SearchUnify Model Context Protocol (MCP)

SearchUnify MCP is a Model Context Protocol (MCP) server that allows compatible AI clients to connect to SearchUnify and use SearchUnify capabilities as callable tools.

In this architecture, the AI application acts as the host, and SearchUnify MCP acts as the server that exposes tools the host can invoke during a conversation. This enables AI assistants to access SearchUnify-powered enterprise search and analytics directly within MCP-compatible environments.

SearchUnify MCP helps organizations bring trusted enterprise knowledge into AI workflows without building custom integrations for each client or assistant.

Note: MCP capabilities were added and backported in the Q2 ’25 release. If your SearchUnify instance is on this or a newer release, check with the Support or Professional Services team to confirm that the MCP-related updates are deployed on your instance.

What you can do with SearchUnify MCP

With SearchUnify MCP, a compatible AI client can:

  • search content indexed in SearchUnify,

  • discover available filters before refining a query,

  • retrieve search analytics and reporting data,

  • and use SearchUnify context directly within AI-assisted workflows.

This allows assistants to work with live SearchUnify data instead of relying only on static model knowledge.

Core capabilities

SearchUnify MCP currently supports the following capabilities:

  1. Search enterprise content

    The search tool allows an assistant to query SearchUnify using a search string, optional pagination, sorting, and facet-based filters.

  2. Discover filters dynamically

    The get-filter-options tool allows the assistant to retrieve available filter values for a query before narrowing the result set.

  3. Access search analytics

    The analytics tool allows the assistant to retrieve SearchUnify analytics reports, including zero-result queries, no-click queries, and search conversion data.

How SearchUnify MCP Works

At a high level, the interaction flow is simple: A user connects an MCP-compatible client to SearchUnify MCP. The client discovers the tools exposed by the server. The assistant invokes a SearchUnify MCP tool when needed. SearchUnify MCP authenticates the request and returns data from SearchUnify.

Supported Connection Models and Authentication Methods

SearchUnify MCP supports the following transport mechanisms:

  • HTTP transport for remotely hosted MCP deployments

  • stdio transport for locally spawned MCP server setups

Depending on your deployment model, SearchUnify MCP can run using http, stdio, or both.

Supported authentication methods

SearchUnify MCP supports the following authentication methods:

  • API Key

  • OAuth 2.0 Password Grant

  • OAuth 2.0 Client Credentials Grant

For most initial implementations, API key-based configuration is the simplest and fastest approach.

Before you begin

To use SearchUnify MCP, you need:

  • valid authentication credentials for SearchUnify,

  • a Search Client UID,

  • the required API scope access,

  • and an MCP-compatible client.

Note: If you plan to run the MCP server locally, Docker is also required.