Merge pull request #10514 from liamsommer-mx/mcp-mistral-updates

Karuna-Mendix · web-flow · commit 53cecc232f66 · 2025-12-24T09:47:34.000+05:30
MCP Mistral MxCloudGenAI updates
diff --git a/content/en/docs/marketplace/genai/_index.md b/content/en/docs/marketplace/genai/_index.md
@@ -53,10 +53,11 @@ Supercharge your applications with Mendix's Agents Kit. This powerful set of com
 | [Blank GenAI App](https://marketplace.mendix.com/link/component/227934) | Start from scratch to create a new application with GenAI capabilities and without any dependencies. | Starter App | 10.24 |
 | [Conversational UI](/appstore/modules/genai/conversational-ui/) | Create a Conversational UI or monitor token consumption in your app. | UI Module | 10.24 |
 | [GenAI Commons](/appstore/modules/genai/commons/) | Common capabilities that allow all GenAI connectors to be integrated with the other modules. You can also implement your own connector based on this. | Common Module | 10.24 |
-| [GenAI Showcase App](https://marketplace.mendix.com/link/component/220475) | Understand what you can build with generative AI. Understand how to implement the Mendix Cloud GenAI, OpenAI, and Amazon Bedrock connectors and how to integrate them with the Conversational UI module. |Showcase App | 10.24 |
-| [MCP Client](https://marketplace.mendix.com/link/component/244893) | Access tools and prompts available via MCP (Model Context Protocol) inside of your Mendix app and add them to LLM requests. | Connector Module | 10.24 |
-| [MCP Server](https://marketplace.mendix.com/link/component/240380) | Make your Mendix business logic available to any agent in your enterprise landscape with the Mendix MCP Server module. Expose reusable prompts, including the ability to use prompt parameters. List and run actions implemented in the application as a tool. | Module | 10.24 |
+| [GenAI Showcase App](https://marketplace.mendix.com/link/component/220475) | Understand what you can build with generative AI. Understand how to implement the Mendix Cloud GenAI, OpenAI, and Amazon Bedrock connectors and how to integrate them with the Conversational UI module. | Showcase App | 10.24 |
+| [MCP Client](/appstore/modules/genai/mcp-modules/mcp-client/) | Access tools and prompts available via MCP (Model Context Protocol) inside of your Mendix app and add them to LLM requests. | Connector Module | 10.24 |
+| [MCP Server](/appstore/modules/genai/mcp-modules/mcp-server/) | Make your Mendix business logic available to any agent in your enterprise landscape with the Mendix MCP Server module. Expose reusable prompts, including the ability to use prompt parameters. List and run actions implemented in the application as a tool. | Module | 10.24 |
 | [Mendix Cloud GenAI Connector](/appstore/modules/genai/mx-cloud-genai/MxGenAI-connector/) | Connect to Mendix Cloud and utilize Mendix Cloud GenAI resource packs directly within your Mendix application. | Connector Module | 10.24 |
+| [Mistral Connector](/appstore/modules/genai/reference-guide/external-connectors/mistral/) | Connect to Mistral AI. | Connector Module | 10.24 |
 | [OpenAI Connector](/appstore/modules/genai/openai/) | Connect to (Azure) OpenAI. | Connector Module | 10.24 |
 | [PgVector Knowledge Base](/appstore/modules/genai/pgvector/) | Manage and interact with a PostgreSQL *pgvector* Knowledge Base. | Connector Module | 10.24 |
 | [RFP Assistant Starter App / Questionnaire Assistant Starter App](https://marketplace.mendix.com/link/component/235917) | The RFP Assistant Starter App and the Questionnaire Assistant Starter App leverage historical question-answer pairs (RFPs) and a continuously updated knowledge base to generate and assist in editing responses to RFPs. This offers a time-saving alternative to manually finding similar responses and enhancing the knowledge management process.  | Starter App | 10.24 |
@@ -69,31 +70,34 @@ Older versions of the marketplace modules and GenAI Showcase App are available i
 Mendix connectors offer direct support for the following models:
 
 | Architecture | Models | Category | Input | Output | Additional capabilities |
-|--------------|---------------------|---------------------|-------------------|-----------|-------------------------|
+| -------------- | --------------------- | --------------------- | ------------------- | ----------- | ----------------------- |
 | Mendix Cloud GenAI | Anthropic Claude 3.5 Sonnet, Anthropic Claude 3.7 Sonnet, Anthropic Claude 4.0 Sonnet | Chat Completions | text, image, document | text | Function calling |
 | | Cohere Embed English, Cohere Embed Multilingual | Embeddings | text | embeddings | |
 | Azure / OpenAI | gpt-4, gpt-4-turbo, gpt-4o, gpt-4o mini, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-5.0, gpt-5.0-mini, gpt-5.0-nano | Chat completions | text, image, document (OpenAI only) | text | Function calling |
 | | DALL·E 2, DALL·E 3, gpt-image-1 | Image generation | text | image | |
-| | text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large     | Embeddings | text | embeddings| |
+| | text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large | Embeddings | text | embeddings | |
+| Mistral | Mistral Large 3, Mistral Medium 3.1, Mistral Small 3.2, Ministral 3 (3B, 8B, 14B), Magistral (Small, Medium) | Chat Completions | text, image | text | Function calling |
+| | Codestral, Devstral (Small, Medium), Open Mistral 7B, Mistral Nemo 12B | Chat Completions | text | text | Function calling |
+| | Mistral Embed, Codestral Embed | Embeddings | text | embeddings | |
 | Amazon Bedrock | Amazon Titan Text G1 - Express, Amazon Titan Text G1 - Lite, Amazon Titan Text G1 - Premier | Chat Completions | text, document (except Titan Premier) | text | |
-| | AI21 Jamba-Instruct | Chat Completions | text | text |  |
-| | AI21 Labs Jurassic-2 (Text) | Chat Completions | text | text |  |
+| | AI21 Jamba-Instruct | Chat Completions | text | text | |
+| | AI21 Labs Jurassic-2 (Text) | Chat Completions | text | text | |
 | | Amazon Nova Pro, Amazon Nova Lite | Chat Completions | text, image, document | text | Function calling |
 | | Amazon Titan Image Generator G1 | Image generation | text | image | |
-| | Amazon Titan Embeddings Text v2 | Embeddings | text | embeddings| |
-| | Anthropic Claude 2.0, Anthropic Claude 2.1| Chat Completions | text, document | text | |
-| | Anthropic Claude 3 Sonnet, Anthropic Claude 3.5 Sonnet, Anthropic Claude 3.5 Sonnet v2, Anthropic Claude 3 Haiku, Anthropic Claude 3 Opus, Anthropic Claude 3.5 Haiku, Anthropic Claude 3.7 Sonnet, Anthropic Claude 4 Sonnet  | Chat Completions | text, image, document | text | Function calling |
+| | Amazon Titan Embeddings Text v2 | Embeddings | text | embeddings | |
+| | Anthropic Claude 2.0, Anthropic Claude 2.1 | Chat Completions | text, document | text | |
+| | Anthropic Claude 3 Sonnet, Anthropic Claude 3.5 Sonnet, Anthropic Claude 3.5 Sonnet v2, Anthropic Claude 3 Haiku, Anthropic Claude 3 Opus, Anthropic Claude 3.5 Haiku, Anthropic Claude 3.7 Sonnet, Anthropic Claude 4 Sonnet | Chat Completions | text, image, document | text | Function calling |
 | | Cohere Command | Chat Completions | text, document | text | |
 | | Cohere Command Light | Chat Completions | text | text | |
 | | Cohere Command R, Cohere Command R+ | Chat Completions | text, document | text | Function calling |
 | | Cohere Embed English, Cohere Embed Multilingual | Embeddings | text | embeddings | |
 | | DeepSeek, DeepSeek-R1 | Text | text | document | |
-| | Meta Llama 2, MetaLlama 3| Chat Completions | text, document | text | |
-| | Meta Llama 3.1| Chat Completions | text, document | text | Function calling |
+| | Meta Llama 2, MetaLlama 3 | Chat Completions | text, document | text | |
+| | Meta Llama 3.1 | Chat Completions | text, document | text | Function calling |
 | | Mistral AI Instruct | Chat Completions | text, document | text | |
 | | Mistral Large, Mistral Large 2 | Chat Completions | text, document | text | Function calling |
 | | Mistral Small | Chat Completions | text | text | Function calling |
-| | OpenAI gpt-oss-20B, gpt-oss-120b  | Chat Completions | text | text | |
+| | OpenAI gpt-oss-20B, gpt-oss-120b | Chat Completions | text | text | |
 
 For more details on limitations and supported model capabilities for the Bedrock Converse API used in the ChatCompletions operations, see [Supported models and model features](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-supported-models-features.html) in the AWS documentation.
 
diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md
@@ -49,7 +49,7 @@ While changing the model version, note the following:
 {{% /alert %}}
 
 {{% alert color="info" %}}
-Ensure you are using Mendix Cloud GenAI Connector version 5.3.0 to support the latest Cohere Embed v4 model. 
+Ensure you are using Mendix Cloud GenAI Connector version 5.3.0 and above to support the latest Cohere Embed v4 model. To see the upgraded model version reflected in your GenAI Connector after upgrading, make sure you are using Mendix Cloud GenAI Connector version 5.4.0 and above.
 {{% /alert %}}
 
 ### Team
diff --git a/content/en/docs/marketplace/genai/reference-guide/mcp-modules/mcp-client.md b/content/en/docs/marketplace/genai/reference-guide/mcp-modules/mcp-client.md
@@ -18,10 +18,7 @@ If the tool resides within the same Mendix application, you can integrate it wit
 
 ### Limitations {#limitations}
 
-The current version has the following limitations:
-
-* Tools and prompt messages can only return String content.
-* Only HTTP+SSE transport is currently supported to communicate with MCP servers.
+The current version has the following limitation: Tools and prompt messages can only return String content.
 
 {{% alert color="info" %}}
 Note that the MCP Client module is still in its early version, and newer versions may include breaking changes. Since both the open-source protocol and the Java SDK are still evolving and regularly updated, these changes may also affect this module.
@@ -52,7 +49,7 @@ See the **Example Implementations** folder inside the module containing example
 
 #### Protocol Version
 
-When creating an MCP client, specify a `ProtocolVersion`. On the official MCP documentation, you can review the differences between the protocol versions in the [changelog](https://modelcontextprotocol.io/specification/2025-03-26/changelog). The MCP Client module currently only supports `v2024-11-05` and the HTTP+SSE transport. MCP servers should support the same version as the client. Note that Mendix supports the capabilities provided by the MCP Java SDK.
+When creating an MCP client, specify a `ProtocolVersion`. On the official MCP documentation, you can review the differences between the protocol versions in the [changelog](https://modelcontextprotocol.io/specification/2025-03-26/changelog). The MCP Client module currently supports `v2024-11-05` with the HTTP+SSE transport and `v2025-03-26` with the streamable HTTP transport, which is the new standard method. MCP servers should support the same version as the client. Note that Mendix supports the capabilities provided by the MCP Java SDK.
 
 ### Discovering Resources {#discover-resources}
 
@@ -64,7 +61,7 @@ In general, prompts are often exposed to end-users in a chat to start or continu
 
 To use a prompt from an MCP Server, you can use the `Get Prompt` action to receive one or multiple `PromptMessages` from the server associated with the `PromptResult` object. Similarly, to use a tool, you can use the `Call Tool` action to receive a `ToolResult` object that contains the return message of the tool.
 
-For both actions, you can pass an `ArgumentCollection` if the prompt or tool requires arguments (the information is available from the [discovered resources](#discover-resources)). The actions `Initialize Argument Collection` and `Argument Collection: Add New Input` help you construct the input for those actions.
+For both actions, you can pass an `ArgumentCollection` if the prompt or tool requires arguments (the information is available from the [discovered resources](#discover-resources)). The actions `Argument Collection: Initialize` and `Argument Collection: Add New Input` help you construct the input for those actions.
 
 ### Using MCP Client Module with GenAI Commons and Conversational UI {#use-with-genai-commons}
 
@@ -89,7 +86,7 @@ The **Documentation** pane displays the documentation for the currently selected
 
 ### MCP Client Cannot Connect to the MCP Server
 
-There are several possible reasons why the client cannot connect to your server. First, check the MCP Client logs. Then, verify that the endpoint is set to the correct URL and that the server supports the same protocol version and transport method (HTTP + SSE) as the client. If authentication is required, make sure to pass the necessary information via HTTP headers.
+There are several possible reasons why the client cannot connect to your server. First, check the MCP Client logs. Then, verify that the endpoint is set to the correct URL and that the server supports the same protocol version and transport method (HTTP + SSE or Streamable HTTP) as the client. If authentication is required, make sure to pass the necessary information via HTTP headers.
    
 ## Read More
 
diff --git a/content/en/docs/marketplace/genai/reference-guide/mcp-modules/mcp-server.md b/content/en/docs/marketplace/genai/reference-guide/mcp-modules/mcp-server.md
@@ -23,9 +23,8 @@ The current version has the following limitations:
 
 * Tools can only return String values, either directly as String type or using the `TextContent` entity.
 * Prompts can only return a single message.
-* The client connection remains active for only 15 minutes, as the Mendix runtime currently does not support async requests.
 * Running an MCP Server is currently only supported on single-instance environments.
-* The tool fails to return responses with large payloads to the client successfully. This issue is currently under investigation.
+* For HTTP+SSE transport (protocol version `v2024-11-05`), tool execution with large payloads are not returned successfully.
 
 Note that the MCP Server module is still in its early version and latest versions may include breaking changes. Since both the open-source protocol and the Java SDK are still evolving and regularly updated, these changes may also affect this module.
 
@@ -39,7 +38,7 @@ If you start from a standard Mendix blank app, or have an existing project, you
 
 ### Create MCP Server {#create-server}
 
-The `Create MCP Server` action initializes an MCP server in the Mendix runtime, creates and returns the `MCPServer` object. You can use the created `MCPServer` to add tools or prompts. The `Path` attribute determines how external systems can reach the MCP server, that means this value needs to be known to the the MCP Client (usually set in a configuration file). After the action gets triggered, the server becomes available for external clients to connect. As mentioned in the [limitations](#limitations) section above, the connection remains active for only 15 minutes.
+The `Create MCP Server` action initializes an MCP server in the Mendix runtime, creates and returns the `MCPServer` object. You can use the created `MCPServer` to add tools or prompts. The `Path` attribute determines how external systems can reach the MCP server, that means this value needs to be known to the the MCP Client (usually set in a configuration file). After the action gets triggered, the server becomes available for external clients to connect. Note that the path must not be `sse` or `mcp`, and must not end with `/sse`or `/mcp`, as these are reserved endpoints.
 
 Based on your use case, this action can be triggered manually by an admin if wrapped around a microflow accessible in the UI, via an after start-up microflow, or by any other microflow such as a scheduled event.
 
@@ -62,7 +61,7 @@ The `User` returned in the microflow is used for all subsequent prompt and tool
 
 #### Protocol Version
 
-When creating an MCP server, you need to specify a `ProtocolVersion`. On the official MCP documentation, you can review the differences between the protocol versions in the [changelog](https://modelcontextprotocol.io/specification/2025-03-26/changelog). The MCP Server module currently only supports `v2024-11-05` and the HTTP+SSE transport. MCP Clients, that need to connect to a Mendix MCP server, should support the same version. Note that Mendix follows the offered capabilities of the MCP Java SDK.
+When creating an MCP server, you need to specify a `ProtocolVersion`. On the official MCP documentation, you can review the differences between the protocol versions in the [changelog](https://modelcontextprotocol.io/specification/2025-03-26/changelog). The MCP Server module currently only supports `v2024-11-05` with the HTTP+SSE transport and `v2025-03-25` with the streamable HTTP transport, which is the new standard transport. MCP Clients, that need to connect to a Mendix MCP server, should support the same version. Note that Mendix follows the offered capabilities of the MCP Java SDK.
 
 ### Add Tools
 
@@ -76,7 +75,7 @@ The selected microflow must adhere to the following principles:
 For an example, see the `Example Implementations` folder inside of the module.
 
 {{% alert color="warning" %}}
-Function calling is a highly effective capability and should be used with caution.
+Function/tool calling is a highly effective capability and should be used with caution.
 
 Mendix strongly recommends keeping the user in the loop (such as by using confirmation logic which is integrated into many MCP clients), if the tool microflows have a potential impact on the real world on behalf of the end-user. Examples include sending emails, posting content online, or making purchases. In such cases, evaluate the use cases and implement security measures when exposing these tools to external AI systems via MCP.
 {{% /alert %}}
