Connect your AI Agents to bioRxiv in minutes

What is a bioRxiv MCP?

It's an MCP server that gives your agents access to bioRxiv's preprint repository via tools. Your agents can invoke these tools to search for recent preprints, retrieve metadata by DOI, filter publications by date range or server, and more.

Cold Spring Harbor Laboratory doesn't offer an MCP server purpose built for bioRxiv, but you can use one from a third-party platform, like Merge Agent Handler.

How can I use the bioRxiv MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

• Research digest delivery: An agent pulls the most recent bioRxiv preprints in a specified subject area on a daily or weekly schedule and sends a formatted summary to a research team via Slack or email, keeping scientists current without manual literature searches

• RAG knowledge base ingestion: An agent retrieves new preprints matching a topic and ingests their abstracts and metadata into a vector database, keeping a retrieval-augmented generation system current with the latest findings in a field

• Preprint monitoring for competitive intelligence: A biopharma or research organization runs an agent that tracks preprints from specific institutions or authors and alerts a team when new work is published in a target area

• Literature review assistance: An agent accepts a research question from a scientist, searches recent bioRxiv preprints for relevant work, and returns a structured summary of findings with DOI links for further reading

What are popular tools for bioRxiv's MCP server?

Here are some of the most commonly used tools:

• list_preprints: retrieves preprints from bioRxiv or medRxiv filtered by date range or count. Useful for agents that need to pull a batch of recent publications for a digest, ingestion pipeline, or trend analysis

• get_preprint: fetches full metadata for a single preprint using its DOI, including title, authors, abstract, and version history. Call this when an agent needs to retrieve structured details about a specific paper before summarizing or storing it

• search_recent_preprints: returns the most recently posted preprints from bioRxiv or medRxiv. Good for workflows that need a live feed of new publications to power alert systems or keep a knowledge base current

What makes Merge Agent Handler's bioRxiv MCP server better than alternative bioRxiv MCP servers?

There are a few reasons to use Merge Agent Handler's bioRxiv MCP server over a community-built alternative:

• Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact fields before they reach an agent. For bioRxiv, this means you can control exactly which metadata fields an agent surfaces, useful for organizations with strict data governance policies around research outputs

• Managed authentication and credentials: Merge stores and refreshes bioRxiv credentials on your behalf. You never expose raw API keys or OAuth tokens to an agent or manage token rotation manually

• Real-time observability and audit trail: Every tool call made against bioRxiv is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly what an agent queried without instrumenting anything yourself

• Tool Packs and controlled access: Tool Packs let you bundle specific bioRxiv tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more

How can I start using Merge Agent Handler's bioRxiv MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account.

2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.

3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.

4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose bioRxiv and complete the auth flow. Merge stores and manages the credentials going forward.

5. Open a Claude Code session and start querying bioRxiv data directly. The first time you use a bioRxiv tool, a Magic Link may appear to complete connector authentication.

If you want to connect Merge Agent Handler's bioRxiv MCP with internal or customer-facing agentic products, you can follow the steps in our docs.