Agent Interface

This page provides structured guidance for AI agents interacting with PharmaTools.AI. The platform offers a suite of AI tools for compliance validation, medical writing, patient communication, and research workflows.

Constraints

MedCheckr and RefCheckr output is input to a compliance decision, not the decision itself. Do not treat a verdict as final without human review.
Do not chain compliance tools without human review between steps.
PLS Generator and LLMentor rewrites must not add claims, indications, or outcomes not present in the source text.
Redacta is not a guarantee of anonymisation. Treat output as a first pass requiring human verification before sharing or processing.
Do not reuse or cache compliance verdicts across different claims or contexts.

Tool Registry

A. Compliance & Validation

MedCheckr — Validate promotional medical claims against selected codes of practice with clause-level analysis and suggested rewrites.

RefCheckr — Verify whether medical claims are accurately supported by cited references. Returns evidence support verdicts, highlighted source passages, and compliance assessments.

Redacta — Pseudonymise clinical text by detecting and replacing patient identifiers with standardised tokens. Preserves clinical meaning and clinician names. Returns redacted document and redaction report.

B. Medical Writing & Transformation

LLMentor — Adapt medical or scientific text for different audiences.

PLS Generator — Convert complex medical abstracts into plain language summaries.

AI Jargon Buster — Identify and replace medical jargon with accessible alternatives.

Pharmonym — Convert between brand and generic drug names with international brand lookup, drug classification, dosage, side effects, and safety data.

C. Patient Communication

Patiently AI — Generate patient-friendly explanations of conditions, treatments, and procedures.

D. Research & Evidence

PubCrawl — MCP server providing real-time access to PubMed, FDA drug labelling, UK medicines data, and ClinicalTrials.gov. Returns structured, verified citations and data.

BiomarkerFinder — Discover biomarkers for a given disease using Open Targets data. Supports cross-disease comparison, network visualisation, and export.

Trial Name Generator — Generate structured acronyms and names for clinical trials.

Case Study Creator — Generate structured pharma business case study drafts for launches, field medical, biomarker adoption, or access strategies. Not for clinical patient cases.

PosterLens — iOS app that extracts and analyses scientific conference posters using OCR. Generates summaries, enables interactive Q&A, and suggests related research.

Media Monitoring Hub — Ingest news feeds, classify by topic and sentiment, and generate structured briefing summaries for communications teams. Schema-bound outputs with confidence scoring.

SideEffectViz — Visualise and analyse medication side effect patterns using FDA FAERS data, ML clustering, and PCA. Interactive network graphs reveal drug-adverse event relationships.

The registry is evolving. Additional tool schemas and endpoints may be exposed over time.

Tool Schemas

MedCheckr

Description

Validate promotional medical claims against one or more codes of practice. Returns a verdict, identified issues, relevant clauses, and a suggested compliant alternative where applicable.

Input

claim (string, required) — the promotional claim to validate
selected_codes (array of strings, required) — code identifiers to check against
context (string, optional) — additional context for the claim

Output

verdict (string) — compliant | non_compliant | review_required
issues (array of objects) — identified problems
relevant_clauses (array of strings) — applicable code clauses
suggested_alternative (string) — a compliant rewrite

RefCheckr

Description

Verify whether medical claims are accurately supported by cited references. Supports verification against uploaded PDFs and reference libraries, with optional compliance assessment against the ABPI Code of Practice.

Input

claim (string, required) — the claim or text to verify
references (array of strings, required) — reference identifiers or uploaded document IDs
mode (string, optional) — verification | compliance | discovery

Output

verdict (string) — strong_support | partial_support | overclaim | not_supported | contradicted
matched_passages (array of objects) — source text, page location, relevance
compliance (object, optional) — ABPI clause alignment, risk rating, suggested rewrite
notes (string) — additional context or caveats

LLMentor

Description

Adapt medical or scientific text for a specified target audience. Supports tone control and returns readability metrics alongside the rewritten text.

Input

source_text (string, required) — the text to adapt
target_audience (string, required) — e.g. patient, HCP, payer, general_public
tone (string, optional) — e.g. formal, conversational, neutral

Output

rewritten_text (string) — the adapted text
readability_shift (string) — summary of readability changes
notes (string) — editorial notes or caveats

PLS Generator

Description

Convert complex medical abstracts or source text into a plain language summary with a title and key points.

Input

source_text (string, required) — the abstract or source material
audience (string, optional) — target reader group
word_limit (integer, optional) — maximum word count

Output

summary_title (string) — a plain language title
plain_language_summary (string) — the simplified text
key_points (array of strings) — main takeaways

PubCrawl

Description

MCP server providing AI assistants with real-time access to PubMed, FDA drug labelling (DailyMed/OpenFDA), UK medicines data (eMC), and ClinicalTrials.gov. Returns structured, verified citations and data — real PMIDs, DOIs, and parsed content. Does not generate summaries.

Input

query (string, required) — natural language research question or search terms
source (string, optional) — PubMed | DailyMed | eMC | ClinicalTrials.gov
date_range (string, optional) — e.g. "2020-2026"
max_results (integer, optional) — number of results to return

Output

results (array of objects) — PMIDs, DOIs, authors, journal, parsed abstract sections
total_found (integer) — total matching records

Manifest

API endpoints are not yet available. PubCrawl is accessible as an MCP server. Other integration routes may be offered on request. Subset of tools shown below; see registry above for the full list.

{
  "platform": "pharmatools.ai",
  "version": "1.0",
  "description": "AI tools for pharmaceutical compliance, medical writing, patient communication, and research.",
  "tool_categories": [
    "compliance_validation",
    "medical_writing",
    "patient_communication",
    "research_evidence"
  ],
  "tools": [
    {
      "name": "MedCheckr",
      "category": "compliance_validation",
      "input_schema": {
        "claim": { "type": "string", "required": true },
        "selected_codes": { "type": "array", "items": "string", "required": true },
        "context": { "type": "string", "required": false }
      },
      "output_schema": {
        "verdict": { "type": "string", "enum": ["compliant", "non_compliant", "review_required"] },
        "issues": { "type": "array", "items": "object" },
        "relevant_clauses": { "type": "array", "items": "string" },
        "suggested_alternative": { "type": "string" }
      }
    },
    {
      "name": "RefCheckr",
      "category": "compliance_validation",
      "input_schema": {
        "claim": { "type": "string", "required": true },
        "references": { "type": "array", "items": "string", "required": true },
        "mode": { "type": "string", "enum": ["verification", "compliance", "discovery"], "required": false }
      },
      "output_schema": {
        "verdict": { "type": "string", "enum": ["strong_support", "partial_support", "overclaim", "not_supported", "contradicted"] },
        "matched_passages": { "type": "array", "items": "object" },
        "compliance": { "type": "object" },
        "notes": { "type": "string" }
      }
    },
    {
      "name": "LLMentor",
      "category": "medical_writing",
      "input_schema": {
        "source_text": { "type": "string", "required": true },
        "target_audience": { "type": "string", "required": true },
        "tone": { "type": "string", "required": false }
      },
      "output_schema": {
        "rewritten_text": { "type": "string" },
        "readability_shift": { "type": "string" },
        "notes": { "type": "string" }
      }
    },
    {
      "name": "PLS Generator",
      "category": "medical_writing",
      "input_schema": {
        "source_text": { "type": "string", "required": true },
        "audience": { "type": "string", "required": false },
        "word_limit": { "type": "integer", "required": false }
      },
      "output_schema": {
        "summary_title": { "type": "string" },
        "plain_language_summary": { "type": "string" },
        "key_points": { "type": "array", "items": "string" }
      }
    },
    {
      "name": "PubCrawl",
      "category": "research_evidence",
      "access": "mcp_server",
      "description": "Real-time access to PubMed, FDA drug labelling, UK medicines data, and ClinicalTrials.gov. Returns structured, verified citations.",
      "input_schema": {
        "query": { "type": "string", "required": true },
        "source": { "type": "string", "enum": ["PubMed", "DailyMed", "eMC", "ClinicalTrials.gov"], "required": false },
        "date_range": { "type": "string", "required": false },
        "max_results": { "type": "integer", "required": false }
      },
      "output_schema": {
        "results": { "type": "array", "items": "object" },
        "total_found": { "type": "integer" }
      }
    },
    {
      "name": "Pharmonym",
      "category": "medical_writing",
      "input_schema": {
        "drug_name": { "type": "string", "required": true }
      },
      "output_schema": {
        "brand_names": { "type": "array", "items": "string" },
        "generic_name": { "type": "string" },
        "classification": { "type": "string" },
        "common_uses": { "type": "array", "items": "string" },
        "dosage": { "type": "string" },
        "side_effects": { "type": "object" },
        "international_names": { "type": "object" },
        "safety_warnings": { "type": "array", "items": "string" }
      }
    },
    {
      "name": "Patiently AI",
      "category": "patient_communication",
      "input_schema": {
        "topic": { "type": "string", "required": true },
        "detail_level": { "type": "string", "required": false },
        "audience": { "type": "string", "required": false }
      },
      "output_schema": {
        "explanation": { "type": "string" },
        "reading_level": { "type": "string" },
        "notes": { "type": "string" }
      }
    }
  ]
}

Examples

MedCheckr

Request

{
  "tool": "MedCheckr",
  "input": {
    "claim": "Our drug reduces hospitalisation rates by 50% compared to standard care.",
    "selected_codes": ["ABPI_2024"],
    "context": "Promotional leaflet for UK healthcare professionals."
  }
}

Response

{
  "verdict": "non_compliant",
  "issues": [
    {
      "type": "unsupported_comparative_claim",
      "detail": "The 50% reduction claim requires a direct reference to a published comparative study. No source citation was provided."
    }
  ],
  "relevant_clauses": [
    "ABPI Clause 6.2 — Substantiation of claims",
    "ABPI Clause 7.4 — Comparative statements"
  ],
  "suggested_alternative": "In a Phase III trial (Smith et al., 2024), the treatment group showed a statistically significant reduction in hospitalisation rates compared to standard care (HR 0.50; 95% CI 0.38–0.66)."
}

LLMentor

Request

{
  "tool": "LLMentor",
  "input": {
    "source_text": "The pharmacokinetic profile of the compound demonstrates nonlinear absorption kinetics with a bioavailability of approximately 62% following oral administration, and a terminal half-life of 14.2 hours.",
    "target_audience": "patient",
    "tone": "conversational"
  }
}

Response

{
  "rewritten_text": "When you take this medicine by mouth, your body absorbs about 62% of it. It stays active in your system for roughly 14 hours before your body clears it.",
  "readability_shift": "Flesch-Kincaid grade level reduced from 16.1 to 7.3. Technical pharmacokinetic terminology replaced with everyday language.",
  "notes": "The term 'nonlinear absorption kinetics' was omitted from the patient version as it requires specialist knowledge to interpret. The clinical significance is preserved in simplified form."
}

Access

API and agent access may be available on request. Some tools are accessible via MCP server; others are planned for REST API exposure. The integration method may vary by tool.

Integrations can be scoped by tool and use case.

To request access, contact info@pharmatools.ai with your use case, the tools you intend to use, and expected call volume.

Outputs should be reviewed by qualified human users, particularly in regulated environments.