> ## Documentation Index
> Fetch the complete documentation index at: https://docs.consensus.app/llms.txt
> Use this file to discover all available pages before exploring further.

# What you can build with the Consensus API and MCP

> Search and return the full text of 400+ million research papers — for internal tools, scientific agents, and custom research systems.

Consensus gives your code and your AI tools search across the **full text of 400+ 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.

<Accordion title="See a real full-text response" icon="code">
  Add `include_full_text_chunks=true` to any search. Full-text excerpts are available on all paid plans.

  ```bash theme={null}
  curl -G "https://api.consensus.app/v1/search" -H "x-api-key: $CONSENSUS_API_KEY" \
    --data-urlencode "query=what dose of creatine improves working memory" \
    --data-urlencode "include_full_text_chunks=true"
  ```

  ```json wrap theme={null}
  {
    "results": [
      {
        "title": "Creatine and improvement in cognitive function: Evaluation of a health claim pursuant to article 13(5) of regulation (EC) No 1924/2006",
        "authors": ["Dominique Turck", "T. Bohn", "Montaña Cámara", "…"],
        "journal_name": "EFSA Journal",
        "publisher_name": "Wiley",
        "publish_year": 2024,
        "sjr_best_quartile": 1,
        "citation_count": 5,
        "doi": "10.2903/j.efsa.2024.9100",
        "url": "https://consensus.app/papers/creatine-and-improvement-in-cognitive-function-turck-bohn/7e703e828b815257b31687a25eceac9d/",
        "takeaway": "Creatine supplementation has not been established as a cause-and-effect relationship for improving cognitive function in one or more domains.",
        "full_text_chunks": [
          "Section: Human intervention studies in healthy individuals conducted under normal conditions | Two studies had an initial loading phase of 20 g/day of creatine for 5 days, followed by 5 g/day … A significant improvement in working memory, as measured by the Backwards Digit Span test, was observed only in the study of shorter duration …",
          "Section: Weighing of the evidence | … the acute effect of creatine on working memory reported in some studies at doses of 20 g/day given for 5-7 days … was not observed at lower creatine doses, ranging from 2.2 to 14 g/day …"
        ]
      }
    ]
  }
  ```

  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.
</Accordion>

## What people build

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

<CardGroup cols={2}>
  <Card title="Internal tools for your organization" icon="building" href="/use-cases/internal-tools">
    Enterprise R\&D teams, biotechs, and AI startups connecting paper search to internal assistants, scientific agents, monitoring agents, and literature tables.
  </Card>

  <Card title="Custom research systems" icon="graduation-cap" href="/use-cases/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.
  </Card>
</CardGroup>

### Internal tools for your organization

<div className="uc-tiles">
  <a className="uc-tile" href="/use-cases/internal-tools#give-your-scientific-agent-paper-search">
    <span className="uc-tile-title"><Icon icon="bot" size={22} />Paper search for your agent</span>
    <span className="uc-tile-desc">Ground the scientific agent you ship in full-text papers, the way Phylo and Owkin do.</span>
    <span className="uc-tile-cta">See how <Icon icon="arrow-up-right" size={14} /></span>
  </a>

  <a className="uc-tile" href="/use-cases/internal-tools#keep-on-top-of-a-field">
    <span className="uc-tile-title"><Icon icon="radar" size={22} />Field-monitoring agent</span>
    <span className="uc-tile-desc">Surface what's new in your team's fields every week, and track who's publishing it.</span>
    <span className="uc-tile-cta">See how <Icon icon="arrow-up-right" size={14} /></span>
  </a>

  <a className="uc-tile" href="/use-cases/internal-tools#build-literature-tables-that-fill-themselves">
    <span className="uc-tile-title"><Icon icon="table" size={22} />Self-filling literature table</span>
    <span className="uc-tile-desc">Run the same literature questions across hundreds of targets or compounds, on demand or on a sync.</span>
    <span className="uc-tile-cta">See how <Icon icon="arrow-up-right" size={14} /></span>
  </a>
</div>

More in the [internal tools guide](/use-cases/internal-tools), including internal AI assistants and exhaustive paper lists.

### Custom research systems

<div className="uc-tiles">
  <a className="uc-tile" href="/use-cases/research-systems#literature-review-pipelines">
    <span className="uc-tile-title"><Icon icon="book-open" size={22} />Literature review pipeline</span>
    <span className="uc-tile-desc">Fan out, filter, and deduplicate into a review you can reproduce and report.</span>
    <span className="uc-tile-cta">See how <Icon icon="arrow-up-right" size={14} /></span>
  </a>

  <a className="uc-tile" href="/use-cases/research-systems#writing-with-grounded-citations">
    <span className="uc-tile-title"><Icon icon="quote" size={22} />Citation-grounded writing</span>
    <span className="uc-tile-desc">Back every claim in a draft with a real paper, or flag it as unsupported.</span>
    <span className="uc-tile-cta">See how <Icon icon="arrow-up-right" size={14} /></span>
  </a>

  <a className="uc-tile" href="/use-cases/research-systems#use-the-tools-you-already-have">
    <span className="uc-tile-title"><Icon icon="message-square" size={22} />Consensus in your AI assistant</span>
    <span className="uc-tile-desc">Run the same workflows in Claude or ChatGPT over MCP, with no code.</span>
    <span className="uc-tile-cta">See how <Icon icon="arrow-up-right" size={14} /></span>
  </a>
</div>

More in the [research systems guide](/use-cases/research-systems), including scheduled evidence reports.

### Real examples

<CardGroup cols={2}>
  <Card title="Phylo: literature retrieval for agentic biology" img="https://mintcdn.com/consensus-f7e6ffce/bWN8de6MrQCsczek/images/case-studies/phylo.jpg?fit=max&auto=format&n=bWN8de6MrQCsczek&q=85&s=3f96519c11cabad3400d7222e1e7eee3" href="https://consensus.app/home/community-voices/phylo/" width="1200" height="675" data-path="images/case-studies/phylo.jpg">
    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.
  </Card>

  <Card title="Owkin: a full-text evidence layer for K Pro" img="https://mintcdn.com/consensus-f7e6ffce/bWN8de6MrQCsczek/images/case-studies/owkin.jpg?fit=max&auto=format&n=bWN8de6MrQCsczek&q=85&s=547fa69e26e6e388143acf59b7ff79cb" href="https://consensus.app/home/community-voices/owkin/" width="1200" height="675" data-path="images/case-studies/owkin.jpg">
    Owkin replaced a hand-maintained set of PubMed abstracts with Consensus MCP inside its agentic AI scientist — 25x the paper coverage, shipped in days.
  </Card>
</CardGroup>

## Two ways to connect

You can reach Consensus two ways:

<CardGroup cols={2}>
  <Card title="REST API" icon="code" href="/api-get-started">
    One `x-api-key`, every filter, and pagination to exhaustion. For pipelines, internal tools, and anything scheduled.
  </Card>

  <Card title="MCP server" icon="plug" href="/consensus-mcp">
    Plug into Claude, ChatGPT, Claude Code, or any MCP-compatible agent. No code, and each user signs in with their own account.
  </Card>
</CardGroup>

## Explore more

<CardGroup cols={3}>
  <Card title="Get started" icon="rocket" href="/use-cases/get-started">
    Pick a surface, run your first filtered search, and find the guide for what you're building.
  </Card>

  <Card title="Use case library" icon="layout-grid" href="/use-cases/gallery">
    30 worked examples you can filter by persona, each with the full prompt or API call behind it.
  </Card>

  <Card title="Best practices" icon="shapes" href="/use-cases/best-practices">
    The five building blocks, rate limits, and the grounding rules that keep output trustworthy.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.