Introducing Admin Analytics for the Scite MCP

When we launched the Scite MCP, we heard the same question from institutional customers almost immediately: how can we tell what are our researchers actually doing with it?

Today we're answering that.

Admin Analytics gives administrators at universities, enterprises, and research institutions full visibility into how their researchers are using the Scite MCP inside their AI tools — what content is being accessed, how it's being used, and who's using it. And it connects that usage data directly to your collections infrastructure so you can act on it.

What's included

The dashboard is organized around the full lifecycle of institutional access, from individual sessions to collection strategy.

Overview — Your top-level summary: total AI reads, unique papers accessed, active users, and sessions. A usage chart shows MCP activity over time, and a per-user breakdown lets you see exactly who's doing research and how often.

Content Access — See which papers your researchers are actually pulling into their AI sessions, down to the DOI level. If someone is researching orthopedic trauma and the MCP is surfacing papers from NEJM and JBJS, it's all logged.

Usage & Audit Log — Session-level detail including timestamps, paper IDs, and which MCP client and model was used (Claude, ChatGPT, Cursor, and others). Useful for understanding how research workflows are evolving and for reporting to stakeholders.

LibKey & OpenURL — Connect your existing access infrastructure directly to the MCP. When a researcher's AI session surfaces a paper, Scite can resolve it against your institutional holdings automatically — so they get to full text without friction, and you're not paying for access that doesn't route correctly.

Collection Gaps — This is where the data gets strategic. If your researchers are repeatedly trying to access content from the same journal or publisher and you don't hold it, that shows up here. Instead of guessing at collection priorities during budget season, you have actual demand signal from real research activity. You can allocate based on what your people are trying to read, not what you think they might want.

COUNTER Reports — COUNTER-friendly usage statistics for compliance, renewals, and publisher negotiations, built into the same dashboard.

The missing piece

Libraries and research IT teams are in a difficult spot. Researchers are using AI tools for literature review constantly, but institutions have had almost no visibility into what's actually happening. Is the AI citing papers you have access to? Is it surfacing content from journals you don't hold? Are researchers hitting dead ends?

Admin Analytics is that data. Researchers get a better way to do literature review inside their AI tools. You get visibility into how they use it, a direct connection to your access infrastructure, and clearer data for your next purchasing decision.

How to access it

If you want to see what this looks like for your institution, contact our sales team.

This is just the beginning for the Scite MCP. More to come.