Overview
What is Heor Agent?
Heor Agent is an AI-powered Health Economics and Outcomes Research (HEOR) agent that operates as a Model Context Protocol (MCP) server. It automates literature review across 44 data sources, risk of bias assessment (RoB 2, ROBINS-I, AMSTAR-2), EQ-5D value set impact estimation, state‑of‑the‑art cost‑effectiveness modelling, HTA dossier preparation for NICE/EMA/FDA/IQWiG/HAS/EU JCA, and maintains a persistent project knowledge base. It is built for pharmaceutical, biotech, CRO, and medical affairs teams who need rigorous, auditable HEOR workflows.
How to use Heor Agent?
Install via npx heor-agent-mcp (Node ≥20 required). Configure your MCP host (Claude Desktop, Claude Code, Cursor, Continue, Cline) by adding the server to the client’s MCP settings file. For Claude Code, run claude mcp add heor-agent -- npx heor-agent-mcp; for Claude Desktop, edit claude_desktop_config.json. Hosted options are also available: a ChatGPT GPT (type /heor) and a Web UI (bring your own Anthropic API key). After configuration, paste prompts to run literature searches, IRB reviews, or HTA dossier pipelines.
Key features of Heor Agent
- 45 MCP tools spanning HEOR, RWE, and pharmacovigilance
- Literature search across 44 data sources with PRISMA audit trail
- Risk of bias assessment (RoB 2, ROBINS-I, AMSTAR-2)
- Cost‑effectiveness modelling (Markov, PartSA, PSA, OWSA, CEAC, EVPI)
- HTA dossier drafting for NICE, EMA, FDA, IQWiG, HAS, EU JCA
- Persistent project knowledge base with Obsidian‑compatible wiki
- AI transparency disclosure aligned with ISPOR ELEVATE-GenAI
Use cases of Heor Agent
- Conduct a systematic literature review with parallel source search and PICO‑based screening
- Perform cost‑effectiveness analysis and budget impact modelling for a new therapy
- Draft a complete HTA dossier for NICE or EU JCA submission
- Classify a planned study under EMA pharmacovigilance regulations (GVP modules)
- Maintain a living evidence knowledge base with automatic gap analysis and orchestration
FAQ from Heor Agent
What runtime or dependencies are required?
Node.js version 20 or higher is required. The server is installed via npx and runs on stdio by default; an HTTP mode is also available.
Can I use Heor Agent without installing anything?
Yes. A hosted ChatGPT GPT (requires ChatGPT Plus/Team) and a Web UI (bring your own Anthropic API key) are available, both running the full toolset.
What tools are included?
The server provides 45 tools, including literature_search, risk_of_bias, cost_effectiveness_model, hta_dossier, pv_classify, utility_value_set, and many more for workflow orchestration and evidence management.
How does Heor Agent handle AI transparency?
Many tools accept an ai_disclosure_level parameter (off/standard/submission). HTA/regulatory tools default to "submission"; analysis tools default to "standard". A global environment variable HEORAGENT_DISCLOSURE_LEVEL can override the default.
Does the server support pharmacovigilance classification?
Yes. The pv_classify tool classifies a planned study into its EMA pharmacovigilance regulatory category (e.g., PASS, PAES, RMP Annex 4) and returns the matching GVP module, ENCePP template ID, and submission obligations.
