mcpbeat Sign in

Panda Research Tools MCP Server

local only

Panda Research Tools runs on your own machine — the client starts it, so there is no endpoint to ping. 267 installs a week from pypi.

Scholarly integrity — citations, literature/PubMed, experts, PDF tables, Wayback (7 tools).

Installs per day peak 267 · avg 8
a month agotoday
267
Installs / week
pypi · panda-research-tools
—
Stars
on GitHub
—
Last commit
from GitHub
—
License
language unknown

Nothing serious here today

Today is the operative word: we check Panda Research Tools every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add panda-research-tools -e 'APIFY_TOKEN=<APIFY_TOKEN>' -- uvx panda-research-tools
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "panda-research-tools": {
      "command": "uvx",
      "args": [
        "panda-research-tools"
      ],
      "env": {
        "APIFY_TOKEN": "<APIFY_TOKEN>"
      }
    }
  }
}
~/.codex/config.toml
[mcp_servers.panda-research-tools]
command = "uvx"
args = ["panda-research-tools"]
env = { APIFY_TOKEN = "<APIFY_TOKEN>" }
.cursor/mcp.json
{
  "mcpServers": {
    "panda-research-tools": {
      "command": "uvx",
      "args": [
        "panda-research-tools"
      ],
      "env": {
        "APIFY_TOKEN": "<APIFY_TOKEN>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "panda-research-tools": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "panda-research-tools"
      ],
      "env": {
        "APIFY_TOKEN": "<APIFY_TOKEN>"
      }
    }
  }
}

Put your own value in place of <APIFY_TOKEN> (Apify API token. Free token: https://console.apify.com/settings/integrations). The author’s registry entry marks it as required.

Alternatives to Panda Research Tools

same job, measured the same way
OmniScholar
by luffysolution-svg

Literature, Zotero, PDF, citation, materials, and scientific image tools for research agents.

354 installs/wk local only
PDF Tables MCP
by mehtaphysical13

Reliable PDF table extraction. Pass a URL, get structured JSON tables with citations.

answering
D
doc.page PDF Extraction
by doc

Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.

7 tools answering
upAPI
by devinosolutions

All public upAPI operations as MCP tools: web scraping, search, screenshots, PDF, OCR and more.

235 installs/wk answering
Paper MCP
by mcpservings

Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.

41 tools answering
Scholar MCP
by liyux3

Federated academic search, citation traversal, persistent PDF download, and temporary reading.

1 742 installs/wk local only
X
x402 Web Tools
by workers-microtools-x402-x402-web-tools

Web/PDF to Markdown, transcription, paper search and citation checks. Pay per call in USDC via x402.

9 tools answering
Deckly
by yolofmeister-git

Design presentations, landing pages and social ads with Deckly's tools, then share or export PDF.

answering

Panda Research Tools — questions

Answers built from our own checks of this server.

Why is there no uptime for Panda Research Tools?
Panda Research Tools runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package panda-research-tools was installed 267 times last week.
How do I connect Panda Research Tools?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls panda-research-tools straight from pypi; nothing to host, nothing to sign up for.
How many people use Panda Research Tools?
The pypi package panda-research-tools was installed 267 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.