MemoryMesh
@CheMiguel23
About MemoryMesh
A knowledge graph server that uses the Model Context Protocol (MCP) to provide structured memory persistence for AI models.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"MemoryMesh": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"memorymesh",
"--client",
"claude"
]
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is MemoryMesh?
MemoryMesh is a local knowledge graph server designed for AI models, with a focus on text-based RPGs and interactive storytelling. It helps AI maintain consistent, structured memory across conversations and is built upon the MCP Knowledge Graph Memory Server.
How to use MemoryMesh?
After installing dependencies with npm install, place your schema files (.schema.json) in the dist/data/schemas directory. The server automatically detects schemas and generates dynamic tools. Data is stored by default in dist/data/memory.json. A companion Memory Viewer web app can load and visualize the memory file.
Key features of MemoryMesh
- Dynamic schema-based tools: automatically generated add/update/delete tools
- Intuitive schema design with required fields, enums, and relationships
- Metadata for AI guidance on entity purpose and connections
- Relationship handling to create edges between related nodes
- Informative error feedback to help the AI improve
- Event system tracking all knowledge graph modifications
- 11 pre-built schemas for text-based RPGs
Use cases of MemoryMesh
- Text-based RPGs with persistent, structured character and world memory
- Interactive storytelling with consistent lore tracking
- Social network simulations with entity relationships
- Organizational planning with structured data management
- Any scenario requiring structured data for AI models
FAQ from MemoryMesh
Where should schema files be placed?
Place your schema files (.schema.json) in the dist/data/schemas directory. Files must be named with a prefix add_ (e.g., add_npc.schema.json).
Where is the memory data stored?
By default, the knowledge graph data is stored in a JSON file at dist/data/memory.json. You can load this file into the Memory Viewer for inspection.
How does dynamic tool generation work?
MemoryMesh reads your schema definitions and automatically creates three tools per entity type: add_<entity>, update_<entity>, and delete_<entity>. These tools are then available for AI clients.
What changed in v0.3.0 and how do I update?
Version 0.3.0 updates the MCP SDK from v1.0.4 to v1.25.2 for compatibility with the latest MCP specification (2025-11-25). After updating, run npm install to fetch new dependencies. Since v0.2.7, the default schema location changed to dist/data/schemas; move your schema files if upgrading from an earlier version.
What are the runtime requirements?
MemoryMesh is a TypeScript project. It requires Node.js and the MCP SDK. The server runs locally and is compatible with MCP clients like Claude Desktop, ChatGPT, Cursor, Gemini, and VS Code.
Frequently asked questions
Where should schema files be placed?
Place your schema files (`.schema.json`) in the `dist/data/schemas` directory. Files must be named with a prefix `add_` (e.g., `add_npc.schema.json`).
Where is the memory data stored?
By default, the knowledge graph data is stored in a JSON file at `dist/data/memory.json`. You can load this file into the Memory Viewer for inspection.
How does dynamic tool generation work?
MemoryMesh reads your schema definitions and automatically creates three tools per entity type: `add_<entity>`, `update_<entity>`, and `delete_<entity>`. These tools are then available for AI clients.
What changed in v0.3.0 and how do I update?
Version 0.3.0 updates the MCP SDK from v1.0.4 to v1.25.2 for compatibility with the latest MCP specification (2025-11-25). After updating, run `npm install` to fetch new dependencies. Since v0.2.7, the default schema location changed to `dist/data/schemas`; move your schema files if upgrading from an earlier version.
What are the runtime requirements?
MemoryMesh is a TypeScript project. It requires Node.js and the MCP SDK. The server runs locally and is compatible with MCP clients like Claude Desktop, ChatGPT, Cursor, Gemini, and VS Code.
Basic information
More Memory & Knowledge MCP servers
Obsidian MCP Server
cyanheadsRead, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
Tempreon
TempreonPerson-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
The Cloud
TekaThe Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your
Orcha
westonhancockOrcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age
Anytype MCP Server
anyprotoAn MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.
Comments