Stores AI memories as Markdown files for visualization in Obsidian's graph view, creating a knowledge graph with entities as nodes and relations as edges.
Obsidian Memory MCP
MCP server that stores AI memories as Markdown files for visualization in Obsidian's graph view.
About
This project is a modified version of Anthropic's memory server that has been adapted for Obsidian integration. The original server stored memories in JSON format, while this version stores them as individual Markdown files with Obsidian-compatible [[link]] syntax for graph visualization.
Key Changes from Original
Storage Format: Changed from JSON to individual Markdown files
Obsidian Integration: Added
[[link]]syntax for relationsYAML Frontmatter: Metadata stored in frontmatter instead of JSON
File Structure: Each entity becomes a separate
.mdfileRemoved Features: Simplified to focus on Markdown-only storage
Related MCP server: MCP Obsidian
Features
Markdown Storage: Individual
.mdfiles for each entityObsidian Integration: Uses
[[link]]syntax for graph visualizationKnowledge Graph: Store entities, relations, and observations
Search Functionality: Query across all stored memories
YAML Frontmatter: Metadata stored in frontmatter
Storage Format
Each entity is stored as an individual Markdown file with:
YAML frontmatter for metadata (entityType, created, updated)
Obsidian-compatible for relations
Organized sections for observations and relations
Example entity file (John_Doe.md):
Installation & Configuration
Then configure in Claude Desktop:
Usage with Obsidian
Configure Claude Desktop with one of the options above
Restart Claude Desktop
Use the MCP memory tools to create entities and relations
Open Obsidian and view the graph
The knowledge graph will be visualized with:
Entity files as nodes
[[links]]as edgesDifferent colors for different entity types (if configured in Obsidian)
API
The server exposes the following tools:
create_entities: Create new entitiescreate_relations: Create relations between entitiesadd_observations: Add observations to existing entitiesdelete_entities: Delete entities and related datadelete_observations: Remove specific observationsdelete_relations: Remove relationsread_graph: Get the entire knowledge graphsearch_nodes: Search entities by queryopen_nodes: Get specific entities by name
Development
Credits
This project is based on Anthropic's memory server from the Model Context Protocol servers collection. We thank Anthropic for releasing the original implementation under the MIT license.
License
MIT License - see LICENSE file for details.
Original memory server: Copyright (c) 2024 Anthropic, PBC
Obsidian integration modifications: Copyright (c) 2025 YuNaga224