> For the complete documentation index, see [llms.txt](https://docs.kpk.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kpk.io/ai-agents.md).

# KPK docs for AI agents

How AI agents and LLM tools can read KPK's documentation: llms.txt, the full-text export, per-page markdown and the MCP server, and how to verify vault facts onchain.

KPK's documentation is written to be read by people and by AI agents. Every page is available as plain markdown, the whole site is indexed for language models, and the facts a risk review depends on (vault and Safe addresses, roles, timelocks, caps and fees) are stated so they can be checked onchain.

### Machine-readable entry points

<table><thead><tr><th width="180">Resource</th><th>URL</th><th>Contents</th></tr></thead><tbody><tr><td><strong>Index</strong></td><td><a href="https://docs.kpk.io/llms.txt">https://docs.kpk.io/llms.txt</a></td><td>Every published page with a one-line summary</td></tr><tr><td><strong>Full text</strong></td><td><a href="https://docs.kpk.io/llms-full.txt">https://docs.kpk.io/llms-full.txt</a></td><td>The whole site as markdown in one file, continued at <a href="https://docs.kpk.io/llms-full.txt/1">/llms-full.txt/1</a></td></tr><tr><td><strong>One page</strong></td><td>Any page URL with <code>.md</code> appended</td><td>That page as markdown, e.g. <a href="https://docs.kpk.io/vaults/vaults/morpho/ethereum/usdc-prime.md">https://docs.kpk.io/vaults/vaults/morpho/ethereum/usdc-prime.md</a></td></tr><tr><td><strong>MCP server</strong></td><td><code>https://docs.kpk.io/~gitbook/mcp</code></td><td>Search, page retrieval and questions over the published docs</td></tr></tbody></table>

Section-specific MCP endpoints narrow the results: `https://docs.kpk.io/vaults/~gitbook/mcp` and `https://docs.kpk.io/funds/~gitbook/mcp`.

### Where to verify what

* **Vaults:** each vault page lists the vault address and its Curator Safe; Morpho vault pages also list the Markets V1 Adapter. The [Morpho overview](https://docs.kpk.io/vaults/vaults/morpho) covers roles, the Security Council, timelocks, the `forceDeallocate` penalty, and custody and encumbrance.
* **Permissions:** [Signer architecture](https://docs.kpk.io/vaults/infrastructure/signer-architecture) and [Automation](https://docs.kpk.io/vaults/infrastructure/automation) describe the Safes, the Permissions Layer and what each agent may do.
* **Risk:** the [Risk framework](https://docs.kpk.io/vaults/infrastructure/risk-framework) sets out market selection, risk tiers and monitoring.
* **Changes:** the [Change log](https://docs.kpk.io/changelog) records every onchain configuration change to a KPK vault or Fund, with its transaction.

The docs do not carry live data. TVL, APY, allocations and balances come from the chain, the Morpho API and the Dune dashboards linked on each vault page.

### Connect an MCP client

Claude Code:

```bash
claude mcp add --transport http kpk-docs https://docs.kpk.io/~gitbook/mcp
```

VS Code, in `.vscode/mcp.json`:

```json
{
  "servers": {
    "kpk-docs": {
      "type": "http",
      "url": "https://docs.kpk.io/~gitbook/mcp"
    }
  }
}
```

Example prompts:

* `Find the KPK USDC Yield vault on Ethereum and list its Curator Safe and timelocks`
* `Which KPK Morpho vaults hold savUSD as collateral?`
* `Show the latest change log entries for KPK USDC Prime`


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.kpk.io/ai-agents.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.