How do I get my Obsidian API key?
Open Obsidian, go to Settings → Community Plugins, find “Local REST API,” click its settings gear, and copy the “API Key” field.
@kmackett
基本信息
Dockerized version of MCP Obsidian server for Obsidian Local REST API integration
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MCP Obsidian Docker is a containerized version of the MCP Obsidian server that interacts with Obsidian via the Local REST API community plugin. It requires Docker, Docker Compose, and an Obsidian vault with the Local REST API plugin installed and an API key.
Clone the repository, configure the OBSIDIAN_API_KEY in a .env file, then build and start the container with docker-compose up -d. The server will be available on port 27124. Verify the container with docker-compose ps and inspect logs with docker-compose logs -f.
.env file./logs directorydocker-compose restartOpen Obsidian, go to Settings → Community Plugins, find “Local REST API,” click its settings gear, and copy the “API Key” field.
Copy `.env.example` to `.env`, then edit the file and replace `your_api_key_here` with your actual API key.
The MCP Obsidian server is available at port 27124 by default. If there is a port conflict, modify the port mapping in `docker-compose.yml`.
Run `docker-compose ps` to see if the container is running, and `docker-compose logs -f` to view logs for authentication or connection errors.
Generate a new key in Obsidian, update the `OBSIDIAN_API_KEY` in your `.env` file, and run `docker-compose restart`.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

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
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.
Project context your AI can query through MCP — with source evidence.

One permissioned folder your team and your AI agents both log into.
评论