MCP + Solace Agent Mesh: The Deep Dive

Solace Agent Mesh
1

Agents in Solace Agent mesh

Agents in Solace Agent Mesh are either created using the add agent GUI interface, authoring yaml configurations, or using the integrated Agent Builder for Enterprise environments. When we delve into the composition of agents, we find out that integrating MCP servers is as simple as adding a tool block with an MCP definition in the agent configuration. This abstraction makes it much easier to integrate MCP in the agent mesh deployment.

Read more about the The Anatomy of Agents in Solace Agent Mesh below :backhand_index_pointing_down:

A key important concept to remember is tools normalization: the ability to combine different “category” of tools within a single agent, enabling comprehensive functionality through modular composition. For example, you might create an agent that uses MCP filesystem tools to read and write files, leverages built-in artifact management tools for data persistence, calls custom Python tools for domain-specific business logic, and connects to another MCP server for database access

For example, you might create an agent that uses MCP filesystem tools to read and write files, leverages built-in artifact management tools for data persistence, calls custom Python tools for domain-specific business logic, and connects to another MCP server for database access. For example, you might create an agent that uses MCP filesystem tools to read and write files, leverages built-in artifact management tools for data persistence, calls custom Python tools for domain-specific business logic, and connects to another MCP server for database access

tools: 
  # MCP filesystem server 
  - tool_type: mcp 
    connection_params: 
      type: stdio 
      command: "npx" 
      args: ["-y", "@modelcontextprotocol/server-filesystem", "/workspace"] 
   
  # Built-in artifact tools 
  - tool_type: builtin-group 
    group_name: "artifact_management" 
   
  # Custom business logic 
  - tool_type: custom 
    module_path: "my_company.custom_tools" 
   
  # Remote MCP database server 
  - tool_type: mcp 
    connection_params: 
      type: streamable-http 
      url: "https://internal-mcp.company.com/database"

Execution + A2A

Solace Agent Mesh has native MCP support built in; simply configured in the tools section of the Agent definition. Which means that connection, discovery of available tools, registration, authentication, authorization, and execution of tools is all handled natively within the framework abstracting away the nitty gritty details. Solace Agent Mesh even translates between A2A and MCP protocols behind the scenes.

MCP transport modes

We can define an MCP integration using one of the following key transport methods:

  1. Stdio - Simple local connections, great for development
  2. SSE (Server-Sent Events) - HTTP-based for remote servers with real-time updates
  3. Streamable HTTP - Combines REST simplicity with streaming capabilities
  4. Docker - Containerized deployment for isolated environments

To learn more about how MCP is integrated with Solace Agent Mesh read more here: MCP Integration | Solace Agent Mesh

If you have any questions feel free to join the conversation here; I’m curious how others are using MCP in their agentic journey!

1 Like