ols4
by EBISPOT
Overview
A comprehensive Ontology Lookup Service (OLS) that provides a web interface, REST API, and an OpenAI-compliant MCP (Microservice-Coded-Prompt) server for biomedical ontologies, supporting search, graph traversal, and AI-driven entity understanding through embeddings.
Installation
No command providedEnvironment Variables
- OLS4_CONFIG
- OPENAI_API_KEY
- OLS_SOLR_HOST
- OLS_NEO4J_HOST
- JAVA_OPTS
- NEO4J_AUTH
- OLS4_DATALOAD_ARGS
- OLS4_APITEST_OUTDIR
- OLS4_APITEST_COMPAREDIR
- KUBECONFIG
- NEO4J_HOME
- SOLR_HOME
- OLS4_HOME
- SERVER_SERVLET_CONTEXT_PATH
- SPRING_AI_MCP_SERVER_BASE_URL
- JDK_JAVA_OPTIONS
- REACT_APP_APIURL
- PUBLIC_URL
- OLS_MINIFY
Security Notes
The Neo4j service (`ols4-neo4j`) in `docker-compose.yml` and Kubernetes (`ols4-neo4j-deployment.yaml`) explicitly sets `NEO4J_AUTH=none`, disabling authentication for the graph database. While this might be acceptable for development or tightly controlled internal deployments where Neo4j is not directly exposed, it represents a critical security vulnerability if the service becomes accessible from an untrusted network. There are no other obvious critical vulnerabilities like arbitrary code execution via 'eval' or hardcoded high-privilege secrets in the provided snippets. Proxy configurations exist (`ols4-proxy-configmap.yaml`) but specify `no_proxy` for local cluster traffic, mitigating some potential exfiltration risks within the cluster.
Similar Servers
mcp_massive
An AI agent orchestration server, likely interacting with LLMs and managing multi-agent workflows.
pyomop
Facilitates OHDSI OMOP Common Data Model (CDM) database interactions, including schema management, data loading (FHIR, Eunomia), querying, and export, with optional LLM-based natural language interfaces.
tiger-linear-mcp-server
Provides LLMs with focused tools to interact with the Linear API for issue and project management.
knowledgebase-mcp
Provides a standardized connection layer between artificial intelligence systems (LLMs) and biomedical research resources for information retrieval and domain-specific tasks.