@soukouki
基本情報
MCP servers focused on fetching and presenting information from Obsidian vaults.
Read a note from the Obsidian vault. If multiple notes with the same name are found, all will be shown.
Search for files with matching names partially.
ObsidianFetch is an MCP server focused on fetching and presenting information from Obsidian vaults. It is designed to address the drawbacks of existing MCP servers—such as slow prompt loading due to many commands and unnecessary tool options—especially when running LLMs on local GPUs.
Install the gem with gem install obsidian_fetch, then run the server by passing your vault path (e.g., obsidian_fetch /path/to/your/vault). By default it uses stdio transport; optionally specify --transport streamable-http and --port for HTTP operation.
read and list.[[link]] searches.It avoids slow prompt loading by supporting only essential commands, eliminates unnecessary tool options that confuse LLMs, and automatically handles `[[link]]` searches by stripping invalid characters.
Install via RubyGems: `gem install obsidian_fetch`.
Yes. Use `--transport streamable-http` and optionally `--port` to customize the listening port (default `9292`).
Two tools: `read` (reads a note by name; shows all matches if multiple exist) and `list` (searches for files with partial name matches).
As a Ruby gem, it requires a Ruby runtime. No other dependencies are mentioned.
Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab
Project context your AI can query through MCP — with source evidence.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference
Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.
コメント