KlastroHeron BioMedical is an MCP server that searches Europe PMC and the EMA regulatory database, then returns one synthesized, cited answer, not a raw list of papers, and not a diagnostic tool. It runs entirely inside your own AWS account via Amazon Bedrock, with no seller-hosted backend and no customer data collection.
KlastroHeron BioMedical is a Model Context Protocol (MCP) server for biomedical literature search and regulatory lookup. Given a natural-language question, it searches Europe PMC for relevant research papers and, for named-drug questions, cross-checks the European Medicines Agency's (EMA) public regulatory database, including marketing authorisation status, ATC code, orphan/biosimilar/generic flags, and any safety alerts on record. It returns a single synthesized, cited answer rather than a raw search result list, so downstream agents and applications get a usable answer, not a research task.
EMA data is downloaded directly from EMA's own public exports and refreshed automatically (at startup, then monthly), so there is no manual data-update process. Premium and Enterprise plans additionally receive citation-metric enrichment and an extracted methodology summary alongside each answer. The service auto-detects the language of each question and answers in kind, across 31 supported languages configurable per deployment.
The product is delivered as a single self-hosted container exposing two MCP tools, search_literature and lookup_drug_regulatory_info, over stateless streamable-HTTP, so it can be called directly by any MCP-compatible orchestrator or agent platform. It runs entirely inside your own AWS account: LLM inference goes through Amazon Bedrock using your account's IAM role, no data is sent to or stored by the seller, and there is no seller-operated backend. This is a research and regulatory-information tool, not a medical device, and it is not intended for diagnosis or treatment decisions.
Highlights
Cited Literature Search & Synthesis: Searches Europe PMC and returns one synthesized, cited answer, not a raw paper list, with citation-metric badges and methodology summaries on Premium/Enterprise plans.
EMA Regulatory Database Integration: For named-drug questions, cross-checks EMA's public regulatory data (authorisation status, ATC code, safety alerts), refreshed automatically from EMA's own exports with no manual updates required.
Self-Hosted, Multi-Language MCP Server: Deploys as a standard MCP-compliant container in your own AWS account via Amazon Bedrock, with no seller-hosted backend, no data leaving your environment, and auto-detected support across 31 languages.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
You choose one of three annual licenses based on who uses the product and how widely it deploys. The Academic & Personal License covers a single individual or staff at one academic or non-profit research institution. The Commercial Team License covers one research or clinical team at a commercial biotech, pharmaceutical, or CRO organization. The Enterprise License covers deployment across all teams and sites within one commercial organization. Pricing scales with organizational scope, moving from an individual or single institution, to one commercial team, to a whole commercial organization. All three bill per unit annually.
Top-of-mind questions for buyers
How do I choose between the three licenses if my organization spans multiple teams and sites?
The license matches your deployment scope. Choose the Academic & Personal License for one individual or one academic or non-profit institution. Choose the Commercial Team License for a single research or clinical team at a commercial organization. Choose the Enterprise License to cover all teams and sites within one commercial organization.
Does each license include control over the model, data path, and encryption key?
The product deploys into an environment where you control the key, model, and data path. This BYOK (bring-your-own-key) design applies to the evidence engine itself. Specific control differences between the three annual licenses are not detailed in the available data, so confirm your setup with the vendor.
What sources does this biomedical evidence engine search under any of the licenses?
The engine searches biomedical literature and European regulatory records. It provides a private evidence engine for pharma and life-science research. All three annual licenses draw on this same engine; they differ only in who may use it and how widely it deploys.
www.klastrovanie.com
Helpful?
Vendor refund policy
Refunds are evaluated case-by-case. Customers may request a refund within 14 days of purchase if the software has not been deployed to production. Contract-based licenses (Academic & Personal License, Commercial Team License, Enterprise License) are non-refundable once deployed to production or after 30 days from the contract start date, except as required by law. To request a refund, contact support@klastrovanie.com with your AWS account ID and order details. We respond within 3 business days.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Fixed a language handling issue where Portuguese (pt) queries could return an English disclaimer and methodology header instead of Portuguese. Portuguese, Arabic, and Hebrew language support have been verified end to end.
Additional details
Usage instructions
Container listens on port 8000, path /mcp (MCP streamable-HTTP transport, stateless, no session state, no web UI).
Required environment variables:
KH_LLM_PROVIDER=bedrock
AWS_REGION=<your AWS region, e.g. eu-north-1>
KH_BEDROCK_GEO=<eu|us|au|jp|global> (must match your AWS_REGION's geography)
Optional environment variables:
KH_EMA_ENABLED=true (default, enables EMA regulatory lookup; EMA data is downloaded automatically at container startup and refreshed monthly)
KH_LANGUAGES=en,ko,ja (comma-separated, restricts which languages are loaded; defaults to a standard set if omitted)
Health check: GET /health on port 8000 returns {"status":"ok", ...}. This image does not include curl. For an ECS container-level health check, use:
"healthCheck": {"command": ["CMD-SHELL", "python3 -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health', timeout=3)" || exit 1"], "interval": 30, "timeout": 5, "retries": 3}
For EKS, a standard httpGet livenessProbe/readinessProbe against path /health, port 8000 works with no changes, since Kubernetes probes are performed by the kubelet rather than from inside the container, so no curl is required.
Full API reference, response schema, and language configuration are in the User Manual under Resources.
Technical support is available for KlastroHeron BioMedical deployment, configuration, container operation, and MCP integration with agent platforms and orchestrators. Support includes assistance with installation issues, container configuration, Amazon Bedrock setup, language configuration, and product-related technical questions.
Standard support is provided by email on business days. Enterprise customers and customers purchasing through a Private Offer may receive additional deployment and integration support according to the terms of their agreement.
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Mediktor is an AI-based digital triage solution that assesses patients symptoms and provides a pre-diagnostic guide, directing them to the appropriate level of medical care. With clinically validated technology developed by doctors, it provides a safe and accurate healthcare experience.
Mediktor offers support, training, and consulting services to help healthcare organizations take full advantage of Mediktor AI Triage (AWS Marketplace product) to optimize resources and maximize efficiency.
Rapidly validate Claude or other LLM workflows in GxP/HIPAA environments. Includes SOP templates, prompt-safety guidelines, and AWS audit logging recipes.
Improve the efficiency, authority, and relevance of your Life Sciences agents with Wiley's Life Sciences Agent Knowledge Base, that incorporates full text, peer reviewed, expert curated corpus spanning the entire drug development pipeline. Our full corpus of trusted content, including over 800k articles from 300+ journals, are available in structured, machine readable, and metadata enriched format, delivered through a seamless and secure API endpoint. Our authoritative content will support you to maximize return on your AI investment, whether you are using AI to accelerate literature review and drug discovery, improve clinical trial outcomes, boost sales and marketing, or transform clinician knowledge delivery. Contact us via Request private offer to connect with a Wiley Sales representative and learn how our trusted, peer-reviewed content can accelerate your enterprise AI initiatives.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.