Theta Health

Installation

TypingMindClaude DesktopCursorVS CodeWindsurf

TypingMind

Prerequisites:

Node.js 18+

Copy

{
  "mcpServers": {
    "Theta Health": {
      "command": "npx",
      "args": [
        "-y",
        "theta_health_mcp"
      ]
    }
  }
}

Available Tools

• get_genetic_data

  Retrieve variant information by rsid, with optional lookup of nearby related variants.

• get_health_indicator

  Get user health indicator data. This is the primary and most powerful tool for retrieving health metrics. It supports fuzzy search, time range filtering, and exclusion of specific indicators to provide precise results.

• get_journal_entries

  Get journal entries for specified dates Retrieves user journal content for the specified dates from th_messages. Returns either text content or voice transcription, whichever is available. Returns fields include:

  • date: Journal date
  • content: Journal content (either text or voice transcription)
  • content_type: Content type ('text' or 'voice')
• search_medical_literature

  [Coarse Search] Batch search for medical literature with pagination, used for preliminary filtering. Returns basic metadata of multiple articles (title, abstract, authors, affiliations, etc.), WITHOUT full text. Use case: Discover relevant literature by keywords, perform initial screening based on abstracts and metadata. To get the complete full text of a specific article, use get_article_by_pmcid() for precise retrieval.

• get_indicators_by_symptoms

  Get health indicators based on symptoms using LCS similarity and LLM matching

• get_user_health_profile

  Get user health profile information Retrieves comprehensive health profile data from health_user_profile_by_system table.

• generate_column_chart

  Generate a column chart, which are best for comparing categorical data, such as, when values are close, column charts are preferable because our eyes are better at judging height than other visual elements like area or angles.

• generate_dual_axes_chart

  Generate a dual axes chart which is a combination chart that integrates two different chart types, typically combining a bar chart with a line chart to display both the trend and comparison of data, such as, the trend of sales and profit over time.

• generate_line_chart

  Generate a line chart to show trends over time, such as, the ratio of Apple computer sales to Apple's profits changed from 2000 to 2016.

• generate_pie_chart

  Generate a pie chart to show the proportion of parts, such as, market share and budget allocation.

• generate_radar_chart

  Generate a radar chart to display multidimensional data (four dimensions or more), such as, evaluate Huawei and Apple phones in terms of five dimensions: ease of use, functionality, camera, benchmark scores, and battery life.

• get_clinical_trials

  Get clinical trials information from ClinicalTrials.gov API. This tool searches for clinical trials based on provided keywords and status filters. It retrieves information about clinical trials in various states. The returned data includes:

  • Trial title and NCT ID
  • Sponsoring organization
  • Trial status and status verification date
  • Medical conditions being studied
  • Brief summary of the trial
  • Direct link to the trial on ClinicalTrials.gov Useful for:
  • Finding clinical trials for specific conditions or treatments
  • Researching available trials for patients
  • Understanding current medical research activities
  • Identifying recruiting trials for specific diseases
• download_global_files

  Download file content from user's upload history and save to workspace. This tool works in conjunction with list_global_files tool:

  1. First use list_global_files to get available file IDs
  2. Then use this tool with those IDs to download files to workspace
  3. Use read_file tool to access the downloaded files The tool supports two modes:

  • Local files (localhost URLs): reads from local storage using file_key
  • Remote files: downloads via HTTP/HTTPS Files are saved to /workspace/downloads/ directory.
• get_drug_synergistic_interactions

  Get synergistic interactions for a specific drug.

• get_fda_drugs

  Get FDA approved drug information from the FDA database. This tool retrieves information about drugs approved by the U.S. Food and Drug Administration (FDA). You can filter by approval date range to find drugs approved during specific time periods. The returned data includes:

  • Drug name and active ingredient
  • FDA approval date and year
  • Approved medical use/indication
  • Drug identification number Useful for:
  • Finding recently approved drugs for specific conditions
  • Researching drug approval history
  • Identifying new treatment options
  • Understanding FDA-approved uses for medications
• get_user_medications

  Get user's current medications from series data.

• get_food_records

  Get user food records

• search_knowledge_qa

  Search knowledge base for relevant Q&A pairs using semantic similarity. Supports parallel multi-keyword search with automatic deduplication. Features:

  • Semantic search using embedding similarity
  • Automatic parallel search for space-separated keywords
  • Deduplication and ranking by similarity score
  • Formatted output ready for agent consumption
• _deduplicate_and_sort_results

  去重并排序搜索结果 去重策略：

  • 基于 question 字段去重
  • 如果同一个问题出现多次，保留相似度最高的
• get_medical_devices

  Get FDA approved medical device information from the FDA database. This tool retrieves information about medical devices approved by the U.S. Food and Drug Administration (FDA). You can filter by approval date range and device category to find specific devices. The returned data includes:

  • Device name and identification
  • Device category/classification
  • FDA approval date Useful for:
  • Finding recently approved medical devices
  • Researching device approval history by category
  • Identifying new medical technologies
  • Understanding FDA-approved medical devices for specific applications
• get_article_by_pmcid

  [Precise Query] Retrieve complete information for a single article by PMCID, INCLUDING full text. Used for in-depth analysis of articles filtered from search_medical_literature() coarse search. Use case: Read full paper content, extract detailed information such as study methods, results, conclusions for fine-grained screening. Typical workflow:

  1. Use search_medical_literature() to search for relevant literature, get article list
  2. Perform initial filtering based on title, abstract, keywords, etc.
  3. Use this method get_article_by_pmcid() to retrieve the complete full text of target article
  4. Extract detailed information from full text (e.g., study population characteristics, methodology, specific data)