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

# MCP Server (Model Context Protocol)

> Connect AI assistants to Algolia indices using the Algolia MCP Server.

The Model Context Protocol (MCP) is an open standard that lets AI agents call external tools
and retrieve structured data in real time. Algolia supports MCP with two offerings so teams can
connect assistants to their data without rebuilding integrations for every model or workflow.

Algolia supports MCP with two offerings. **Both are Algolia-managed services.**

* [Algolia Public MCP](#algolia-public-mcp). **All the Search & Discovery capabilities of Algolia**, available in any AI assistant across your indices and Recommend models.
* [Algolia Productivity MCP](#algolia-productivity-mcp). **User-scoped automation** for day-to-day work like search optimizations and analytics.

## Algolia Public MCP

Use the Algolia Public MCP when you want to expose specific Algolia indices to AI agents in a controlled,
application-scoped way.

What it's for:

* **AI-facing search and recommendations** on a defined set of indices.
* Integrate with MCP-compatible platforms like [ChatGPT](https://chatgpt.com), [Claude](https://claude.ai), [Vertex AI](https://cloud.google.com/vertex-ai), [Perplexity](https://www.perplexity.ai), [Amazon Q](https://aws.amazon.com/q/),
  [Microsoft Copilot](https://www.microsoft.com/en-us/microsoft-copilot), or [Salesforce Agentforce](https://www.salesforce.com/agentforce/).
* Support production use cases such as product discovery, support bots, and customer-facing AI experiences.

Key traits:

* **Tool-scoped interface** that exposes search and recommend without exploding tool counts.
* Usage counts toward your existing Algolia plan; no separate MCP SKU or fee.

## Algolia Productivity MCP

Use the Algolia Productivity MCP for internal, user-scoped workflows that need broad access to your
Algolia data across applications.

What it's for:

* **Exploration, analysis, and internal productivity** with LLM-powered tools.
* Personal workflows where your own Algolia permissions determine access.
* Business intelligence-style questions and one-off operational checks like spotting trending searches or zero-result queries.

Key traits:

* **User-scoped access** across all applications and indices you can access.
* **Authentication required** (for example, when discovered through MCP registries).
* **Read-only index access**, with an extended set of tools such as analytics.
* Registry-visible, so it appears in public MCP directories.

## Choose the right MCP

| Need                                                    | Use                      |
| ------------------------------------------------------- | ------------------------ |
| Expose a curated set of indices to external agents      | Algolia Public MCP       |
| Personal, internal access across all your Algolia data  | Algolia Productivity MCP |
| High-traffic, low-latency requirements                  | Algolia Public MCP       |
| LLM-guided analysis and automation for index operations | Algolia Productivity MCP |

## Get started

* [Algolia Public MCP](/doc/guides/model-context-protocol/public-mcp): Create an MCP server in the Algolia dashboard, select the indices to expose, then
  connect the server URL to your MCP client.
* [Algolia Productivity MCP](/doc/guides/model-context-protocol/productivity-mcp): Enable it in your Algolia account, then sign in when prompted by your MCP
  client or registry and start using your existing permissions.