--- title: Get started with the Hosted Model Context Protocol (MCP) Server slug: pboe0358 canonical_url: https://docs.coveo.com/en/pboe0358/ collection: leverage-machine-learning source_format: adoc --- # Get started with the Hosted Model Context Protocol (MCP) Server The Coveo Hosted Model Context Protocol (MCP) Server enables Large Language Model (LLM) applications and AI agent frameworks to seamlessly access Coveo's enterprise search and retrieval capabilities. It empowers these apps and frameworks to dynamically invoke Coveo tools, such as [Search](#search-tool), [Fetch](#fetch-tool), [Answer](#answer-tool), and [Passage Retrieval](#passage-retrieval-tool) without the need for custom integrations, making it easier for end users to obtain secure, relevant, and context-aware responses grounded in enterprise data. > **Tip** > > For simplicity, the term _LLM app_ is used throughout this article to refer to both an LLM application (such as ChatGPT) and an AI agent framework (such as AWS Bedrock). ## Solution overview The Hosted MCP Server acts as an intermediary between LLM apps and Coveo's APIs, streamlining the process of tool invocation and data retrieval. The following diagram provides a high-level overview of the Hosted MCP Server solution: ![MCP Server solution overview | Coveo](https://docs.coveo.com/en/assets/images/leverage-machine-learning/mcp-solution-overview.png) [cols="2"] |=== |1 |The MCP client, which is integrated into the LLM app, communicates with the Hosted MCP Server to request access to specific tools based on end user prompts or tasks. |2 |The Hosted MCP Server processes these requests and routes them to the appropriate Coveo APIs based on the tool being invoked. |3 |The Coveo APIs execute the requested operations, retrieving relevant data or generating answers from your [indexed](https://docs.coveo.com/en/204/) content. |4 |The Hosted MCP Server then returns the results to the MCP client, enabling it to return or generate contextually relevant responses for end users. |=== ## Key benefits The Hosted MCP Server offers several benefits for organizations looking to enhance the capabilities of their LLM apps: * **Seamless integration**: The Hosted MCP Server standardizes tool access, making Coveo's [Search](#search-tool), [Fetch](#fetch-tool), [Answer](#answer-tool), and [Passage Retrieval](#passage-retrieval-tool) APIs accessible by leading third-party [LLM apps](https://docs.coveo.com/en/pbog0163/) at runtime. * **Enhanced relevance and context**: By leveraging Coveo's powerful search and retrieval capabilities, the Hosted MCP Server ensures that responses generated by LLM apps are grounded in contextually relevant information from your [indexed](https://docs.coveo.com/en/204/) content. * **Plug-and-play compatibility**: The Hosted MCP Server is compatible with leading third-party [LLM apps](https://docs.coveo.com/en/pbog0163/), allowing organizations to choose the best client apps for their specific use cases. * **Scalability**: The Hosted MCP Server is designed to handle large request volumes, making it suitable for enterprise workloads. * **Enterprise-grade security**: The Hosted MCP Server adheres to Coveo's robust security standards, ensuring that data access is secure and compliant with organizational policies. ## Which tool is right for your implementation? The Hosted MCP Server offers the [Search](#search-tool), [Fetch](#fetch-tool), [Answer](#answer-tool), and [Passage Retrieval](#passage-retrieval-tool) tools that LLM apps can use to access and retrieve information from your [indexed](https://docs.coveo.com/en/204/) content. The tools you choose to use depend on the specific requirements of your application and the nature of end user prompts and [queries](https://docs.coveo.com/en/231/). These tools can be used independently or in combination to provide a comprehensive solution for various use cases. The following sections provide an overview of each tool, highlighting their key features and typical use cases. ### Search tool The Search tool leverages the [Coveo Search API](https://docs.coveo.com/en/52/) to perform full-text searches across your [indexed](https://docs.coveo.com/en/204/) content. It's useful for surfacing ranked [items](https://docs.coveo.com/en/210/) that match a [query](https://docs.coveo.com/en/231/), which helps end users find relevant information quickly. **Use case example** You want to build a research assistant that explores, filters, and reasons over results by executing [queries](https://docs.coveo.com/en/231/) to retrieve relevant [items](https://docs.coveo.com/en/210/) based on end user input. ### Fetch tool The Fetch tool leverages a function of the [Coveo Search API](https://docs.coveo.com/en/13/api-reference/search-api#tag/Search-V3/operation/dataStreamV3) to retrieve a specific [item](https://docs.coveo.com/en/210/) based on a unique identifier. It's particularly useful when direct access to a known [item](https://docs.coveo.com/en/210/), in the form of its full content, is required. **Use case example** You want to build an internal knowledge bot that can retrieve a specific policy document or technical manual when an employee requests a document ID or title. ### Answer tool The Answer tool leverages the [Coveo Answer API](https://docs.coveo.com/en/p3ob0090/) to generate answers using [Relevance Generative Answering (RGA)](https://docs.coveo.com/en/nbtb6010/). It's ideal for providing generated answers that are grounded in your [indexed](https://docs.coveo.com/en/204/) content. **Use case example** You want to build an autonomous support agent that answers or deflects tickets by providing end users with grounded generated answers using your official knowledge base and product documentation. ### Passage Retrieval tool The Passage Retrieval tool leverages the [Coveo Passage Retrieval API](https://docs.coveo.com/en/o86c8334/) to retrieve specific sections of text, known as _passages_, from your [indexed](https://docs.coveo.com/en/204/) content. It's useful for retrieving the most relevant passages for a given [query](https://docs.coveo.com/en/231/) so third-party LLM apps can use them to generate answers. **Use case example** You want to build a legal assistant that can generate answers to complex questions by retrieving pertinent passages from contracts and legal documents grounded in your enterprise data. ## Current limitations While the Hosted MCP Server significantly enhances the capabilities of LLM apps, there are some limitations to be aware of: * Effective tool selection by the LLM app depends on clear tool descriptions in your configuration, so plan to iterate and test descriptions to achieve reliable results. * Direct debugging capabilities aren't yet available. * Filtering options such as [facets](https://docs.coveo.com/en/198/) aren't yet available. ## Solution demo The following video[.footnote]^[[1](#functionality-cookies)]^ showcases the Hosted MCP Server solution, describing its key features and benefits for LLM apps.
-- 1. Functionality cookies are required to view this video. To enable this setting, click icon:dots-circle-horizontal[alt=dots-circle-horizontal,width=16] in the upper-right corner of the page, and then select **Cookie preferences** > **Functionality Cookies**. -- ## What's next? See [Manage Hosted MCP Server configurations](https://docs.coveo.com/en/q1mb0212/) for instructions on how to add, configure, and manage a Hosted MCP Server.