Lumis
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_taxonomyA | Get the Lumis value chain taxonomy — phases, areas, and available knowledge categories. Call this first to understand what domains Lumis covers and how knowledge is organized. |
| search_knowledgeA | Search the Lumis knowledge base across the life sciences value chain. Foundation knowledge (org strategy, regulatory, terminology) is always included. Use phase and area to narrow scope. Args: query: Natural language search query phase: Value chain phase — 'discovery', 'clinical', 'commercialization', 'foundation', or 'all' area: Area within phase — e.g. 'crm', 'safety-pv', 'regulated-content', 'market-access', or 'all' category: Knowledge category — 'modules', 'decision-trees', 'gotchas', 'country-rules', 'validation-rules', 'terminology', 'org-strategy', or 'all' limit: Maximum results to return (default 5) |
| get_module_mappingA | Get the target platform equivalent for a source module. Args: source_module: The source module name (e.g. 'CLM', 'Legacy Events', 'AE Reporting') area: Which area to search — 'crm', 'safety-pv', 'regulated-content', etc. (default 'crm') |
| get_gotchasC | Get non-obvious pitfalls and gotchas for a module, country, or domain area. Args: module: Filter by module name (optional) country: Filter by country (optional) phase: Value chain phase filter (default 'all') area: Area filter — 'crm', 'safety-pv', etc. (default 'all') |
| traverse_decision_treeB | Walk a decision tree given user inputs to produce a recommendation. Args: tree_name: Name of the decision tree (e.g. 'module-selection', 'migration-path', 'org-strategy') inputs: JSON string of input parameters for the tree phase: Value chain phase filter (default 'all') area: Area filter (default 'all') |
| get_country_rulesA | Get regulatory and configuration rules for a specific country. Foundation rules (GDPR, APPI, data residency) are always included. Use area to add domain-specific rules (e.g. 'safety-pv' for adverse event reporting timelines). Args: country: Country name or code (e.g. 'Germany', 'DE', 'Japan') module: Optional module filter (e.g. 'Sample Management', 'AE Reporting') phase: Value chain phase filter (default 'all') area: Area filter (default 'all') |
| run_validationB | Run a validation rule or find rules matching a reported symptom. Args: rule_id: Specific rule ID to run (optional) symptom: User-reported problem to match against rules (optional) area: Area to validate — 'crm', 'safety-pv', etc. (default 'crm') |
| get_terminologyB | Look up correct vs incorrect terminology to avoid hallucinations. Args: term: Term to look up (e.g. 'CLM', 'Approved Email', 'ICSR', 'CIOMS') |
| get_agent_workflowA | Get the workflow, phases, and checklists for a specific Lumis agent. Args: agent: Agent name — 'migration', 'implementation', 'audit', or 'operations' |
| assess_migration_readinessB | Run a migration readiness assessment for any commercialization area. Args: source_platform: Current platform (e.g. 'Legacy CRM', 'Argus Safety', 'Veeva Vault') modules_in_use: Comma-separated list of modules currently in use country_count: Number of countries in scope user_count: Approximate number of users area: Commercialization area — 'crm', 'safety-pv', 'regulated-content' (default 'crm') |
| plan_multi_country_rolloutA | Plan a wave-based multi-country rollout for any commercialization area. Args: country_count: Total countries in scope modules: Comma-separated list of modules to deploy regions: Comma-separated regions in scope (e.g. 'EU, Americas, APAC, LATAM') includes_us: Whether the US is in scope (adds regulatory complexity) includes_japan: Whether Japan is in scope (requires standalone wave) area: Commercialization area — 'crm', 'safety-pv', 'regulated-content' (default 'crm') |
| compare_entitiesA | Compare two entities side-by-side — countries, modules, regulatory frameworks, or any knowledge base entries. Args: entity_a: First entity to compare (e.g. 'Germany', 'CLM', 'Argus') entity_b: Second entity to compare (e.g. 'France', 'Events', 'Vault Safety') dimension: Optional focus dimension (e.g. 'sample rules', 'field mapping', 'regulatory') phase: Value chain phase filter (default 'all') area: Area filter (default 'all') |
| plan_system_validationA | Plan a computer system validation (CSV/CSA) for a life sciences system. Returns applicable regulations, methodology recommendation, GAMP classification, deliverables list, effort estimate, gap assessment areas, and decision tree guidance. This tool supports planning for 21 CFR Part 11, EU Annex 11, GAMP 5, and related regulatory requirements across CRM, clinical, safety, and manufacturing systems. Args: system_name: Name of the system being validated (e.g. 'Salesforce CRM', 'Veeva Vault', 'SAP QM') system_type: Type of system — 'saas', 'cots', 'configured', 'custom', 'hybrid' platform: Platform vendor if applicable (e.g. 'Salesforce', 'Veeva', 'SAP', 'Oracle') regulatory_geography: Jurisdiction — 'US', 'EU', 'Japan', 'Global', 'WHO' (default 'US') gxp_context: GxP context — 'GMP', 'GCP', 'GLP', 'GPvP', 'GDP', or comma-separated combo modules_in_use: Comma-separated modules (e.g. 'Sample Management, Events, Consent') has_mobile: Whether mobile/offline is in scope (adds validation complexity) has_integrations: Whether system integrations are in scope has_custom_code: Whether custom code (e.g. Apex, custom middleware) exists user_count: Approximate number of users country_count: Number of countries in scope |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Most tools have clearly distinct jobs: retrieval (get_country_rules, get_terminology, get_module_mapping, get_gotchas), action-oriented planning (assess_migration_readiness, plan_multi_country_rollout, plan_system_validation), and generic utilities (search_knowledge, compare_entities, traverse_decision_tree). The main blur is that search_knowledge exposes category filters ('country-rules', 'gotchas', 'terminology', 'decision-trees') that substantially overlap with four specialized tools, so an agent could plausibly reach for the wrong one. Descriptions suggest the specialized tools return structured/filtered output, which mitigates but does not eliminate the overlap.
All 13 names follow a consistent snake_case verb_noun pattern (get_*, run_*, search_*, traverse_*, assess_*, plan_*, compare_*). Verbs are chosen meaningfully rather than arbitrarily, and there are no mixed conventions or versioned/suffixed outliers.
Thirteen tools is squarely in the well-scoped range for a knowledge-plus-advisory server, with each tool mapping to a distinct knowledge category or planning task. Nothing feels like filler, and the surface is not so large that selection becomes a burden.
The read-only advisory surface is well covered: taxonomy discovery, knowledge search, rules/terminology/gotchas retrieval, decision trees, comparison, and three substantive planning tools (migration readiness, rollout waves, CSV). Minor gaps exist — analytical tools default to commercialization areas ('crm', 'safety-pv', 'regulated-content') with no equivalent depth for discovery/clinical, and there is no way to enumerate available decision trees or agent workflows other than via get_taxonomy/get_agent_workflow. These are workable-around rather than blocking.