (e.g., "3-1-1" or "3.1.1"). If not specified, uses latest version. headers_: Optional custom headers
Returns: dict: Domain classes information
Example: get_sendig_classes() get_sendig_classes("3-1-1")
Inputs: headers_, sendig_version.
get_sendig_domain_structureA
Get complete SEND domain structure with all variables and metadata
Args: domain (str): SEND domain name (e.g., "DM", "EX", "LB", "MI") sendig_version (str): SENDIG version (e.g., "3-1-1" or "3.1.1"). If not specified, uses latest version. headers_: Optional custom headers
Returns: dict: Complete domain structure including variables with metadata
Example: get_sendig_domain_structure("DM") get_sendig_domain_structure("LB", "3-1-1")
Inputs: domain (required), headers_, sendig_version.
get_sendig_latest_versionC
Get the latest SEND Implementation Guide version from CDISC Library
Args: headers_: Optional custom headers
Returns: dict: Latest SENDIG version information
Example: get_sendig_latest_version()
Inputs: headers_.
get_sendig_variable_detailsA
Get detailed metadata for a SEND variable with optional codelist integration
Args: variable (str): Variable name (e.g., "USUBJID", "LBTESTCD", "MISPEC") domain (str): SEND domain name. If not specified, will attempt to auto-detect. sendig_version (str): SENDIG version (e.g., "3-1-1"). If not specified, uses latest version. include_codelist (bool): If True and variable has controlled terminology, retrieve the codelist headers_: Optional custom headers
Returns: dict: Variable details including label, datatype, core status, and optional codelist
Example: get_sendig_variable_details("USUBJID") get_sendig_variable_details("LBTESTCD", "LB", include_codelist=True)
Inputs: variable (required), domain, headers_, sendig_version, +1 more.
search_cdisc_libraryA
Search across all CDISC Library content (variables, domains, codelists, BC, etc.)
Args: query (str): Search query string limit (int): Maximum number of results to return (default: 100, max: 500) headers_: Optional custom headers
Returns: dict: Search results with hits, totalHits, and hasMore
Example: search_cdisc_library("blood pressure") search_cdisc_library("USUBJID", limit=50)
Inputs: query (required), limit, headers_.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 31 tools
Many tools form near-duplicate clusters, especially the five SDTM dataset specialization tools and the Biomedical Concept tools (get_latest_bc vs get_latest_bc_cat vs get_latest_bc_list). Several descriptions even reference the wrong function name, e.g., get_latest_bc's usage calls get_latest_bc_cat, increasing confusion.
Tools consistently use get_ prefix and snake_case, but word order and qualifier placement vary unpredictably: get_sdtm_dataset_specialization_list_for_package vs get_sdtm_dataset_specialization_package_list, and get_ct_latest_version vs get_sdtm_latest_version. Singular/plural forms are also mixed, and abbreviations like bc, ct, cdashig are inconsistently placed.
31 tools is excessive for what is essentially a read-only metadata retrieval API. Many tools could be consolidated with standard and version parameters, and the count exceeds the reasonable upper bound for a coherent tool set.
The set covers SDTM, ADaM, CDASH, SEND, Controlled Terminology, Biomedical Concepts, dataset specializations, and search, so major workflows are supported. Minor gaps exist, such as no direct ADaM-IG version tool or general package list, but these are workable.
Maintenance
Related MCP Connectors
NIH Clinical Tables Search Service MCP.
Siftable MCP server for governed work, knowledge, calendar, people, datasets, and Vault.
MCP server for AI access to Swagger by SmartBear.
Hosted MCP server for finding authoritative primary data sources and official portals.
Related MCP Servers
- FlicenseAqualityDmaintenanceA TypeScript MCP server for interacting with CDISC Define-XML 2.0 and 2.1 files, enabling users to load, search, and retrieve clinical data metadata including datasets, variables, and codelists. It supports local file processing with document caching and provides responses in both JSON and Markdown formats.13-
- AlicenseAqualityBmaintenanceUnified MCP server providing LLMs with reliable lookup access to ICD-11, LOINC, RxNorm, MeSH, ATC, CID-10, and (optionally) SNOMED CT.33339 npm16MIT
- AlicenseNot gradedqualityDmaintenanceEnables querying and browsing SNOMED CT medical terminology concepts, including search, details, and hierarchy navigation via MCP tools.3MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides SNOMED CT clinical terminology lookup via any FHIR R4 terminology server supporting SNOMED CT and ECL. Offers tools for searching by term, fetching by code, and navigating the concept hierarchy.21Apache 2.0