Connect Algolia to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Algolia, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Algolia + Microsoft Copilot

Let your AI search and inspect your Algolia indices: list indices, search and browse records, read settings, synonyms and Rules, see top searches and searches without results and, with your confirmation, add or update records.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

ALGOLIA_APP_ID, ALGOLIA_API_KEY, ALGOLIA_ANALYTICS_REGION

Step 1 — Get credentials

1. Open the Algolia dashboard at Settings → API Keys (https://dashboard.algolia.com/account/api-keys) and copy the Application ID into ALGOLIA_APP_ID.
2. Create a dedicated key under All API keys → New API key instead of reusing the Admin key. Give it a description such as AnythingMCP, optionally limit it to some indices, and give it the ACL search, browse, listIndexes, settings and analytics. Paste it into ALGOLIA_API_KEY.
3. Set ALGOLIA_ANALYTICS_REGION to us or de, the analytics region shown in the dashboard under Settings → Infrastructure → Analytics. Most applications use us.
4. Install the connector. The connection check lists your indices, as algolia_list_indices does.

Why not the Search-Only key: the connection check needs the listIndexes ACL. Algolia's default Search-Only API key has only search, so it fails the check with 403 "Method not allowed with this API key", even though search itself would work with it. Create the custom read key from step 2 instead. Do not use the Admin API key either: it can delete indices and manage keys, and no tool here needs that. Every key's ACL, index limits and rate limit are listed under Settings → API Keys → All API keys.

What the AI can do: search an index the way your site does, with typo tolerance, filters such as brand:Apple AND price < 500, facet counts and paging (10 hits by default, at most 100); read records in bulk with algolia_browse; and read single records, index settings, synonyms and Rules to explain why results rank the way they do. Searches made by the AI stay out of your analytics.

Search analytics: algolia_top_searches, algolia_no_result_searches (what people look for and do not find), algolia_top_hits and algolia_search_count. The default period is the last 8 days. Analytics lag behind by up to a few hours, and an index needs traffic before it has any data.

Writes ask first: algolia_save_object adds a record or replaces it entirely, and algolia_partial_update_object changes some of its attributes. Before each, the AI shows you the index, the objectID and the content and waits for your yes. Both need the addObject ACL in addition, so a read key stays read-only. Algolia applies changes in the background, and they are searchable a moment later.

Switched off at install: algolia_delete_object, which deletes a record for good. An administrator turns it on deliberately, and it needs the deleteObject ACL.

Common errors: 403 "Invalid Application-ID or API key": the Application ID or the key is wrong, or the key was deleted. 401 "Invalid credentials" means the same on the Analytics API; check the analytics region too. 403 "Method not allowed with this API key": the key lacks an ACL. "Index not allowed with this API key": the key is limited to other indices. 404: the index or record does not exist; index names are case-sensitive. 429: the key hit its rate limit.

The connector does not create, copy or delete indices, change settings, synonyms or Rules, manage API keys, or cover Insights events, Recommend, Query Suggestions or the Crawler.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Algolia tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "Which Algolia indices do we have, and how many records does each hold?"
• "What did people search for most on the products index in the last 30 days, and which searches returned nothing?"
• "Search the products index for running shoes with the filter brand:Nike and show me the top 10 with price."
• "Why does record 4711 rank so low for 'sneakers'? Check the index settings, synonyms and Rules."
• "Change the price of record 4711 in the products index to 89.90. Show me the change first."

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse