Knowledge retrieval API for AI agents

Give your agents accurate
retrieval in minutes

Connect your unstructured data and give your agents accurate, cited context from your knowledge base via API or MCP.

200+ leading companies chose Kapa instead of building retrieval themselves

200+ leading companies chose Kapa

instead of building retrieval themselves

Capabilities

Everything you need to give your AI agents context from unstructured knowledge

Pre-built connectors

Connect your data in minutes

Connect any technical knowledge source, with every integration's auth, pagination, and rate limits, handled for you.

Continuous sync

Updates your sources automatically

Kapa detects and re-processes only what changed in your sources, and updates land in minutes, so agents are never fed stale context.

Fully managed pipeline

Agentic retrieval, with no maintenance

Chunking, embedding, hybrid search, reranking and evals, tuned continuously for you. All of it behind one API call or MCP server.

Complete observability

Observe every agent and user query

See what agents are querying, where Kapa couldn't provide a confident answer, and know what documentation to write next.

Use cases

What teams are building on Kapa retrieval

One knowledge base grounds every agent across your product, support, engineering, marketing and sales stack in your technical documentation.

In-product agent

AI agents embedded directly in your application. Build one on Kapa's Retrieval API, or use the pre-built components in the Kapa Agent SDK.

Learn more
route.tsCopy
1// Your own in-app agent, on Kapa Retrieval
2const RETRIEVAL =
3 "https://api.kapa.ai/query/v1" +
4 "/projects/acme/retrieval/";
5
6export async function POST(req: Request) {
7 const { question, user } = await req.json();
8
9 // Ranked chunks from your knowledge base
10 const res = await fetch(RETRIEVAL, {
11 method: "POST",
12 headers: {
13 "X-API-KEY": process.env.KAPA_API_KEY,
14 "Content-Type": "application/json",
15 },
16 body: JSON.stringify({
17 query: question,
18 integration_id: INTEGRATION_ID,
19 top_k: 5,
20 use_pruning: true,
21 user: { unique_client_id: user.id },
22 }),
23 });
24
25 // [{ source_url, content }], best first
26 const chunks = await res.json();
27 return streamAnswer(question, chunks);
28}
app.acme.com/projects/prod-eu/api-keys
Acme Cloud
API keys
API keysCreate key
P
P
C
Acme Product Agent
Getting 401s after rotating our API key. How do I rotate keys without downtime?
Searched documentation
Checking key rotation guide…
Ask anything…
Powered by

Customer stories

Why the best engineering teams chose not to build retrieval themselves

Rated 4.9/5 on G2

How Nokia deploys Kapa agents across seven networking product lines

+300k

queries processed

125+

sources integrated

How Raspberry Pi uses Kapa's knowledge retrieval to help 88% of users self-serve

88%

self-serve rate

+18k

queries processed since launch

How Nordic Semiconductor deployed Kapa across docs, support form and MCP server

+700k

queries processed

-83%

query token cost

How monday.com scaled their in-product agent to 100,000+ customers

+161k

queries processed

98%

ticket deflection rate

How Nokia deploys Kapa agents across seven networking product lines

+300k

queries processed

125+

sources integrated

How Raspberry Pi uses Kapa's knowledge retrieval to help 88% of users self-serve

88%

self-serve rate

+18k

queries processed since launch

How Nordic Semiconductor deployed Kapa across docs, support form and MCP server

+700k

queries processed

-83%

query token cost

How monday.com scaled their in-product agent to 100,000+ customers

+161k

queries processed

98%

ticket deflection rate

Everything you need to give your agents accurate retrieval, ready in minutes.

Get started for free. Connect your sources and get an API key or hosted MCP server to give your agents the context they need to do reliable work at scale.

Enterprise-grade security and controls

Zero data retention & PII masking

Security controls to limit data retention and PII processing for sensitive use cases.

SOC 2

SOC 2 & GDPR

Independently audited controls for security, availability, and confidentiality.

SSO & RBAC

Single sign-on and role-based access across the platform.

EU/US

Data regions

US and EU hosting available, so your knowledge stays where compliance needs it.

Frequently asked questions

What is Kapa?

Kapa is an ingestion and retrieval system for your unstructured knowledge. Ingestion assembles a unified knowledge base from 20+ types of sources - documentation sites, PDFs, tickets, community threads, API specifications — and keeps it up to date as that content changes. Agentic retrieval searches across it to find what the agent needs, the moment it needs it. You hand Kapa to your agent as a search tool via MCP, or call it directly through the API. And for the cases where you do not want to build an agent at all, Kapa offers Prebuilt Agents for common use cases, out of the box.

What can I build with Kapa?

+

Why do agents need retrieval? Can’t I just put my docs in the context window?

+

How is this different from building retrieval in-house?

+

When would I use a web search API like Exa or Tavily instead?

+

Which knowledge sources can Kapa ingest?

+

How does Kapa keep the knowledge base up to date?

+

Does it work with my agent framework and model?

+

I just want a documentation assistant. Do I have to build an agent?

+

Is my data secure? Is it used for training?

+

How does pricing work?

+

Can Kapa run on-prem or in our own VPC?

+