Obsidian Memory
This MCP server stores AI memories as individual Markdown files optimized for Obsidian's graph view visualization, transforming Anthropic's original JSON-based memory server into a format that leverages Obsidian's [[link]] syntax for knowledge graph exploration. Built by YuNaga224 using TypeScript with the Model Context Protocol SDK and gray-matter for YAML frontmatter parsing, it creates separate .md files for each entity with metadata stored in frontmatter and relations expressed as Obsidian-compatible links, enabling natural graph visualization of AI conversation memories. The implementation provides tools for entity creation, relation management, observation tracking, and graph querying while maintaining file-based persistence that integrates seamlessly with existing Obsidian vaults, making it valuable for users who want to visualize and explore AI conversation context through Obsidian's powerful graph view and note-taking ecosystem.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-01.
Scan details: Circle-IR · 2026-09-01 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/yunaga224/obsidian-memory-mcp
- Author type
- human
- Last scanned
- 2026-09-01
- Updated
- 2026-09-01
Use via MCP
Resolve Obsidian Memory from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.