Enables multi-hop research query decomposition and synthesis planning for Perplexity, allowing complex research prompts to be broken into manageable subqueries and aggregated into evidence-based results.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@genpark-multihop-research-query-decomposer-skill Decompose: 'What are the long-term effects of ketogenic diets on cardiovascular health?'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🌐 GenPark MCP Hub Showcase • 📦 GenPark Official Website • 📖 Documentation
genpark-multihop-research-query-decomposer-skill is a deterministic, zero-dependency Python skill engineered for autonomous scientific paper analysis, consensus ratio calculation, citation credibility verification, and multi-hop research query execution.
Executive Capability: Complex multi-faceted research prompt decomposer & synthesis DAG planner (Perplexity / Genspark)
🐍 Zero External pip Dependencies: Runs instantaneously on standard Python 3.9+ with zero environment bloat.
🔌 Native Model Context Protocol (MCP): Seamlessly integrates into Claude Desktop, Cursor IDE, Perplexity workspaces, and autonomous research swarms.
🎯 Deterministic & Reliable: 100% predictable input/output contracts with full JSON Schema validation.
🚀 Low Latency: Sub-millisecond execution overhead tailored for high-concurrency research pipelines.
Related MCP server: genpark-deep-research-evidence-synthesis-graph-skill
graph LR
User([🔬 Researcher / Agent]) -->|Research Query & Corpus| MCP[⚡ MCP Server / Protocol]
MCP --> Client[🛠️ Research Kernel]
Client --> Engine[🧠 Scientific Evidence Analysis Pipeline]
Engine --> Synthesis[📊 Consensus Dossier & Verified Citations]
Synthesis --> Userpython example_usage.pyfrom client import MultihopResearchQueryDecomposerClient
client = MultihopResearchQueryDecomposerClient()
result = client.decompose_research_query()
print(result)Connect this skill to Claude Desktop, Cursor, or any MCP-compliant client:
claude_desktop_config.json{
"mcpServers": {
"genpark-multihop-research-query-decomposer-skill": {
"command": "python",
"args": ["/path/to/genpark-multihop-research-query-decomposer-skill/mcp_server.py"]
}
}
}Parameter | Type | Required | Description |
|
| Yes | Primary input parameter parsed and executed deterministically |
|
| Yes | Standardized response schema containing execution telemetry |
GenPark AI Agent Skills are engineered with zero external dependencies using pure Python standard library code. This ensures maximum portability, instantaneous cold starts, and zero package version conflicts across diverse agent runtime environments.
Explore the comprehensive directory of 1,200+ open-source, production-ready AI Agent skills at the GenPark AI MCP Hub and learn more about scientific research tools at GenPark AI.
Run python mcp_server.py --test to verify MCP protocol discovery and tool schema negotiation.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Read-only MCP over an agentic SLR workspace with per-claim citation verification
Read-only MCP over an agentic SLR workspace with per-claim citation verification
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/alphaparkinc/genpark-multihop-research-query-decomposer-skill'
If you have feedback or need assistance with the MCP directory API, please join our Discord server