Skip to content

Conversation

@lucky7323
Copy link

Description

Add Stitch AI MCP Server. Stitch AI: Decentralized Knowledge Hub for AI.
The Stitch AI MCP server provides tools for creating, retrieving, and managing AI agent memories.

Server Details

Motivation and Context

Stitch AI MCP Server introduces a unified memory management layer for AI agents, enabling seamless sharing of contextual memories and state between multiple agents or LLM instances. By providing built‑in version control and synchronization, it prevents data fragmentation and drift, ensures that all participants operate from a consistent knowledge base, and makes it easy to roll back or audit changes to an agent’s memory over time.

How Has This Been Tested?

stitchai

claude_desktop_config

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

Breaking Changes

None

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Documentation update

Checklist

  • I have read the MCP Protocol Documentation
  • My changes follows MCP security best practices
  • I have updated the server's README accordingly
  • I have tested this with an LLM client
  • My code follows the repository's style guidelines
  • New and existing tests pass locally
  • I have added appropriate error handling
  • I have documented all environment variables and configuration options

Additional context

Stitch AI enables AI agents and LLMs to seamlessly manage, share, and version their contextual memories by bridging the Model Context Protocol (MCP) with Stitch AI’s decentralized knowledge hub. It provides a simple, unified API and conversational interface for creating, retrieving, and synchronizing memory entries across multiple agents or LLMs.

@olaservo
Copy link
Member

olaservo commented Jun 9, 2025

Thanks for your contribution to the servers list. This has been merged in this combined PR: #2007

This is a new process we're trying out, so if you see any issues feel free to re-open the PR and tag me.

@olaservo olaservo closed this Jun 9, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants