by StitchAI
Stitch AI is a decentralized knowledge hub for AI agents, providing a Model Context Protocol (MCP) server for memory management.
Stitch AI's MCP Server is a decentralized knowledge hub designed for AI agents. It implements the Model Context Protocol (MCP) to provide a robust system for creating, retrieving, and managing AI agent memories. This allows AI agents to have persistent and organized knowledge bases.
To use Stitch AI's MCP Server, you primarily interact with it through its provided tools. The server can be run locally and integrated with applications like Claude Desktop.
Running the Server:
npm run start
Integration with Claude Desktop:
git clone https://github.com/StitchAI/stitch-ai-mcp.git
npm install @modelcontextprotocol/sdk zod
and npm install -D @types/node typescript
claude_desktop_config.json
file (located in ~/Library/Application Support/Claude/
on macOS or %AppData%\Claude\
on Windows) to include your MCP server configuration, specifying the command to run the server and any necessary environment variables like API_KEY
and BASE_URL
.create_space
: Create new memory spaces with specified names and types.delete_space
: Delete existing memory spaces.get_all_spaces
: Retrieve a list of all available memory spaces.upload_memory
: Upload new memories (messages and content) to a specified memory space.get_memory
: Retrieve a specific memory by its ID from a memory space.get_all_memories
: Retrieve all memories from a specified memory space, with optional filtering by memory names, limit, and offset.claude_desktop_config.json
file in your Claude Desktop application support directory to point to the Stitch AI MCP server and provide necessary API keys and base URLs.get_all_memories
supports filtering by memory_names
as well as pagination parameters like limit
and offset
.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.
The MCP server provides the following tools:
create_space
Creates a new memory space with the specified name.
space_name
: The name of the memory space to createtype
: The type of memory space to createdelete_space
Deletes a memory space with the specified name.
space_name
: The name of the memory space to deleteget_all_spaces
Gets a list of all available memory spaces.
upload_memory
Uploads a new memory to a specified memory space.
space
: The name of the memory space to upload tomessage
: The memory message to uploadmemory
: The memory content to uploadget_memory
Retrieves a specific memory by ID from a memory space.
space
: The name of the memory spacememory_id
: The ID of the memory to retrieveget_all_memories
Retrieves all memories from a specified memory space.
space
: The name of the memory space to retrieve memories frommemory_names
: Comma-separated list of memory names to filterlimit
: Maximum number of memories to return (default: 50)offset
: Number of memories to skip (default: 0)npm run start
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
Configure Claude for Desktop
~/Library/Application Support/Claude/claude_desktop_config.json
%AppData%\Claude\claude_desktop_config.json
Edit Configuration File
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
code $env:AppData\Claude\claude_desktop_config.json
{
"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"
}
}
}
}
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by topoteretes
Enables AI agents to store, retrieve, and reason over past conversations, documents, images, and audio transcriptions by loading data into graph and vector databases with minimal code.
by basicmachines-co
Basic Memory is a local-first knowledge management system that allows users to build a persistent semantic graph from conversations with AI assistants. It addresses the ephemeral nature of most LLM interactions by providing a structured, bi-directional knowledge base that both humans and LLMs can read and write to.
by smithery-ai
mcp-obsidian is a connector that allows Claude Desktop to read and search an Obsidian vault or any directory containing Markdown notes.
by qdrant
Provides a semantic memory layer on top of the Qdrant vector search engine, enabling storage and retrieval of information via the Model Context Protocol.
by GreatScottyMac
A database‑backed MCP server that stores project decisions, progress, architecture, custom data, and vector embeddings, allowing AI assistants in IDEs to retrieve precise, up‑to‑date context for generation tasks.
by StevenStavrakis
Enables AI assistants to read, create, edit, move, delete, and organize notes and tags within an Obsidian vault.
by mem0ai
Provides tools to store, retrieve, and semantically search coding preferences via an SSE endpoint for integration with MCP clients.
by graphlit
Enables integration between MCP clients and the Graphlit platform, providing ingestion, retrieval, RAG, and publishing capabilities across a wide range of data sources and tools.
by chroma-core
Provides vector, full‑text, and metadata‑based retrieval powered by Chroma for LLM applications, supporting in‑memory, persistent, HTTP, and cloud clients as well as multiple embedding functions.