Paperai MCP Server

AI for medical and scientific papers

Local serverstdioPython

What is the Paperai MCP server?

If you already use Paperai, the paperai mcp server is the piece that lets your assistant work with it directly. AI for medical and scientific papers.

What the server does

paperai is an AI application for medical and scientific papers.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • name — Date
  • CSV — Renders a CSV report. Columns and answers are extracted from articles with the results stored in a CSV file
  • Annotation — Columns and answers are extracted from articles with the results annotated over the original PDF files. Requires passing in a path with the original
  • paperai.report — Builds a report for a series of queries. For each query, the top scoring articles are shown along with matches from those articles. There is also a
  • paperai.query — Runs a single query from the terminal
  • paperai.shell — Allows running multiple queries from the terminal
  • Notebook — Description
  • Application — Description
  • Field — Description
  • options — RAG pipeline options - set the LLM, prompt templates, max length and more
  • report — Each unique top level parameter sets the report name. In the example above, it's called Research
  • query — Vector query that identifies the top n documents

Installation

The server ships on PyPI as paperai, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Where it fits

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Paperai's toolset — name, CSV, Annotation and 11 more — is a fair guide to whether it matches your workflow. It is maintained by NeuML; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Paperai's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Paperai.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
nameDate
CSVRenders a CSV report. Columns and answers are extracted from articles with the results stored in a CSV file.
AnnotationColumns and answers are extracted from articles with the results annotated over the original PDF files. Requires passing in a path with the original PDF files.
paperai.reportBuilds a report for a series of queries. For each query, the top scoring articles are shown along with matches from those articles. There is also a highlights section showing the most relevant results.
paperai.queryRuns a single query from the terminal
paperai.shellAllows running multiple queries from the terminal
NotebookDescription
ApplicationDescription
FieldDescription
optionsRAG pipeline options - set the LLM, prompt templates, max length and more
reportEach unique top level parameter sets the report name. In the example above, it's called Research
queryVector query that identifies the top n documents
columnsList of columns
DateArticle publication date

How to install the Paperai MCP server

{
  "mcpServers": {
    "paperai": {
      "command": "uvx",
      "args": ["paperai"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Paperai to name.
  • Use Paperai to CSV.
  • Use Paperai to Annotation.

Frequently asked questions

It connects Paperai to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (name, CSV, Annotation, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Paperai directly.