How to Use the PMC Open Access (PubMed Central) MCP in Claude Code

Q: How do I use Claude Code to get all article IDs from PMC Open Access (PubMed Central) for a specific topic?

You'd use the oailistidentifiers tool. The command would look something like claude mcp exec pmc-open-access-pubmed-central-mcp oailistidentifiers --set 'bioinformatics'. You can then pipe that JSON output to jq for filtering.

Q: Can I export citations directly from the command line?

Yes. Use the exportcitation tool with a specific article ID. For example: claude mcp exec pmc-open-access-pubmed-central-mcp exportcitation --id 'PMC3166846' --format 'bibtex' > mycitation.bib.

Q: How do I add this MCP server to my Claude Code environment?

It's a one-line command: claude mcp add pmc-open-access-pubmed-central-mcp -- . After that, all the tools are available for you to use in your terminal.

Pipe millions of PubMed Central articles directly into your terminal scripts and CI/CD pipelines with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PMC Open Access (PubMed Central) MCP to Claude Code

Create your Vinkius account to connect PMC Open Access (PubMed Central) to Claude Code — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PMC Open Access (PubMed Central) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Put PubMed Central in Your Shell Scripts

This is for developers who live in the terminal. Use standard Unix pipes to chain PMC data into your existing workflows. No need to write custom API clients or parsers for one-off tasks. For example, `claude mcp exec pmc-open-access-pubmed-central-mcp oai_list_identifiers --set neurogenesis | jq -r '.records[].header.identifier' | xargs ...`. It's a simple, powerful way to integrate a massive scientific database into your command-line tools.

Automate Backend Data Syncing

Run this in a cron job or a GitHub Action. It's perfect for keeping an internal database in sync with PubMed Central's public records. The headless nature of Claude Code means it runs anywhere. The `convert_ids` tool is especially useful for backend jobs. You can feed it a stream of article IDs from one system and get back the corresponding IDs for another, ensuring your data stays consistent across different services.

A Headless MCP Server for Production

This isn't a toy. Because Claude Code is a CLI, you can reliably integrate this MCP server into production data pipelines. It returns structured JSON, so you can count on the output. Use `oai_get_record` to fetch the full XML for a specific paper and pipe it into an NLP processing service. Or use `oai_identify` as a health check in your CI/CD pipeline to ensure the PMC repository is responding before running a larger data import job.

Setup guide

Set up PMC Open Access (PubMed Central) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see pmc-open-access-pubmed-central-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest PMC Open Access (PubMed Central) transactions." It will automatically discover and invoke the available PMC Open Access (PubMed Central) tools.

Terminal

claude mcp add --transport http pmc-open-access-pubmed-central-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the PMC Open Access (PubMed Central) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "pmc-open-access-pubmed-central-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by PMC (PubMed Central). All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect PMC Open Access (PubMed Central) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about PMC Open Access (PubMed Central) MCP in Claude Code

You'd use the `oai_list_identifiers` tool. The command would look something like `claude mcp exec pmc-open-access-pubmed-central-mcp oai_list_identifiers --set 'bioinformatics'`. You can then pipe that JSON output to `jq` for filtering.

Yes. Use the `export_citation` tool with a specific article ID. For example: `claude mcp exec pmc-open-access-pubmed-central-mcp export_citation --id 'PMC3166846' --format 'bibtex' > my_citation.bib`.

Authentication and simplicity. Vinkius handles the auth token, so you don't have to manage API keys. The MCP server provides named tools with clear parameters, which is more reliable for scripting than crafting raw HTTP requests and parsing messy XML.

It's a one-line command: `claude mcp add pmc-open-access-pubmed-central-mcp -- `. After that, all the tools are available for you to use in your terminal.

Yes. The server works exclusively with public article metadata from PMC. Your connection token is managed by Vinkius, and each request runs in a temporary, isolated environment that's destroyed right after your command finishes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript