Skip to main content
Glama

gapup-mcp

by io.github.getgapup

clinical_pharma_intel

Read-only

Clinical and pharmaceutical intelligence for biotech analysts, healthcare fund managers, pharma BD teams, catalyst-driven hedge funds and health journalists. Aggregates live data across five modes: • trials — active/completed clinical trials (ClinicalTrials.gov v2 + EU CTR in parallel, 450k+ records) • pipeline — full pipeline by sponsor: trial count by phase + top indications • approvals — FDA drug label approvals + mechanism of action (OpenFDA) • recalls — FDA enforcement recalls classified by severity (Class I/II/III) • adverse_events — FAERS aggregated reactions: top 10 reactions + serious%

Signal detection (P0/P1/P2): P0 if Class I recall OR trial terminated for safety reason P1 if serious adverse events >30% OR ≥3 recalls in 12 months P2 otherwise (standard monitoring)

All sources are public and keyless. Optional env OPENFDA_API_KEY raises daily quota from 1,000 to 120,000 requests. SLA: ≤16s p95 (parallel fetch, 8s budget per source). Cache: 6h trials, 24h approvals, 12h recalls, 6h adverse events.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoAnalysis mode. Default "trials". trials=clinical trials, pipeline=sponsor overview, approvals=FDA approvals, recalls=enforcement, adverse_events=FAERS
asyncNoIf true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
phaseNoFilter trials by phase (1/2/3/4/NA). Only applies to modes trials and pipeline.
queryYesDrug name, indication, sponsor or molecule (e.g. "atezolizumab", "metastatic NSCLC", "Roche", "semaglutide")
countryNoISO 2-letter country code to filter trial sites (e.g. US, FR, DE).
max_resultsNoMaximum number of results to return. Default 20.
status_filterNoFilter trials by status. Only applies to modes trials and pipeline.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYes
queryYes
statusYes
trialsNo
recallsNo
signalsYes
sourcesYes
pipelineNo
approvalsNo
quality_scoreYes
adverse_eventsNo

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag readOnlyHint=true and destructiveHint=false, and the description adds substantial operational behavior: parallel fetching with source-level budgets, SLA p95 ≤16s, cache durations per data type, keyless access, and optional OPENFDA_API_KEY quota increase. It also describes signal prioritization logic (P0/P1/P2) that governs how results are interpreted, far exceeding annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with bullets and sections (modes, signal detection, operational details). Every sentence contributes substantive information, and the front-loaded purpose sentence ensures quick understanding. Slight verbosity in listing audiences and operational stats is justified given tool complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 7 parameters, 5 modes, and an output schema present, the description fully covers what the tool does, data sources, caching, SLA, rate limits, and basic signal logic. It does not need to describe return values because the output schema exists, and all essential operational context is provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions already explain each parameter (mode, query, phase, etc.), giving baseline 3. The description enhances this by detailing what each mode returns (e.g., '450k+ records', 'trial count by phase + top indications', 'serious%') and clarifying the meaning of status_filter and phase in context, adding value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool aggregates live clinical and pharmaceutical data across five named modes (trials, pipeline, approvals, recalls, adverse_events), each with concrete sources and outputs. The verb 'aggregates' combined with the enumerated resource makes the purpose specific and distinguishes it from generic search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description identifies target audiences (biotech analysts, fund managers, etc.) and lists the five modes, implying when each mode might be used. However, it does not explicitly contrast with sibling tools like clinical_evidence_briefer or provide 'when not to use' guidance, leaving usage context partially implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All gapup-mcp toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.4/5.0
Disambiguation1/5

Over 50 tools share the identical template 'Gapup agent-payable C-suite expertise' with similar French descriptions and reference cases, making their boundaries indistinguishable. Clusters like competitor_intel, competitive_deep_dive, competitor_moves, competitor_profiles, competitor_pricing_radar, competitor_pricing_scrape, and competitor_recommendations heavily overlap in purpose.

Naming Consistency1/5

Names are chaotic: mix of French and English, snake_case and camelCase, verb_noun, noun, and adjective forms with no uniform pattern. Examples like 'bp_narratif', 'content_enrichment', 'ai_governance_full_report_async', and 'job_result' show no coherent naming convention.

Tool Count1/5

271 tools is far beyond any reasonable MCP server scope, creating an overwhelming selection burden for agents. This count vastly exceeds the 25+ threshold for 'too many' and makes navigation impractical.

Completeness2/5

While the server covers many business domains, it lacks lifecycle operations (e.g., no update/delete tools for the deliverables it generates) and the input specifications are vague ('documented case fields' without documentation), creating functional dead ends. The sheer breadth does not compensate for these gaps.

Resources