AI Agent Hub
Back to plugins
academica-mcp preview

academica-mcp

Web Tools Updated 2026.08.25

Run the following command in DeepSeek Harness:

dsh plugin install academica-sh/academica-mcp

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install academica-sh/academica-mcp in DeepSeek Harness to install; the source repository is https://github.com/academica-sh/academica-mcp

About this plugin

Building AI agents that reason over scientific, healthcare, or financial data is straightforward until the first hallucinated citation reaches production. Academica MCP closes that gap by exposing eight read-only Model Context Protocol servers that wire your agent directly to primary evidence: PubMed biomedical literature, clinical trial protocols, CMS Open Payments, healthcare provider records, SEC ownership and filing fundamentals, provider-market intelligence, and reimbursement data. Every record that comes back carries stable identifiers such as PMID, NCT ID, and NPI, so you can trace a conclusion straight to the source document.

The eight servers are independent and composable. Mount just PubMed for a literature-review pipeline, or layer SEC filings on top of reimbursement evidence to build a cross-domain compliance workflow. All tools are read-only by design, no tool can mutate upstream records, and credentials are user-issued and revocable, keeping the security boundary tight.

Whether you are a PhD student assembling an evidence-based medical QA system, a sell-side analyst automating 10-K digestion, or a health-IT engineer wiring up a regulatory-review pipeline, Academica MCP turns your agent from a confident reciter of model memory into a system that cites auditable, source-resolvable evidence.

Screenshots

Use Cases

  • Feed traceable PubMed literature and clinical-trial evidence into AI agents
  • Auto-retrieve SEC holdings, 10-K filings, and XBRL financial metrics for agents
  • Integrate CMS Open Payments and reimbursement data into compliance-review workflows

Best For

  • PhD students and medical NLP engineers building evidence-based AI assistants
  • Sell-side or buy-side analysts automating earnings analysis and compliance review
  • AI-agent platform architects needing multi-source evidence integration