Heor Agent
@neptun2000
About Heor Agent
No overview available yet
Basic information
Category
AI & Agents
License
MIT
Runtime
node
Transports
stdio
Publisher
neptun2000
Submitted by
Michael Naumov
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"heor-agent": {
"command": "npx",
"args": [
"heor-agent-mcp"
]
}
}
}Tools
15Search PubMed, ClinicalTrials.gov, bioRxiv/medRxiv, ChEMBL, FDA Orange Book, FDA Purple Book, enterprise sources (Embase, ScienceDirect, Cochrane, Citeline, Pharmapendium, Cortellis), HTA cost reference sources (CMS NADAC, PSSRU, NHS National Cost Collection, BNF, PBS Schedule), LATAM sources (DATASUS, CONITEC, ANVISA, PAHO, IETS, FONASA), APAC sources (HITAP), and HTA appraisal/guidance sources (NICE TAs, CADTH CDR/pCODR, ICER, PBAC PSDs, G-BA AMNOG, HAS Transparency Committee, IQWiG, AIFA, TLV Sweden, INESSS Quebec) for evidence on a drug or indication. Returns structured results including HTA precedents and appraisal decisions with a full audit trail suitable for HTA submissions.
Build a cost-utility analysis (ICER, QALY, PSA, sensitivity analysis) for a drug vs comparator. Follows ISPOR good practice guidelines and NICE reference case. Includes probabilistic sensitivity analysis (PSA), one-way sensitivity, and cost-effectiveness acceptability curve (CEAC).
Structure evidence into HTA body-specific submission format (NICE STA, EMA, FDA, IQWiG, HAS, EU JCA, or Global Value Dossier). Produces draft sections with gap analysis and auto-GRADE evidence quality tables. Accepts output from literature_search and cost_effectiveness_model.
Search a project's knowledge base (raw/ and wiki/) for text matches. Returns file paths with line numbers and snippets. Use this to find previously-retrieved literature, model runs, and compiled wiki content without re-querying external APIs.
Read a file from a project's raw/ or wiki/ tree. Path is relative to project root. Only raw/ and wiki/ subtrees accessible.
Write a file to the project's wiki/ tree. Path MUST start with 'wiki/' and end with '.md'. Use this to compile/organize evidence from raw/ files into a structured knowledge base. Supports Obsidian-style [[wikilinks]].
Initialize a new HEOR project workspace with directory skeleton and project.yaml metadata. Idempotent — returns existing project if already created. Required before using the `project` parameter in other tools.
Analyze literature search results to build an evidence network map. Extracts intervention-comparator pairs from titles and abstracts, constructs a treatment comparison network, and assesses NMA (network meta-analysis) feasibility. Pass the results array from a prior literature_search call.
Compute indirect treatment comparisons using the Bucher method (single common comparator) or frequentist network meta-analysis (full network). Requires user-supplied effect sizes (point estimates + 95% CI) from published trials. Supports mean differences (MD) and ratio measures (OR, RR, HR). Auto-selects method based on network structure, or user can specify.
Estimate the total budget impact of adopting a new intervention over 1-5 years. Follows ISPOR Budget Impact Analysis good practice guidelines (Mauskopf 2007, Sullivan 2014). Computes year-by-year net cost to payer, including market share uptake, treatment displacement, and population growth.
⚠️ EXPERIMENTAL / orientation-only. Approximate population-adjusted indirect comparison using summary-level statistics (mean, SD per covariate). True MAIC/STC per NICE DSU TSD 18 requires individual patient data (IPD) for one trial. This tool inflates the SE of a Bucher indirect comparison based on covariate imbalance (MAIC-style ESS penalty) and applies a simple linear adjustment based on standardized mean differences (STC-style). Point estimates should be interpreted as approximate — not submission-ready. For a definitive analysis, use IPD with an outcome regression model.
⚠️ EXPERIMENTAL. Fit parametric survival distributions (Exponential, Weibull, Log-logistic, Log-normal, Gompertz) to Kaplan-Meier SUMMARY data. Returns AIC/BIC model comparison for orientation. IMPORTANT: this fits to KM step data (time, survival proportion, n_at_risk), not individual patient-level events/censoring times. Results are approximate compared to true MLE on IPD. For NICE DSU TSD 14 compliant survival modeling, use IPD with flexsurv (R) or equivalent. Provide n_at_risk on each KM row for better fits — otherwise a default sample size is assumed.
Screen literature search results using PICO criteria. Scores each abstract by relevance to the research question, classifies study design, and returns a ranked shortlist with inclusion/exclusion decisions and reasons. Pass the results array from a prior literature_search call (use output_format='json'). Follows Cochrane Handbook Chapter 4 screening methodology.
Assess risk of bias for a set of studies using the appropriate Cochrane instrument: RoB 2 (RCTs), ROBINS-I (observational studies), or AMSTAR-2 (systematic reviews/meta-analyses). Instrument is auto-detected from study_type or can be specified. Judgments are inferred from abstract text — domains without sufficient reporting are marked Unclear. Returns a per-study table and a rob_results object to pass to hta_dossier_prep for evidence-based GRADE assessment.
Validate URLs by making HEAD requests and checking HTTP status codes. Returns categorization: working (200), browser_only (403 from bot-blocking sites that work in browsers), broken (404/410), or timeout/error. ALWAYS use this before presenting reference links to users — broken links destroy trust. Pass all URLs you plan to cite.
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.
More AI & Agents MCP servers
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
Intervals.icu MCP Server
mvilanovaModel Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.
欢迎来到 智言平台
Shy2593666979AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。
Comments