Click on "Install 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., "@EMA MCP Server search for authorized diabetes medicines with semaglutide"
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.
A Model Context Protocol (MCP) server providing access to the European Medicines Agency (EMA) public JSON API for regulatory intelligence and pharmaceutical research.
This MCP server complements FDA data sources by providing comprehensive access to EU drug approvals, EPARs (European Public Assessment Reports), orphan designations, supply shortages, safety reviews, and regulatory procedures. Together with FDA coverage, this provides ~70% global pharmaceutical market regulatory intelligence.
Key Features:
Single unified ema_info tool with method parameter (MCP best practice)
14 comprehensive methods covering medicines, safety, documents, and pediatrics
2,641+ EU-approved medicines with 39 fields each
Real-time orphan designations, supply shortages, and safety data
Document search (EPAR, all EMA documents, non-EPAR documents)
Related MCP server: ,APEX MCP Server
{
"mcpServers": {
"ema-mcp-server": {
"command": "node",
"args": ["/path/to/ema-mcp-server/build/index.js"],
"env": {}
}
}
}search_medicinesSearch EU-approved medicines database.
Parameters:
active_substance (string, optional): Active substance name (e.g., "semaglutide", "adalimumab")
therapeutic_area (string, optional): Disease or therapeutic area (e.g., "diabetes", "cancer")
status (string, optional): Medicine status - "Authorised", "Withdrawn", "Refused", "Suspended"
orphan (boolean, optional): Filter for orphan medicines only
prime (boolean, optional): Filter for PRIME (priority) medicines only
biosimilar (boolean, optional): Filter for biosimilar medicines only
conditional_approval (boolean, optional): Filter for conditionally approved medicines
limit (number, optional): Maximum results (default: 100, max: 10000)
Example:
{
"method": "search_medicines",
"active_substance": "semaglutide",
"status": "Authorised",
"limit": 10
}Returns: 3 semaglutide medicines (Ozempic, Wegovy, Rybelsus)
get_medicine_by_nameGet specific medicine by trade name.
Parameters:
name (string, required): Medicine trade name (case-insensitive, supports partial matching)
Example:
{
"method": "get_medicine_by_name",
"name": "Ozempic"
}Returns: Complete medicine record with EMA product number, active substance, approval details, etc.
get_orphan_designationsGet EU orphan drug designations for rare diseases.
Parameters:
therapeutic_area (string, optional): Disease/condition (searches in intended_use field)
active_substance (string, optional): Active substance name
year (number, optional): Designation year (1995-2026)
status (string, optional): "Positive", "Negative", "Withdrawn"
limit (number, optional): Maximum results (default: 100, max: 10000)
Example:
{
"method": "get_orphan_designations",
"therapeutic_area": "cancer",
"year": 2024,
"status": "Positive"
}Returns: Cancer orphan designations from 2024 with positive status
get_supply_shortagesGet medicine supply shortage information.
Parameters:
active_substance (string, optional): Active substance or INN
medicine_name (string, optional): Medicine trade name
therapeutic_area (string, optional): Therapeutic area
status (string, optional): "Ongoing" or "Resolved" (case-insensitive)
limit (number, optional): Maximum results (default: 50, max: 10000)
Example:
{
"method": "get_supply_shortages",
"status": "Ongoing",
"medicine_name": "insulin"
}Returns: Ongoing insulin shortages with affected products and reasons
get_referralsGet EU-wide safety reviews and referrals.
Parameters:
safety (boolean, optional): Filter for safety-related referrals (true=Yes, false=No)
active_substance (string, optional): Active substance name
status (string, optional): Current status (e.g., "Under evaluation", "Completed")
year (number, optional): Procedure start year (1995-2026)
limit (number, optional): Maximum results (default: 50, max: 10000)
Example:
{
"method": "get_referrals",
"safety": true,
"year": 2024
}Returns: Safety-related referrals started in 2024
Note: The safety_referral field uses "Sì" (Italian) for Yes and "No" for No.
get_post_auth_proceduresGet post-authorization procedures (label updates, extensions, etc.).
Parameters:
medicine_name (string, optional): Medicine name to filter
limit (number, optional): Maximum results (default: 50, max: 10000)
Example:
{
"method": "get_post_auth_procedures",
"medicine_name": "Brilique"
}Returns: Post-authorization procedures for Brilique
get_dhpcsGet Direct Healthcare Professional Communications (DHPCs) - safety communications sent to healthcare professionals.
Parameters:
medicine_name (string, optional): Medicine name to filter
active_substance (string, optional): Active substance name
dhpc_type (string, optional): Type of DHPC
year (number, optional): Dissemination year (1995-2026)
limit (number, optional): Maximum results (default: 50, max: 10000)
Example:
{
"method": "get_dhpcs",
"year": 2024
}Returns: DHPCs from 2024 with safety information for healthcare professionals
get_psusasGet Periodic Safety Update Reports (PSUSAs) - ongoing safety monitoring outcomes.
Parameters:
active_substance (string, optional): Active substance name (searches both active_substance and active_substances_in_scope_of_procedure)
regulatory_outcome (string, optional): Regulatory outcome
limit (number, optional): Maximum results (default: 100, max: 10000)
Example:
{
"method": "get_psusas",
"active_substance": "metformin"
}Returns: PSUSA records for metformin with safety monitoring results
get_pipsGet Paediatric Investigation Plans (PIPs) - pediatric development requirements.
Parameters:
active_substance (string, optional): Active substance name
therapeutic_area (string, optional): Therapeutic area
decision_type (string, optional): Type of decision
year (number, optional): Decision year (1995-2026)
limit (number, optional): Maximum results (default: 100, max: 10000)
Example:
{
"method": "get_pips",
"therapeutic_area": "diabetes",
"year": 2024
}Returns: PIPs for diabetes approved in 2024
get_herbal_medicinesGet herbal medicine assessments.
Parameters:
substance (string, optional): Herbal substance or botanical name
therapeutic_area (string, optional): Therapeutic area
limit (number, optional): Maximum results (default: 50, max: 10000)
Example:
{
"method": "get_herbal_medicines",
"substance": "valerian"
}Note: EMA does not currently publish herbal medicine data as a JSON endpoint. This method returns empty results until a valid endpoint is identified.
get_article58_medicinesGet medicines for use outside EU (Article 58) - positive scientific opinions for non-EU countries.
Parameters:
active_substance (string, optional): Active substance name
medicine_name (string, optional): Medicine name
limit (number, optional): Maximum results (default: 50, max: 10000)
Example:
{
"method": "get_article58_medicines",
"active_substance": "artemether"
}Note: EMA does not currently publish Article 58 data as a JSON endpoint. This method returns empty results until a valid endpoint is identified.
search_epar_documentsSearch EPAR (European Public Assessment Report) documents with translations.
Parameters:
medicine_name (string, optional): Medicine name to filter
document_type (string, optional): Document type (e.g., "EPAR - Summary for the public")
language (string, optional): Language code (e.g., "en", "fr", "de")
limit (number, optional): Maximum results (default: 100, max: 10000)
Example:
{
"method": "search_epar_documents",
"medicine_name": "Ozempic",
"document_type": "Summary for the public"
}Returns: EPAR documents for Ozempic with public summaries and translations
search_all_documentsSearch all EMA documents (complete repository).
Parameters:
search_term (string, optional): Search in title or document_title
document_type (string, optional): Document type
category (string, optional): Document category
limit (number, optional): Maximum results (default: 100, max: 10000)
Example:
{
"method": "search_all_documents",
"search_term": "guideline"
}Returns: All EMA documents matching "guideline"
search_non_epar_documentsSearch non-EPAR documents (guidelines, procedures, etc.).
Parameters:
search_term (string, optional): Search in title or document_title
document_type (string, optional): Document type
limit (number, optional): Maximum results (default: 100, max: 10000)
Example:
{
"method": "search_non_epar_documents",
"search_term": "procedure"
}Returns: Non-EPAR documents matching "procedure"
All methods return a consistent format:
{
"total_count": 3,
"results": [...],
"source": "EMA Medicines Database",
"source_url": "https://www.ema.europa.eu/...",
"last_updated": "2025-12-11T10:30:00.000Z"
}The server accesses 14 EMA JSON endpoints organized into 4 categories:
Medicines Database: medicines-output-medicines_json-report_en.json (2,641+ medicines)
Orphan Designations: medicines-output-orphan_designations-json-report_en.json
Supply Shortages: shortages-output-json-report_en.json
Referrals: referrals-output-json-report_en.json
Post-Authorization: medicines-output-post_authorisation_json-report_en.json
Herbal Medicines: (placeholder - no JSON endpoint available)
DHPCs: dhpc-output-json-report_en.json (160+ records)
PSUSAs: medicines-output-periodic_safety_update_report_single_assessments-output-json-report_en.json (2,508+ records)
PIPs: medicines-output-paediatric_investigation_plans-output-json-report_en.json (3,229+ records)
EPAR Documents: documents-output-epar_documents_json-report_en.json
All Documents: documents-output-json-report_en.json
Non-EPAR Documents: documents-output-non_epar_documents_json-report_en.json
Article 58: (placeholder - no JSON endpoint available)
Update Schedule: Twice daily (06:00 and 18:00 CET)
Document Format: Document endpoints return {data: [...]} format, others return [...] array format
EMA Term | FDA Equivalent |
EPAR (European Public Assessment Report) | Drug Label / Approval Package |
Active Substance | Active Ingredient |
Orphan Designation | Orphan Drug Designation |
PRIME (Priority Medicines) | Breakthrough Therapy |
Conditional Approval | Accelerated Approval |
Referral | Safety Review |
Marketing Authorisation Holder | Sponsor/Applicant |
Medicinal Product | Drug Product |
Unified tool for EMA (European Medicines Agency) drug information lookup. Provides access to EU drug approvals, EPARs, orphan designations, supply shortages, and regulatory information through EMA's public JSON API.
| Name | Required | Description | Default |
|---|---|---|---|
| method | Yes | The operation to perform: search_medicines (search EU approved drugs), get_medicine_by_name (get specific medicine), get_orphan_designations (EU orphan drugs), get_supply_shortages (medicine shortages), get_referrals (EU safety reviews), get_post_auth_procedures (label updates), get_dhpcs (safety communications), get_psusas (periodic safety reports), get_pips (paediatric plans), get_herbal_medicines (herbal assessments), get_article58_medicines (non-EU use), search_epar_documents (EPAR docs), search_all_documents (all EMA docs), search_non_epar_documents (non-EPAR docs) | |
| active_substance | No | For search_medicines, get_supply_shortages: Active substance name (e.g., "semaglutide", "adalimumab") | |
| therapeutic_area | No | For search_medicines, get_orphan_designations: Therapeutic area or disease (e.g., "diabetes", "cancer", "multiple sclerosis") | |
| status | No | For search_medicines: Medicine status filter. For get_supply_shortages: "ongoing" or "resolved" | |
| orphan | No | For search_medicines: Filter for orphan medicines only | |
| prime | No | For search_medicines: Filter for PRIME (priority) medicines only | |
| biosimilar | No | For search_medicines: Filter for biosimilar medicines only | |
| conditional_approval | No | For search_medicines: Filter for conditionally approved medicines | |
| limit | No | Maximum number of results to return (default: 100 for medicines, 50 for other methods) | |
| name | No | For get_medicine_by_name: Medicine trade name to search (e.g., "Ozempic", "Wegovy", "Humira") | |
| year | No | For get_orphan_designations, get_referrals: Filter by year (e.g., 2024, 2023) | |
| safety | No | For get_referrals: Filter for safety-related referrals (true=Yes, false=No) | |
| medicine_name | No | For get_supply_shortages, get_post_auth_procedures: Medicine name to filter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool accesses EMA's public JSON API, which hints at read-only behavior, but doesn't explicitly state if it's read-only, requires authentication, has rate limits, or describes error handling. For a tool with 13 parameters and no annotations, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded and efficiently structured in two sentences: the first states the unified purpose, and the second lists the accessible information types and API source. Every sentence earns its place without redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (13 parameters, no output schema, no annotations), the description is adequate but incomplete. It covers the purpose and scope well but lacks details on behavioral traits, return values, or usage nuances. With no output schema, it should ideally hint at response formats, but it doesn't, leaving gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema, such as explaining relationships between methods and parameters. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('lookup', 'provides access to') and resources ('EMA drug information', 'EU drug approvals, EPARs, orphan designations, etc.'). It distinguishes this as a unified tool for EMA's public JSON API, making its scope explicit even without sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for EMA-related drug information queries but provides no explicit guidance on when to use specific methods or alternatives. Without sibling tools, it doesn't need to differentiate, but it lacks context on prerequisites or optimal use cases for the various operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'ema_info' has a clearly defined and distinct purpose for EMA drug information lookup.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'ema_info' follows a clear and appropriate pattern for its function.
A single tool is too few for the broad scope implied by the description, which covers multiple aspects like drug approvals, EPARs, orphan designations, supply shortages, and regulatory information. This thin surface likely requires agents to handle complex queries within one tool, which is suboptimal for typical MCP server design.
The tool set is severely incomplete for the EMA domain. While 'ema_info' provides a unified lookup, there are obvious gaps such as separate tools for different resource types (e.g., approvals vs. shortages) or operations (e.g., search vs. get details), which could lead to agent confusion or inefficiency in handling specific queries.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Citation-backed regulatory intelligence tools for explicit multi-jurisdiction packs
Regulatory Catalysts MCP — high-value biotech regulatory calendar events (keyless).
EU regulatory compliance data: 17 regulations, deadlines, enforcement actions. EU-hosted.
FDA drug approvals, 510(k) device clearances, recalls and adverse-event reports.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/openpharma-org/ema-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
