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

# Integrations

Vayl is a standard **Model Context Protocol** server, so it drops into any MCP client and talks to any OpenAI-compatible model. Point it at the tools you already use — no adapters, no lock-in.

## MCP clients

Any MCP-capable agent can call Vayl's tools. Add the server to your client's configuration (see [Quickstart](/vayl-docs/documentation/getting-started/quickstart.md)) and restart.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><h4><i class="fa-robot" style="color:$primary;">:robot:</i> Claude Desktop</h4></td><td>Add Vayl under <code>mcpServers</code> and restart the app.</td><td><a href="/pages/416edc1381c20849bc41111b02e482a722a49b94">/pages/416edc1381c20849bc41111b02e482a722a49b94</a></td></tr><tr><td><h4><i class="fa-i-cursor" style="color:$primary;">:i-cursor:</i> Cursor</h4></td><td>Register <code>vayl-mcp</code> as an MCP server in settings.</td><td><a href="/pages/416edc1381c20849bc41111b02e482a722a49b94">/pages/416edc1381c20849bc41111b02e482a722a49b94</a></td></tr><tr><td><h4><i class="fa-terminal" style="color:$primary;">:terminal:</i> Claude Code</h4></td><td>Add Vayl with <code>claude mcp add</code> and it's available in-session.</td><td><a href="/pages/416edc1381c20849bc41111b02e482a722a49b94">/pages/416edc1381c20849bc41111b02e482a722a49b94</a></td></tr><tr><td><h4><i class="fa-plug" style="color:$primary;">:plug:</i> Any MCP client</h4></td><td>Vayl speaks stdio and streamable-HTTP — any compliant client works.</td><td><a href="/pages/81aEMdYPcN3Gx3TwvNGx">/pages/81aEMdYPcN3Gx3TwvNGx</a></td></tr></tbody></table>

## Models & embedders

Vayl needs one model to extract facts and one embedder for retrieval — any **OpenAI-compatible** endpoint. Set them in [Configuration](/vayl-docs/documentation/reference/configuration.md).

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><h4><i class="fa-brain" style="color:$primary;">:brain:</i> OpenAI</h4></td><td>Set <code>OPENAI_API_KEY</code>; <code>gpt-5-mini</code> is the default.</td><td><a href="/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d">/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d</a></td></tr><tr><td><h4><i class="fa-house-laptop" style="color:$primary;">:house-laptop:</i> Ollama (local)</h4></td><td>Point <code>OPENAI_BASE_URL</code> at Ollama — nothing leaves the machine.</td><td><a href="/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d">/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d</a></td></tr><tr><td><h4><i class="fa-microchip" style="color:$primary;">:microchip:</i> vLLM / LM Studio</h4></td><td>Any local OpenAI-compatible server works the same way.</td><td><a href="/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d">/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d</a></td></tr><tr><td><h4><i class="fa-network-wired" style="color:$primary;">:network-wired:</i> Any OpenAI-compatible</h4></td><td>Self-hosted or EU-region endpoints for data residency.</td><td><a href="/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d">/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d</a></td></tr></tbody></table>

## Storage

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><h4><i class="fa-database" style="color:$primary;">:database:</i> SQLite</h4></td><td>The default — one file, zero setup, nothing to operate.</td><td><a href="/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d">/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d</a></td></tr><tr><td><h4><i class="fa-server" style="color:$primary;">:server:</i> Postgres</h4></td><td>Set <code>VAYL_DATABASE_URL</code> for concurrent, multi-writer scale.</td><td><a href="/pages/56a52747d54863f8df67ff3ce908938888c69b66">/pages/56a52747d54863f8df67ff3ce908938888c69b66</a></td></tr><tr><td><h4><i class="fa-diagram-project" style="color:$primary;">:diagram-project:</i> Neo4j graph</h4></td><td>Optional projection for deep multi-hop relational queries.</td><td><a href="/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d">/pages/65332f63d0b6cedd6ac718136ba8d89ec6cc1a4d</a></td></tr></tbody></table>


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://vayl.gitbook.io/vayl-docs/documentation/integrations.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.