Context Portal (ConPort) MCP Server

What does “Context Portal” MCP Server do?

Context Portal (ConPort) is a memory bank MCP server designed to supercharge AI assistants and developer tools within IDEs by managing structured project context. Acting as a project-specific knowledge graph, ConPort enables powerful Retrieval Augmented Generation (RAG), allowing AI to quickly access and utilize relevant project information. It stores important project data such as decisions, tasks, progress, architectural patterns, glossaries, and specifications in a structured way. This helps AI assistants provide more accurate and context-aware responses, enhancing development workflows by making project knowledge easily searchable and actionable.

List of Prompts

No prompt templates are mentioned in the available repository files or documentation.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No explicit MCP resources are listed in the available repository files or documentation.

List of Tools

No specific tools are described or listed from server.py or other server logic in the available repository files or documentation.

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Project Knowledge Management
  Store and retrieve key project decisions, glossaries, specifications, and architectural patterns, enabling AI assistants to provide project-specific guidance and context.

• Context-Aware AI Coding Assistance
  Allow AI assistants within IDEs to access structured project memory, improving code suggestions and explanations by leveraging project history and terminology.

• Retrieval Augmented Generation (RAG)
  Enhance LLM-powered assistants by providing them with up-to-date and relevant project data for more accurate and context-rich responses.

• Project Progress Tracking
  Keep a structured record of completed tasks, outstanding issues, and ongoing work, so AI agents can summarize or report project status.

How to set it up

Windsurf

1. Ensure prerequisites are installed (e.g., Node.js, Python as required).
2. Locate your Windsurf configuration file.
3. Add the Context Portal MCP Server with a configuration similar to:

   {
     "mcpServers": {
       "context-portal": {
         "command": "npx",
         "args": ["@context-portal/mcp-server@latest"]
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify that the setup is active and the MCP server is reachable.

Claude

1. Confirm prerequisites (such as the required runtime).
2. Open Claude’s configuration file.
3. Insert the following JSON snippet under MCP servers:

   {
     "mcpServers": {
       "context-portal": {
         "command": "npx",
         "args": ["@context-portal/mcp-server@latest"]
       }
     }
   }
   

4. Save the config and restart Claude.
5. Check connectivity to make sure the MCP server is running.

Cursor

1. Install any required dependencies.
2. Edit the Cursor MCP configuration file.
3. Add Context Portal MCP Server:

   {
     "mcpServers": {
       "context-portal": {
         "command": "npx",
         "args": ["@context-portal/mcp-server@latest"]
       }
     }
   }
   

4. Save and restart the Cursor IDE.
5. Confirm the MCP server is registered and available.

Cline

1. Meet all prerequisites (see project requirements).
2. Find Cline’s MCP servers configuration section.
3. Register Context Portal MCP server:

   {
     "mcpServers": {
       "context-portal": {
         "command": "npx",
         "args": ["@context-portal/mcp-server@latest"]
       }
     }
   }
   

4. Save the config and restart Cline.
5. Validate that the MCP server is active.

Securing API Keys:
To securely provide API keys, use environment variables. Here’s an example of how to include them in your configuration:

{
  "mcpServers": {
    "context-portal": {
      "command": "npx",
      "args": ["@context-portal/mcp-server@latest"],
      "env": {
        "CONPORT_API_KEY": "${CONPORT_API_KEY}"
      },
      "inputs": {
        "apiKey": "${CONPORT_API_KEY}"
      }
    }
  }
}

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:

{
  "context-portal": {
    "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 “context-portal” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

Context Portal MCP (ConPort) provides a clear overview and strong use case articulation, but lacks explicit technical documentation for prompts, tools, and resources in the available public files. The setup instructions and API key guidance are helpful. Overall, its utility is evident, but deeper server details would enhance its score.

MCP Table rating: 6/10

MCP Score