MCP Connector

Provision, Configure, and Query Algolia Search Indexes

Experimental Go MCP server for Algolia - search, index, and manage Algolia data from Claude, with granular read and write tool scoping via env vars.

Works with algolia

91
Spark score
out of 100
Updated 3 months ago
Version 1.0.0
Models
universal

Add to Favorites

Why it matters

Leverage AI agents to automate the management of your Algolia search indexes. This asset enables provisioning, configuration, and complex querying of your data within Algolia.

Outcomes

What it gets done

01

Provision new Algolia search indexes.

02

Configure index settings like searchable attributes and ranking.

03

Query products based on complex criteria (e.g., brand, price).

04

Add and update data within Algolia indexes.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-algolia | bash

Capabilities

Tools your agent gets

search_index

Search an Algolia index with filters and query parameters

add_object

Add a JSON object to an Algolia index

update_searchable_attributes

Update the searchable attributes configuration for an index

configure_ranking

Configure ranking rules and attributes for an Algolia index

Overview

Algolia MCP Server

An experimental, community-maintained Go MCP server for Algolia, giving Claude and other MCP clients search, index management, analytics, and A/B testing access, with tools individually enableable and read and write access separately scoped by API key. Use it to search or manage Algolia indices from an AI assistant, scoping to search_read-only tools unless write access via an admin key is explicitly needed. It carries no Algolia SLA and may change or break without notice.

What it does

An experimental MCP server, written in Go, that wraps Algolia's APIs so Claude and other MCP clients can search, query, and manage Algolia indices directly from a conversation. Beyond core search, it exposes tools for A/B testing, analytics, collections, monitoring, query suggestions, recommend, and usage - the same operational surface a developer would otherwise reach through Algolia's dashboard or API clients. Algolia also now offers a separately hosted MCP with no local setup, documented on their site, and a distinct Node.js MCP server in a sibling repository; this project is the original, self-hosted Go prototype.

When to use - and when NOT to

Use it to let an AI assistant search an Algolia index conversationally, for example querying all products where brand is Nike and price is under 100, or to manage index content and settings, such as adding a record or updating searchable attributes. Scope access carefully: search_read exposes only listing indices, reading settings, running queries, and getting objects, while search_write additionally allows clearing, copying, moving, and deleting objects and indices, and requires the admin-level ALGOLIA_WRITE_API_KEY rather than the regular search key. Do not treat this repository as production-grade or officially supported: Algolia states explicitly that it is experimental, not covered by their SLA, and may be changed, broken, or removed at any time, with no guarantee that local customizations survive an update.

Capabilities

Ten tool groups can be enabled individually via MCP_ENABLED_TOOLS (comma-separated), with all enabled by default: abtesting, analytics, collections, monitoring, querysuggestions, recommend, search, search_read, search_write, and usage. The server runs over stdio by default or over SSE on a configurable port (MCP_SSE_PORT, default 8080) via MCP_SERVER_TYPE. It can be debugged with the official MCP Inspector (npx @modelcontextprotocol/inspector ./mcp) and can run against local models through mcphost, an MCP orchestrator that connects to Ollama-served models instead of Claude.

How to install

Requires Go.

git clone git@github.com:algolia/mcp.git
cd mcp/cmd/mcp
go build

Then configure the client with the full path to the built binary:

{
   "mcpServers": {
      "algolia": {
         "command": "/path/to/the/repo/cmd/mcp/mcp",
         "env": {
            "ALGOLIA_APP_ID": "<APP_ID>",
            "ALGOLIA_INDEX_NAME": "<INDEX_NAME>",
            "ALGOLIA_API_KEY": "<API_KEY>",
            "ALGOLIA_WRITE_API_KEY": "<ADMIN_API_KEY>"
         }
      }
   }
}

Use ALGOLIA_WRITE_API_KEY only if write operations are actually needed.

Who it's for

Developers already using Algolia who want to search, inspect, and manage their indices from an AI assistant for prototyping or internal tooling, not for production workloads that need Algolia's official support and SLA.

Source README

🚀 Hosted MCP Now Available
We’re excited to announce that a Hosted MCP is now available! This makes it easier than ever to connect your external data and APIs to your favorite AI tool - no setup or hosting required.

👉 Learn more and get started in our documentation.

MCP

This repository contains experimental Model Context Protocol (or MCP) servers for interacting with Algolia APIs. This MCP repo is something we're sharing for you to explore and experiment with. Feel free to use it, fork it, or build on top of it - but just know that it's not officially supported by Algolia and isn't covered under our SLA. We might update it, break it, or remove it entirely at any time. If you customize or configure things here, there's a chance that work could be lost. Also, using MCP in production could affect your Algolia usage.

We also have a Node.js MCP Server that you can find here: https://github.com/algolia/mcp-node.

If you have feedback or ideas (even code!), we'd love to hear it. Just know that we might use it to help improve our products. This project is provided "as is" and "as available," with no guarantees or warranties. To be super clear: MCP isn't considered an "API Client" for SLA purposes.

Installation

First follow the quick start, which will install Claude Desktop and setup a sample Fileserver MCP server. This is a great introduction to using MCP and will let you debug things using the official guide if there are issues.

Setup the prototype Algolia MCP server

Requirements:

Clone the repo and build the server

Clone the repo, amd build the mcp server:

$ git clone git@github.com:algolia/mcp.git
$ cd mcp/cmd/mcp
$ go build

We need to have the full path of the built server binary:

$ pwd
/path/to/the/repo/cmd/mcp

NOTE: When adding this command to your configuration, you must specify the binary along with the path (/path/to/the/repo/cmd/mcp/mcp)

Update the settings to point to the new server

In Claude desktop edit the settings as per https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server and this time add the server definition for algolia (using the server path that you found earlier).

{
   "mcpServers": {
      "algolia": {
         "command": "/path/to/the/repo/cmd/mcp/mcp",
         "env": {
            "ALGOLIA_APP_ID": "<APP_ID>",
            "ALGOLIA_INDEX_NAME": "<INDEX_NAME>",
            "ALGOLIA_API_KEY": "<API_KEY>",
            "ALGOLIA_WRITE_API_KEY": "<ADMIN_API_KEY>",  /* if you want to allow write operations, use your ADMIN key here */
            "MCP_ENABLED_TOOLS": "",  /* optional: specify which tools to enable (e.g., "search,collections") */
            "MCP_SERVER_TYPE": "stdio",  /* optional: server type, either "stdio" (default) or "sse". If not set, defaults to "stdio" */
            "MCP_SSE_PORT": "8080"  /* optional: port for SSE server, default is 8080 (only used when MCP_SERVER_TYPE is "sse") */
         }
      }
   }
}

By default, all available tools are enabled when MCP_ENABLED_TOOLS is empty or not set. If you want to enable only specific tools, you can set this variable to a comma-separated list of tool names. Available tools are: abtesting, analytics, collections, monitoring, querysuggestions, recommend, search, search_read, search_write, usage.

  • search: Enables all search operations (both read and write)
  • search_read: Enables only read operations (list indices, get settings, run queries, get objects)
  • search_write: Enables only write operations (clear, copy, delete, move, set settings, delete objects, insert objects)

Restart Claude desktop, and you should see a new "algolia" tool is available.

Debugging

You can run the Inspector (see https://modelcontextprotocol.io/docs/tools/inspector) to check the MCP features and run them manually.

From the repo root, setup the environment

$ export ALGOLIA_APP_ID=""
$ export ALGOLIA_INDEX_NAME=""
$ export ALGOLIA_API_KEY=""
$ export ALGOLIA_WRITE_API_KEY=""  # if you want to allow write operations, use your ADMIN key here
$ export MCP_ENABLED_TOOLS=""  # if you want to restrict the tools activated you can optionally specify a list
$ export MCP_SERVER_TYPE="stdio"  # optional: server type, either "stdio" (default) or "sse". If not set, defaults to "stdio"
$ export MCP_SSE_PORT="8080"  # optional: port for SSE server, default is 8080 (only used when MCP_SERVER_TYPE is "sse")

Move into the server directory, and rebuild (if necessary):

$ cd cmd/mcp
$ go build # might already be up-to-date

Run the MCP inspector on the server:

$ npx @modelcontextprotocol/inspector ./mcp

Using with Ollama

You can actually run a local mcphost (which orchestrates the MCP servers for you), and then use them with other models locally via Ollama.

We are using https://github.com/mark3labs/mcphost for this.

As per the README you need a a config file, so you can copy the Claude one, and put it somewhere sensible so you can use it on the command line (for example ~/mcp.json)

{
   "mcpServers": {
      "algolia": {
         "command": "/path/to/the/repo/cmd/mcp/mcp",
         "env": {
            "ALGOLIA_APP_ID": "<APP_ID>",
            "ALGOLIA_INDEX_NAME": "<INDEX_NAME>",
            "ALGOLIA_API_KEY": "<API_KEY>",
            "MCP_ENABLED_TOOLS": "",  /* optional: specify which tools to enable (e.g., "search,collections") */
            "MCP_SERVER_TYPE": "stdio",  /* optional: server type, either "stdio" (default) or "sse". If not set, defaults to "stdio" */
            "MCP_SSE_PORT": "8080"  /* optional: port for SSE server, default is 8080 (only used when MCP_SERVER_TYPE is "sse") */
         }
      }
   }
}

By default, all available tools are enabled when MCP_ENABLED_TOOLS is empty or not set. If you want to enable only specific tools, you can set this variable to a comma-separated list of tool names. Available tools are: abtesting, analytics, collections, monitoring, querysuggestions, recommend, search, search_read, search_write, usage.
You can now run it directly (no need to check out the repo):

$ go run github.com/mark3labs/mcphost@latest --config ~/mcp.json -m ollama:qwen2.5:3b

FAQ

What sort of things can I do once I install this MCP?

Here are some sample prompts to seed your imagination:

  • “Search all products in the index where brand = ‘Nike’ and price < 100.”
  • “Add this JSON object to the blog_posts index.”
  • “Update the searchable attributes for the recipes index to include ingredients.”
  • “Configure my index to rank nebula_award winners higher”

Where can I read more about the Algolia MCP server?

Check out this blog post including an embedded demo video.

Resource templates and root are not supported by Claude desktop right now

This is a weird one, since there is a bunch of content online showing the templates, maybe it's just not GA yet.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.