Skip to main content
Consensus gives your code and your AI tools search across the full text of 220+ million peer-reviewed research papers — not just titles and abstracts. Ask in natural language, narrow with the filters a researcher would apply — study design, date, journal quality, field, country — and get back ranked papers, the passages from inside them that answer your query, and the links you need to cite them.

Full text, not just abstracts

Methods, doses, and effect sizes rarely make it into the abstract. Consensus searches the whole paper and returns the part that matters.
  • Search inside the paper: match on methods and results, not just abstracts.
  • Return the passage: get query-relevant excerpts, labeled by section.
  • Ground every answer: cite the actual text, not a paraphrase.
Add include_full_text_chunks=true to any search. Full-text excerpts are available on all paid plans.
A real response, trimmed to one result with shortened excerpts. The takeaway gives you the paper’s conclusion. The full_text_chunks give you what the abstract leaves out — the doses, durations, and study designs behind that conclusion — each labeled with the section of the paper it came from.

What people build

Most teams building on Consensus fall into one of two groups.

Internal tools for your organization

Enterprise R&D teams, biotechs, and AI startups connecting paper search to internal assistants, scientific agents, monitoring agents, and literature tables.

Custom research systems

Academics and research groups building their own literature-review, writing, and reporting pipelines — in code or inside the AI tools they already use.

Internal tools for your organization

More in the internal tools guide, including internal AI assistants and exhaustive paper lists.

Custom research systems

More in the research systems guide, including scheduled evidence reports.

Real examples

phylo

Phylo: literature retrieval for agentic biology

Phylo’s agents fan each biology question out into parallel Consensus API searches. One internal team screens about 20,000 targets across hundreds of diseases, with almost zero production errors.
owkin

Owkin: a full-text evidence layer for K Pro

Owkin replaced a hand-maintained set of PubMed abstracts with Consensus MCP inside its agentic AI scientist — 25x the paper coverage, shipped in days.

Two ways to connect

You can reach Consensus two ways:

REST API

One x-api-key, every filter, and pagination to exhaustion. For pipelines, internal tools, and anything scheduled.

MCP server

Plug into Claude, ChatGPT, Claude Code, or any MCP-compatible agent. No code, and each user signs in with their own account.

Explore more

Get started

Pick a surface, run your first filtered search, and find the guide for what you’re building.

Use case library

30 worked examples you can filter by persona, each with the full prompt or API call behind it.

Best practices

The five building blocks, rate limits, and the grounding rules that keep output trustworthy.