MCP tools

This is a beta feature according to Algolia’s Terms of Service (“Beta Services”).

MCP tools extend your agent’s capabilities to enable integration with Algolia MCP Server and third-party services (such as weather, CRM, and inventory systems), and custom APIs.

Key capabilities

External integrations: connect to weather APIs, CRM platforms, inventory systems, or payment processors
Algolia MCP Server: share your Algolia indices across multiple AI platforms with centralised configuration
Multi-tenant support: override authentication tokens at request time for per-user credentials
Tool filtering: filter and rename exposed tools for precise agent control
Secure storage: automatic credential encryption at rest
Local development: use ngrok to expose local MCP servers during development
Timeout protection: 10-second timeout for reliable performance

Algolia encrypts credentials before storing them. Supports runtime header overrides for multi-tenant apps. For more information, see MCP security.

MCP servers

Algolia MCP Server: a pre-configured server that exposes your Algolia indices across multiple AI platforms. Create instances from the Algolia dashboard MCP servers page. For more information, see Algolia MCP Server
Third-party MCP servers: connect to external services like weather APIs, CRM platforms, inventory systems, or custom APIs. Browse the official MCP registry for pre-built servers.

MCP tools use the Streamable HTTP](https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http) transport method. STDIO and SSE aren’t supported.

Connect MCP tools to your agent

From the dashboard
With the API

Prepare your MCP server

For Algolia MCP Server:

Go to the MCP servers page
Click Create MCP server
Select the indices you want to expose (for example, products, articles)
Add descriptions to help the AI choose the correct
Click Save
Copy the generated MCP server URL (format: https://mcp.{REGION}.algolia.com/1/{UNIQUE_ID}/mcp)

For more information, see Algolia MCP Server.For external MCP servers:

Find a server in the official MCP registry
Build your own MCP server following the MCP specification
For local development, use ngrok to expose your local MCP server with a public URL:
```
ngrok http 3000
```
ngrok generates a public URL (for example, https://abc123.ngrok.io) that you can use in Agent Studio.

Add MCP tool to your agent

From the Agent Studio agent edit view in the Algolia dashboard:

Click Add tool > MCP Tool
Configure the MCP server connection:

Name: unique identifier (no spaces, alphanumeric, underscores, and hyphens only)
URL: your MCP server HTTP streaming endpoint
- Algolia MCP: https://mcp.{REGION}.algolia.com/1/{UNIQUE_ID}/mcp
- External: your MCP server URL (for example, https://weather-api.example.com/mcp)
Authorization token (optional): JWT bearer token for authentication
- For Algolia MCP: use the format {APP_ID}:{SEARCH_API_KEY}
- For external APIs: your API key or token as provided by the service

Click Connect to fetch available tools from the MCP server

Select tools and set approval level

Once connected, the dashboard displays all available tools from the MCP server:

Select tools: choose which tools to enable for your agent

Select all tools with one click, or
Select specific tools individually

Set approval level: configure how the agent uses these tools

Never require approval: agent can call tools automatically (recommended for most use cases)
Always require approval: user must approve each tool call before it runs (useful for sensitive operations)

Click Add tools to complete the configuration

Use tools like ngrok to expose your local MCP server during development. This creates a public HTTPS URL that Agent Studio can connect to, letting you test and debug your custom MCP server without deploying it to production.

JSON tool definition:

JSON

{
  "type": "mcp_tools",
  "name": "weather_service",
  "url": "https://weather-api.example.com/mcp",
  "transport": "streamable_http",
  "headers": {
    "Authorization": "Bearer YOUR_API_KEY"
  },
  "allowedTools": {
    "get_forecast": {
      "alias": "check_weather"
    },
    "get_historical_data": true,
    "admin_endpoint": false
  }
}

Required fields

type: must be "mcp_tools"
name: unique identifier for this MCP server (3-32 characters, start with letter, alphanumeric + underscore/hyphen, no spaces)
url: HTTP or HTTPS endpoint of the MCP server (in a valid URL format)
transport: must be "streamable_http" (SSE supported, STDIO not supported)
headers: dictionary of HTTP headers (use {} if no authentication needed, maximum of 10 entries)

Optional fields

allowedTools: filter and rename tools from the MCP server
- Omit entirely: all tools from MCP server are enabled with original names
- Specify object: only listed tools are enabled
  - true: enable tool with original name
  - false: block tool (same as omitting, but explicit)
  - {"alias": "new_name"}: rename tool (3-32 characters, same naming rules as name)

Tool filtering behavior

When allowedTools is specified, only explicitly listed tools with true or an alias are available. Tools set to false or not mentioned are blocked. For example:

Algolia MCP Server
External MCP server with tool filtering

JSON

{
  "type": "mcp_tools",
  "name": "algolia_mcp",
  "url": "https://mcp.us.algolia.com/1/abc123/mcp",
  "transport": "streamable_http",
  "headers": {
    "Authorization": "Bearer YOUR_APP_ID:YOUR_SEARCH_API_KEY"
  }
}

JSON

{
  "type": "mcp_tools",
  "name": "weather_api",
  "url": "https://weather-api.example.com/mcp",
  "transport": "streamable_http",
  "headers": {
    "Authorization": "Bearer YOUR_API_KEY"
  },
  "allowedTools": {
    "get_forecast": true,
    "get_alerts": {"alias": "weather_alerts"}
  }
}

Result: only get_forecast and weather_alerts (renamed from get_alerts) are available.

Security notes

Authorization headers are encrypted at rest
JWT Bearer token authentication supported
10-second timeout for all MCP connections
Runtime header overrides available for multi-tenant scenarios.

For complete configuration details, see the Agent Studio API reference.

Search and Discovery platform

Optimization and Personalization

AI-powered experiences

Production and scale

MCP servers

Connect MCP tools to your agent

Required fields

Optional fields

Tool filtering behavior

Security notes

See also

Search and Discovery platform

Optimization and Personalization

AI-powered experiences

Production and scale

​MCP servers

​Connect MCP tools to your agent

​Required fields

​Optional fields

​Tool filtering behavior

​Security notes

​See also

MCP servers

Connect MCP tools to your agent

Required fields

Optional fields

Tool filtering behavior

Security notes

See also