StitchAI MCP Server

What does “StitchAI” MCP Server do?

StitchAI MCP Server is a Model Context Protocol (MCP) server implementation designed to power Stitch AI’s memory management system. It acts as a decentralized knowledge hub for AI, enabling seamless connections between AI assistants and external data sources, APIs, and services. Through this server, AI agents can efficiently create, retrieve, and manage “memories”—structured pieces of information that enhance their contextual awareness and reasoning capabilities. By exposing a set of tools for memory operations, StitchAI MCP Server streamlines workflows such as storing insights, tracking contextual data, or retrieving relevant information. This empowers developers to build AI solutions that are more context-aware, interactive, and capable of sophisticated information handling.

List of Prompts

No prompt templates were found in the available documentation or code.

List of Resources

No explicit MCP “resources” were found in the available documentation or code.

List of Tools

• createMemory: Allows the AI agent to create a new memory with specified content and metadata.
• getMemory: Retrieves a specific memory by its identifier, enabling recall of stored information.
• listMemories: Lists all available memories, providing an overview of the stored knowledge base.
• deleteMemory: Deletes a specific memory by its identifier, allowing management and pruning of the memory store.

Use Cases of this MCP Server

• Long-term Context Management: Enables AI agents to store and recall information across multiple interactions or sessions, improving continuity and user experience.
• Agent Knowledge Base Construction: Assists developers in building persistent knowledge bases for AI agents, supporting more advanced reasoning and context tracking.
• Data Annotation and Storage: Facilitates the capture of important data points or annotations during conversations, which can be retrieved and referenced later.
• Collaborative Memory for Multi-Agent Systems: Allows multiple agents to share and manage a common pool of memories, fostering collaborative intelligence.
• Memory Pruning and Organization: Provides tools for deleting and listing memories, enabling efficient management and organization of contextual data.

How to set it up

Windsurf

1. Ensure Node.js is installed on your system.
2. Open your Windsurf configuration file.
3. Add the StitchAI MCP Server to the mcpServers section with the command and arguments.
4. Save the configuration and restart Windsurf.
5. Verify the server is running and accessible.

Example JSON:

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

Claude

1. Make sure Node.js is installed.
2. Locate your Claude configuration file.
3. Insert the StitchAI MCP Server configuration under mcpServers.
4. Save changes and restart Claude.
5. Confirm that the server appears in Claude’s tool list.

Example JSON:

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

Cursor

1. Install Node.js if not already present.
2. Open the Cursor settings or configuration file.
3. Add the StitchAI MCP Server in the mcpServers object.
4. Save and restart Cursor.
5. Test server connection within Cursor’s interface.

Example JSON:

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

Cline

1. Confirm Node.js is installed.
2. Edit your Cline configuration file.
3. Include the StitchAI MCP Server in the mcpServers.
4. Save the file and restart Cline.
5. Check that StitchAI MCP Server is accessible via Cline.

Example JSON:

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

Securing API Keys

Use environment variables to securely inject API keys or secrets into your MCP server configuration.

Example:

{
  "mcpServers": {
    "stitchai-mcp": {
      "command": "npx",
      "args": ["@stitchai/mcp-server@latest"],
      "env": {
        "API_KEY": "${API_KEY}"
      },
      "inputs": {
        "api_key": "${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:

{
  "stitchai-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

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

Overview

Our opinion

StitchAI MCP Server provides a focused set of memory management tools and is easy to set up across platforms. However, the lack of clear resource and prompt definitions, as well as missing features like sampling and roots, limits its flexibility for broader MCP workflows. The project is new and has little community traction so far.

On a scale of 0 to 10, this MCP scores a 4 for core functionality and clarity, but lacks maturity, extensibility, and adoption.

MCP Score