SkillAgentSearch skills...

DeepBoner

AI-Powered Deep Research Agent for Sexual Health

Install / Use

claude mcp add The-Obstacle-Is-The-Way -- npx -y github:The-Obstacle-Is-The-Way/DeepBoner

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

67/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of DeepBoner

DeepBoner scores 67/100 on our quality scale, 401st of 426 Education & Research skills we index.

Its MCP Server is 5.4 KB long, well organised into 20 sections with 5 code examples: a solid amount of guidance for an agent.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
26/30
Structure
20/20
Description
8/15
Adoption
3/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 10 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-09-20 found the source still online.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 81/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

DeepBoner compared with similar skills

All 4 of these similar skills score higher than DeepBoner; compare them before choosing.

SkillScoreStarsUpdatedFormat
DeepBoner (this skill)by The-Obstacle-Is-The-Way67310mo agoMCP Server
Agent-Reachby Panniantong10090.5k19d agoCLAUDE.md
headroomby headroomlabs-ai10074.4ktodayCLAUDE.md
last30days-skillby mvanhorn10063.5k3d agoCLAUDE.md
CowAgentby zhayujie10047.2ktodayCLAUDE.md

Frequently asked questions

How do I install DeepBoner?
Run claude mcp add The-Obstacle-Is-The-Way -- npx -y github:The-Obstacle-Is-The-Way/DeepBoner. The install tabs above show the steps for each supported agent.
Which AI agents does DeepBoner work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is DeepBoner safe to use?
It is Apache-2.0-licensed and scores 81/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is DeepBoner still maintained?
The repository was last updated about 10 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

title: DeepBoner emoji: 🍆 colorFrom: pink colorTo: purple sdk: gradio sdk_version: "6.0.1" python_version: "3.11" app_file: src/app.py pinned: true license: apache-2.0 short_description: "Deep Research Agent for the Strongest Boners 💪🔬" tags:

  • mcp-in-action-track-enterprise
  • mcp-hackathon
  • agents
  • sexual-health
  • reproductive-medicine
  • hormone-therapy
  • wellness-research
  • pydantic-ai
  • llamaindex
  • pubmed
  • clinical-trials
  • evidence-based
  • multi-agent

DeepBoner 🍆

CI codecov

"Peer-reviewed boners only. We take evidence-based arousal very seriously." 🔬

AI-Powered Deep Research Agent for Sexual Health

Making the world harder, one PubMed query at a time. 💪

Deep research for sexual wellness, ED treatments, hormone therapy, libido, and reproductive health - for all genders. Because everyone deserves rock-solid scientific evidence for their intimate health questions.

Why DeepBoner?

Sexual health is health. Period. Yet it remains one of the most under-researched and stigmatized areas of medicine. We built DeepBoner to:

  • Break the stigma - Ask your embarrassing questions to an AI, not a judgmental search engine
  • Get real science - Every answer backed by peer-reviewed research from PubMed & clinical trials
  • Cover everyone - ED, libido, hormones, menopause, HSDD, reproductive health - all genders welcome
  • Stay current - Access the latest clinical trials and preprints, not decade-old WebMD articles

Features

  • 🔍 Multi-Source Deep Search: PubMed, ClinicalTrials.gov, Europe PMC, OpenAlex - simultaneously
  • 🤖 MCP Integration: Use our tools from Claude Desktop or any MCP client
  • 🧠 Smart Evidence Synthesis: LLM-powered judge evaluates and synthesizes findings
  • 🔬 Evidence Deduplication: Cross-source dedup by PMID/DOI prevents duplicate papers
  • ⚡ Unified Architecture: Same powerful multi-agent orchestration for everyone
  • 🆓 Free Tier: Works without API keys (HuggingFace Qwen 2.5 7B)
  • 🚀 Paid Tier: Unlocks GPT-5 automatically when OpenAI key is provided

Example Queries

Ask anything about sexual health. We don't judge. The science does.

  • 💊 "What drugs improve female libido post-menopause?"
  • 🧪 "Clinical trials for ED alternatives to PDE5 inhibitors?"
  • 🔬 "Evidence for testosterone therapy in women with HSDD?"
  • ⚠️ "Drug interactions with sildenafil?"
  • 📊 "Latest research on flibanserin efficacy?"
  • 🩺 "Non-hormonal treatments for vaginal dryness?"
  • 💪 "Natural supplements for erectile function - what actually works?"

Quick Start

1. Environment Setup

# Install uv if you haven't already
pip install uv

# Sync dependencies
uv sync

2. Run the UI

# Start the Gradio app
uv run python src/app.py

Open your browser to http://localhost:7860.

3. Connect via MCP

This application exposes a Model Context Protocol (MCP) server, allowing you to use its search tools directly from Claude Desktop or other MCP clients.

MCP Server URL: http://localhost:7860/gradio_api/mcp/

Claude Desktop Configuration: Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "deepboner": {
      "url": "http://localhost:7860/gradio_api/mcp/"
    }
  }
}

Available Tools:

  • search_pubmed: Search peer-reviewed biomedical literature
  • search_clinical_trials: Search ClinicalTrials.gov for active/completed trials
  • search_europepmc: Search Europe PMC preprints and papers
  • search_all_sources: Search all sources simultaneously with deduplication

Development

Run Tests

uv run pytest

Run Checks

make check

Architecture

DeepBoner uses a Vertical Slice Architecture:

  1. Search Slice: Retrieving evidence from PubMed, ClinicalTrials.gov, and Europe PMC.
  2. Judge Slice: Evaluating evidence quality using LLMs.
  3. Orchestrator Slice: Managing the research loop and UI.

Built with:

  • Agent Framework: Microsoft's agent-framework-core for multi-agent orchestration
  • Gradio: For the streaming user interface with MCP server
  • PubMed, ClinicalTrials.gov, Europe PMC, OpenAlex: For biomedical data
  • ChromaDB + Sentence-Transformers: For evidence deduplication and RAG
  • LangGraph: For workflow state management

Team

Built with love (and rigorous methodology) by The-Obstacle-Is-The-Way

Hackathon

MCP 1st Birthday Hackathon - Track 2: MCP in Action (Enterprise)

We believe sexual health research deserves the same AI-powered tooling as every other medical domain. This is our contribution to normalizing conversations about intimate health through technology.

Disclaimer

⚠️ This is a research tool, not medical advice. Always consult a healthcare provider for personal medical decisions. We search the literature - we don't replace your doctor.

Links


"The science is rock solid." 🪨

Related Skills

View on GitHub
GitHub Stars3
CategoryEducation
Updated9mo ago
Forks7

Languages

Python

Trust signals

81/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

3 low