Stitch AI MCP Server

What is Stitch AI MCP Server about?

A lightweight Node.js server that implements the Model Context Protocol to manage AI agent memories. It lets developers create dedicated memory spaces, upload and retrieve individual memories, and query collections of memories with filtering and pagination.

How to use Stitch AI MCP Server?

Clone the repository

git clone https://github.com/StitchAI/stitch-ai-mcp.git

Install dependencies

npm install @modelcontextprotocol/sdk zod
npm install -D @types/node typescript

Start the server
```
npm run start
```
(Optional) Integrate with Claude for Desktop – add an entry to claude_desktop_config.json that points to the server script using npx ts-node (see the serverConfig section below).

Key Features of Stitch AI MCP Server

Space Management: create_space, delete_space, get_all_spaces.
Memory Operations: upload_memory, get_memory, get_all_memories with optional name filtering, limit, and offset.
Simple CLI start via npm run start.
Type‑safe validation using Zod.
Easy integration with Claude for Desktop through MCP configuration.

Use Cases of Stitch AI MCP Server

Persisting context for conversational agents across sessions.
Building a decentralized knowledge hub where multiple AI assistants share and retrieve facts.
Archiving and querying logs or observations generated by autonomous AI agents.
Providing a backend for custom AI tooling that requires fast, filtered access to stored memories.

FAQ

Q: Do I need an API key? A: Yes, the server expects an API_KEY environment variable for authentication with Stitch AI’s backend services.

Q: Can I run the server on a different port? A: The repository uses the default port defined in the source code; you can change it by modifying the server configuration or environment variables.

Q: Is there a Docker image? A: The README does not provide a Docker setup, but the Node.js app can be containerized using a standard Node base image.

Q: How do I filter memories by name? A: Use the optional memory_names query parameter (comma‑separated) in the get_all_memories tool.

Q: What is the default pagination? A: limit defaults to 50 and offset defaults to 0 if not supplied.

Stitch AI's MCP Server

Decentralized Knowledge Hub for AI

This repository contains a Model Context Protocol (MCP) server implementation for Stitch AI's memory management system. The server provides tools for creating, retrieving, and managing AI agent memories.

Available Tools

The MCP server provides the following tools:

`create_space`

Creates a new memory space with the specified name.

Parameters:
- space_name: The name of the memory space to create
- type: The type of memory space to create

`delete_space`

Deletes a memory space with the specified name.

Parameters:
- space_name: The name of the memory space to delete

`get_all_spaces`

Gets a list of all available memory spaces.

Parameters: None

`upload_memory`

Uploads a new memory to a specified memory space.

Parameters:
- space: The name of the memory space to upload to
- message: The memory message to upload
- memory: The memory content to upload

`get_memory`

Retrieves a specific memory by ID from a memory space.

Parameters:
- space: The name of the memory space
- memory_id: The ID of the memory to retrieve

`get_all_memories`

Retrieves all memories from a specified memory space.

Parameters:
- space: The name of the memory space to retrieve memories from
- Optional Parameters:
  - memory_names: Comma-separated list of memory names to filter
  - limit: Maximum number of memories to return (default: 50)
  - offset: Number of memories to skip (default: 0)

Run the server

npm run start

Using with Claude Desktop

Clone the repository

git clone https://github.com/StitchAI/stitch-ai-mcp.git

Install dependencies

npm install @modelcontextprotocol/sdk zod
npm install -D @types/node typescript

Install Claude for Desktop
- Download and install the latest version from Claude's website
Configure Claude for Desktop
- Locate your Claude for Desktop configuration file:
  - macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  - Windows: %AppData%\Claude\claude_desktop_config.json
- Create the file if it doesn't exist
Edit Configuration File
- Open the configuration file in a text editor:
  - macOS: code ~/Library/Application\ Support/Claude/claude_desktop_config.json
  - Windows: code $env:AppData\Claude\claude_desktop_config.json
- Add your MCP server configuration:

{
    "mcpServers": {
        "stitchai": {
            "command": "npx",
            "args": [
                "ts-node",
                "/path/to/cloned/stitch-ai-mcp/src/server.ts"
            ],
            "env": {
                "API_KEY": "<STITCH_AI_API_KEY>",
                "BASE_URL": "https://api-demo.stitch-ai.co"
            }
        }
    }
}

Restart Claude for Desktop
- After saving the configuration file, restart Claude for Desktop
- The MCP UI elements will appear in Claude for Desktop once at least one server is properly configured

Contact

https://x.com/StitchAI_hq

{ "mcpServers": { "stitchai": { "command": "npx", "args": [ "ts-node", "/path/to/cloned/stitch-ai-mcp/src/server.ts" ], "env": { "API_KEY": "<STITCH_AI_API_KEY>", "BASE_URL": "https://api-demo.stitch-ai.co" } } } }