Discourse MCP Server

What does “Discourse” MCP Server do?

The Discourse MCP Server is a Node.js implementation of the Model Context Protocol (MCP) designed to connect AI assistants with Discourse forums. It acts as a bridge, enabling AI systems to perform search operations on Discourse platforms via standardized MCP interfaces. By exposing Discourse search capabilities as tools, this server allows developers and AI workflows to query forum posts programmatically—automating knowledge retrieval, facilitating community management, and enhancing development environments that require contextual forum data. This integration streamlines operations such as post discovery and data extraction, making it easier for AI agents to surface relevant discussion threads or answers from Discourse-based communities.

List of Prompts

No prompt templates are mentioned in the available documentation or code.

List of Resources

No explicit resources are documented or described in the repository.

List of Tools

• search_posts
  • Allows searching posts on a configured Discourse forum.
  • Input: query (string)
  • Returns: An array of post objects matching the search criteria.

Use Cases of this MCP Server

• Automated Knowledge Retrieval
  • Developers can automate the extraction of relevant information from Discourse forums using AI, reducing manual search time.
• Community Management
  • Moderators or bots can efficiently identify specific posts or discussions, aiding in content curation and moderation.
• Customer Support Integration
  • Integrate forum search into support workflows to surface community solutions in response to user queries.
• Contextual AI Assistance
  • AI assistants can provide context-aware answers by searching relevant forum discussions and presenting helpful threads to users.

How to set it up

Windsurf

No setup instructions for Windsurf are provided in the repository.

Claude

1. Ensure Docker or Node.js/npx is installed on your system.
2. Open your claude_desktop_config.json configuration file.
3. Add the Discourse MCP Server under the mcpServers object with the following JSON snippet (choose Docker or npx):

Docker Example:

{
  "mcpServers": {
    "discourse": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e", "DISCOURSE_API_URL=https://try.discourse.org",
        "-e", "DISCOURSE_API_KEY=1234",
        "-e", "DISCOURSE_API_USERNAME=ash",
        "ashdev/discourse-mcp-server"
      ]
    }
  }
}

npx Example:

{
  "mcpServers": {
    "discourse": {
      "command": "npx",
      "args": [
        "-y",
        "@ashdev/discourse-mcp-server"
      ],
      "env": {
        "DISCOURSE_API_URL": "https://try.discourse.org",
        "DISCOURSE_API_KEY": "1234",
        "DISCOURSE_API_USERNAME": "ash"
      }
    }
  }
}

4. Save the file and restart Claude Desktop.
5. Verify the setup by ensuring the Discourse MCP Server is running and accessible.

Securing API Keys:
Environment variables are used to store sensitive information. For example:

"env": {
  "DISCOURSE_API_URL": "https://try.discourse.org",
  "DISCOURSE_API_KEY": "1234",
  "DISCOURSE_API_USERNAME": "ash"
}

Cursor

No setup instructions for Cursor are provided in the repository.

Cline

No setup instructions for Cline are provided in the repository.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "discourse": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “discourse” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available documentation and code, Discourse MCP Server is minimal but functional, exposing a single useful tool and providing clear setup for Claude. However, it lacks prompts, resource definitions, and broader platform support, limiting its extensibility. Roots and sampling support are not mentioned.
Rating: 4/10

MCP Score