> ## 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.

# Add a citable evidence layer to an agent you already ship

> Give a working agent access to peer-reviewed literature as a tool, so its claims carry citations instead of assertions.

## What you get

An agent that already does something valuable, now grounded: every claim it makes traces to a real paper, and "the literature does not answer this" becomes an answer it can give.

The integration is a tool registration, not a re-architecture. Owkin shipped theirs to users in days.

## Who it's for

Product engineers whose agent works but overclaims — it reasons well and cites nothing, and your users have started noticing.

## How it went at Owkin

[Owkin](https://consensus.app/home/community-voices/owkin/) exposed Consensus to K Pro's orchestrator the same way it exposes its other tools. That architectural fit is the whole story: no new retrieval service, no corpus to maintain, no bespoke ranking layer.

> "The Consensus MCP slotted directly into our agentic stack and gave K Pro's capabilities a dramatic upgrade overnight."
>
> — **Lucas Brechot**, Senior Product Manager, AI Products, Owkin

Agents now ground their reasoning in full-text literature with programmatic controls for recency, citation count, and journal reputation — the filters a human researcher applies instinctively when judging whether a paper is relevant and credible.

## Wiring it in

<CodeGroup>
  ```bash MCP theme={null}
  # OAuth per user, so each person's own plan and limits apply
  https://mcp.consensus.app/mcp
  ```

  ```bash REST theme={null}
  # one service key, full control over pagination
  curl -G "https://api.consensus.app/v1/search" \
    -H "x-api-key: $CONSENSUS_API_KEY" \
    --data-urlencode "query=your agent's search string"
  ```
</CodeGroup>

Choose by auth model rather than by preference: **MCP** when each user should search under their own account and limits, **REST** when the integration needs one shared quota and programmatic pagination.

## What separates a grounded agent from a decorated one

<Steps>
  <Step title="Decompose before retrieving">
    One search per user question is the most common cause of thin answers. Split the question into subquestions and give each its own search with its own filters.
  </Step>

  <Step title="Retrieve excerpts, not just abstracts">
    Request `include_full_text_chunks=true` so the generation step reasons over results paragraphs rather than the introduction.
  </Step>

  <Step title="Enforce grounding at generation time">
    Require a `doi` or `url` on every claim and drop unsupported sentences. Make "the literature does not answer this" a first-class output rather than a failure state.
  </Step>

  <Step title="Surface the filters you applied">
    Show the study types, years, and quality thresholds used. A researcher cannot trust a result set whose inclusion criteria are hidden.
  </Step>

  <Step title="Cache on the full parameter set">
    Cache on every parameter, not the query string alone, with a short TTL so new literature still lands.
  </Step>
</Steps>

## What to check before you trust it

* **Check the unanswerable case.** Ask your agent something the literature genuinely does not settle. If it produces a confident cited answer anyway, your grounding rule is decorative.
* **Spot-check citations against claims.** A real paper attached to a claim it never made is the failure that survives review.
* **Watch your rate limit under real traffic.** Per-user OAuth spreads load across accounts; a shared service key concentrates it. See [rate limits](/use-cases/best-practices#rate-limits-and-result-caps).
* **Do not hide the filters.** If your product narrows to Q1 journals by default, say so in the UI.

## Related

<CardGroup cols={2}>
  <Card title="Swap a hand-maintained paper corpus for full-text search" icon="arrows-rotate" href="/use-cases/swap-a-paper-corpus">
    When you already have a corpus and want it gone.
  </Card>

  <Card title="Answer one question with many parallel searches" icon="diagram-project" href="/use-cases/parallel-search-angles">
    The retrieval pattern that makes a grounded agent good rather than merely cited.
  </Card>

  <Card title="Best practices" icon="shapes" href="/use-cases/best-practices">
    Rate limits, grounding rules, and the five primitives.
  </Card>

  <Card title="All use cases" icon="grid-2" href="/use-cases">
    Browse the gallery by persona.
  </Card>
</CardGroup>