AIND Data MCP Server
AllenNeuralDynamics/aind-data-mcp
Acesso a dados neurocientíficos AIND via MCP com MongoDB e NWB
Ver no GitHubServidor MCP que fornece acesso a metadados e ativos de dados do Allen Institute for Neural Dynamics (AIND) através de ferramentas para consulta MongoDB, navegação de schema V2 e acesso a arquivos NWB. Integra-se com Claude para análise e exploração de dados neurocientíficos estruturados.
Instalação
npx convez-ai AllenNeuralDynamics/aind-data-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Consultar e filtrar metadados de experimentos neurais em MongoDB
- Explorar estrutura de schema V2 do AIND durante análise
- Carregar e inspecionar arquivos NWB de Code Ocean ou S3
- Gerar agregações complexas e resumos AI-powered de ativos de dados
Veredito

Ferramenta especializada e bem-construída (100% cobertura de testes, documentação clara) para pesquisadores que trabalham com repositórios AIND. Recomendado apenas se você trabalha com dados neurais estruturados do Allen Institute; caso contrário, não é relevante.
README
A tradução para o português deste README ainda está na fila.
AIND Data MCP Server
An MCP (Model Context Protocol) server that provides access to AIND (Allen Institute for Neural Dynamics) metadata and data assets through a comprehensive set of tools and resources. This server targets the V2 aind-data-schema format.
Installation
Each IDE/client has its own configuration method, look at their documentation for instructions on MCP configuration/setup.
You can either use the command uvx aind-data-mcp to launch the server, or install it locally with uv tool install aind-data-mcp and then launch it with just aind-data-mcp.
For use in Code Ocean
- Refer to the code ocean MCP server for additional support
Features
This MCP server provides the following tools:
Data Retrieval & Querying
get_records— Query MongoDB collections using filters and projectionsaggregation_retrieval— Execute complex MongoDB aggregation pipelinescount_records— Count documents matching a filterflatten_records— Retrieve and flatten records into dot-notation for easier inspectionget_project_names— List all project names in the databaseget_summary— Generate an AI-powered summary for a specific data asset
Schema Navigation
get_top_level_nodes— Explore the top-level fields of the V2 metadata schemaget_additional_schema_help— Query-writing guidance for V2 aggregationsget_modality_types— List all available data modality names and abbreviations
Schema Examples (one tool per document type)
get_acquisition_example,get_data_description_example,get_instrument_example,get_procedures_example,get_subject_example,get_processing_example,get_model_example,get_quality_control_example
NWB File Access
identify_nwb_contents_in_code_ocean— Load an NWB file from the/datadirectory in a Code Ocean capsuleidentify_nwb_contents_with_s3_link— Load an NWB file from an S3 path
Resources (accessible via the MCP protocol)
resource://aind_api— Context and usage patterns for the AIND data access APIresource://load_nwbfile— Reference script for loading NWB files
Development
To develop the code, run
uv sync --extra dev
To run tests:
uv run coverage run -m unittest discover && uv run coverage report
To run linting:
uv run flake8 . && uv run interrogate --verbose .