Log inSubmit server
Plos logo

Plos

Search PLOS open-access research by text, DOI, author, or publication date through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Plos

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "plos": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-plos"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 4 tools correctly (7d ago).

Overview

Plos MCP server exposes PLOS's Solr-backed search API for full-text discovery across open-access journals. It provides tools for Solr-style queries, DOI lookups, author searches, and recent publications. Use the hosted gateway for HTTP or streamable MCP access, or run the package locally over stdio without a gateway account. It is suited to agents that need to find and retrieve PLOS research articles.

Use cases

  • Search PLOS articles with Solr field queries
  • Retrieve a PLOS article by DOI
  • Find publications by an author name
  • List recent PLOS publications
  • Connect an agent to PLOS research over stdio or HTTP

Key features

  • Full-text search across PLOS open-access journals
  • Solr query syntax with pagination and sorting options
  • Article lookup by DOI
  • Author-based article search
  • Recent publication retrieval
  • Hosted gateway and local stdio modes

Tools4

What Plos lets your agent do. Expand a tool for its parameters.

Verified live~286 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

9/9 checks healthy over the last 51d

What it can do

From the 4 tools this server returned when we ran it.

Makes network requests · 1Read-only tools · 4
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age158 days
Maintainers1

Observed 2026-10-21 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 4d ago via OSV.dev · @pipeworx/mcp-plos (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads443Package downloads in the last 30 days.
Last commit1mo agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed4Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Plos works

What Plos MCP server does

Plos MCP server connects AI agents to the PLOS Search API at https://api.plos.org/search. The API provides full-text search across PLOS open-access journal content and accepts Solr query syntax. The package exposes four domain-specific tools:

  • search(query, rows?, start?, sort?, fl?) for Solr-style searches with pagination, sorting, and field selection.
  • article(doi) for retrieving an article by DOI.
  • search_authored_by(name, rows?) for finding articles associated with an author name.
  • recent(rows?) for listing the most recent PLOS publications.

This makes the Plos MCP server relevant for literature discovery, article retrieval, and research workflows focused on PLOS content.

How it works

The hosted MCP endpoint is https://gateway.pipeworx.io/plos/mcp. An MCP client can connect to that URL and call the PLOS tools through the Pipeworx gateway. The pack endpoint also exposes shared Pipeworx meta-tools, including ask_pipeworx, discover_tools, search_within, and remember/recall. The exact tool scope is returned by the connection's initialize response and may change over time.

The gateway can also be used through HTTP without an MCP client. For example, POST https://gateway.pipeworx.io/v1/tools/plos_search accepts a JSON request containing a search query. Tool details can be inspected with the corresponding GET /v1/tools/plos_search endpoint.

For a pack-only connection, the package runs locally as a stdio MCP server. In that mode, it handles MCP initialization, tool listing, and tool calls for the PLOS tools without the gateway's shared meta-tools or cross-catalog routing.

Setup and configuration

Add the hosted endpoint to an MCP client using its URL configuration. The README specifically gives configurations for Claude Desktop, Cursor, and Windsurf. No API key or environment variable is documented for the PLOS data source, and the gateway can be used without an account for initial calls.

To run locally, configure the client to execute npx -y @pipeworx/mcp-plos. The same command can be run directly to verify that the process starts. Local execution avoids a gateway round trip and does not require a Pipeworx account.

Alternatively, connect to https://gateway.pipeworx.io/mcp for the full Pipeworx gateway. The full endpoint lists tools from all available packs directly, while ask_pipeworx can route questions across the catalog from either gateway URL.

Tools and capabilities

The primary search interface accepts a query and optional rows, start, sort, and fl values. Queries can use PLOS's Solr syntax, such as field-qualified expressions. DOI lookup, author-name search, and recent-publication retrieval provide narrower alternatives when a general full-text query is not appropriate.

The Plos MCP server is keyless at the PLOS API layer. It does not document a separate credential, account setup, or local configuration file. Its data scope is PLOS open-access journal content rather than a general scholarly index.

Limitations and notes

The hosted pack endpoint includes shared gateway tools in addition to the PLOS-specific tools, so its total tool count is larger than the four tools listed here. The standalone package exposes only the pack's own tools.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Plos

Plos is an MCP server that connects AI agents to the PLOS Search API for open-access journal content. Its main tools support Solr-style full-text search, article lookup by DOI, searches by author name, and retrieval of recent publications. It can run through the Pipeworx gateway or locally over stdio.

Install it locally by configuring an MCP client to run `npx -y @pipeworx/mcp-plos`. The package communicates over stdin and stdout and does not require a Pipeworx account. You can instead configure the hosted endpoint at `https://gateway.pipeworx.io/plos/mcp`.

Yes, Plos works with Cursor through the hosted MCP endpoint. Add `https://gateway.pipeworx.io/plos/mcp` to Cursor's MCP configuration.

Call the `search` tool with a Solr-style `query`, such as a field-qualified expression. Optional `rows`, `start`, `sort`, and `fl` arguments control the requested result set. The same search can be called over HTTP through the gateway's `plos_search` tool endpoint.

No API key is documented for the PLOS data source.

Related MCP servers

All in Research All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewPlos AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/plos?style=directory)](https://allmcps.com/mcp/plos)
HTML Embed
<a href="https://allmcps.com/mcp/plos"><img src="https://allmcps.com/api/badge/plos?style=directory" alt="Plos on AllMCPs" /></a>