obsidian-dev-memory
Provides AI coding assistants persistent engineering memory stored as Markdown files in an Obsidian vault, enabling project context retrieval, session capture, decision recording, and memory search without requiring Obsidian to be running.
README
Obsidian Developer Memory MCP
A local Model Context Protocol server that gives AI coding assistants such as Cursor and GitHub Copilot persistent engineering memory.
Memory is stored as ordinary Markdown files in an Obsidian vault. Obsidian does not need to be running. There is no community plugin and no Obsidian API key.
The same stdio MCP server works with both Cursor and GitHub Copilot / VS Code.
Architecture
Cursor Agent --------------------\
\
> MCP stdio server
/ |
GitHub Copilot / VS Code --------/ v
obsidian-dev-memory
|
v
Obsidian Markdown Vault
Developer opens spring-auth in Cursor
|
v
Cursor calls get_project_context("spring-auth")
|
v
AI sees current project state + recent decisions
|
v
Developer and AI implement feature
|
v
AI calls capture_work_session(...)
|
+--> session note
|
+--> Git branch/SHA recorded
|
v
Durable architecture choice?
|
yes
|
v
record_decision(...)
Why direct Markdown?
The vault is the source of truth. Notes remain readable and editable in Obsidian, git, or any text editor. The server never depends on Obsidian being open, never talks to a hosted memory API, and never writes a proprietary database.
Requirements
- Python 3.12+
- uv
- A local Obsidian vault directory
- Git on
PATHonly if you want automatic repository snapshots
Installation
git clone https://github.com/jmjava/obsidian-mcp.git
cd obsidian-mcp
uv sync
uv sync installs the official MCP Python SDK and the project package.
Configuration
Required:
export OBSIDIAN_VAULT_PATH="$HOME/Documents/ObsidianVault"
Optional:
export OBSIDIAN_MEMORY_ROOT="AI Memory"
OBSIDIAN_MEMORY_ROOT defaults to AI Memory. Editor MCP configuration can supply these variables directly. This project includes .env.example for documentation; the server does not automatically load .env files.
Running the server
export OBSIDIAN_VAULT_PATH="/tmp/example-vault"
mkdir -p "$OBSIDIAN_VAULT_PATH"
uv run python -m obsidian_dev_memory
or:
uv run obsidian-dev-memory
The process speaks MCP over stdio. Do not write application logs to stdout; diagnostics go to stderr.
Cursor setup
Project-level Cursor config lives at .cursor/mcp.json and uses the current mcpServers format. A portable template is in config/cursor.mcp.json.example:
{
"mcpServers": {
"obsidian-dev-memory": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/obsidian-dev-memory-mcp",
"run",
"python",
"-m",
"obsidian_dev_memory"
],
"env": {
"OBSIDIAN_VAULT_PATH": "/ABSOLUTE/PATH/TO/OBSIDIAN/VAULT"
}
}
}
}
This repository also ships .cursor/rules/obsidian-memory.mdc, which tells Cursor when to read and write memory.
Machine-specific .cursor/mcp.json files are created by the installer and are not committed here.
GitHub Copilot / VS Code setup
Workspace Copilot / VS Code config lives at .vscode/mcp.json and uses the current servers format. A portable template is in config/vscode.mcp.json.example:
{
"servers": {
"obsidian-dev-memory": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/obsidian-dev-memory-mcp",
"run",
"python",
"-m",
"obsidian_dev_memory"
],
"env": {
"OBSIDIAN_VAULT_PATH": "/ABSOLUTE/PATH/TO/OBSIDIAN/VAULT"
}
}
}
}
.github/copilot-instructions.md gives Copilot the same memory behavior as Cursor.
Installer usage
Wire this server into another development project:
./scripts/install-project.sh \
--project /home/user/src/example \
--vault /home/user/Documents/ObsidianVault
Optional:
./scripts/install-project.sh \
--project /home/user/src/example \
--vault /home/user/Documents/ObsidianVault \
--server /path/to/obsidian-dev-memory-mcp
If --server is omitted, the script infers this repository from its own location.
The installer creates or updates:
<project>/.cursor/mcp.json<project>/.cursor/rules/obsidian-memory.mdc<project>/.vscode/mcp.json<project>/.github/copilot-instructions.md
It fails clearly when the target project or vault is missing, and it merges MCP JSON so unrelated servers are not destroyed.
MCP tools
| Tool | Purpose |
|---|---|
get_project_context |
Read Project State.md plus the newest session and decision notes |
capture_work_session |
Append a timestamped section to today's session note |
record_decision |
Write a durable decision note |
update_project_state |
Replace the concise project-state note |
search_memory |
Local filename and text search over project memory |
read_note |
Read one vault-relative Markdown file |
append_daily_note |
Append to Daily/YYYY-MM-DD.md |
get_project_context returns empty sections when a project is new instead of failing.
record_decision writes YYYY-MM-DD-<decision-slug>.md. If that file already exists, the server adds a numeric suffix (-2, -3, ...) instead of overwriting.
capture_work_session accepts an optional repository_path. When that path is a Git repository, the note records repository name, branch, short SHA, dirty state, and a short changed-file list. Full diffs are never written. A non-Git path is ignored.
Vault layout
AI Memory/
└── Projects/
└── <project-slug>/
├── Project State.md
├── Sessions/
│ └── YYYY-MM-DD.md
└── Decisions/
└── YYYY-MM-DD-<decision-slug>.md
Daily/
└── YYYY-MM-DD.md
The AI Memory folder honors OBSIDIAN_MEMORY_ROOT. Logical project names are slugified (Spring Authorization Server → spring-authorization-server).
Example workflow
- Open a project in Cursor or VS Code.
- Before substantial work, the assistant calls
get_project_context. - After meaningful implementation, it calls
capture_work_session. - When an architecture choice is made, it calls
record_decision. - When overall status changes, it calls
update_project_state. - Open the vault in Obsidian at any time to read or edit the same files.
Security model
- All note paths must resolve inside
OBSIDIAN_VAULT_PATH. - Absolute note paths,
../traversal, and detectable symlink escapes are rejected. - Writes are atomic (
tempfile+os.replace) where practical. - The tools are not a general filesystem API.
- Secret-looking values (keys, tokens, JWTs, private keys,
password=assignments) are replaced with[redacted-secret]before they are written. - Cursor rules and Copilot instructions tell the assistant never to persist passwords, API keys, tokens, JWTs, private keys,
.envcontents, database credentials, production secrets, or sensitive customer data.
Testing
Tests use temporary directories, never your real vault.
uv run pytest
A broader local check:
export OBSIDIAN_VAULT_PATH="$HOME/Documents/ObsidianVault"
./scripts/smoke-test.sh
The smoke test verifies the environment variable, vault directory, package import, server construction, and the pytest suite.
Troubleshooting
| Symptom | What to check |
|---|---|
| Server exits immediately | OBSIDIAN_VAULT_PATH is set and the directory exists |
| Tools do not appear in Cursor | Project .cursor/mcp.json is present; reload the window; uv is on PATH |
| Tools do not appear in Copilot | Workspace .vscode/mcp.json uses a top-level servers key, not mcpServers |
Path traversal is not allowed |
Pass vault-relative paths such as AI Memory/Projects/spring-auth/Project State.md |
| Decision file name already existed | The server wrote YYYY-MM-DD-<slug>-2.md instead of overwriting |
| Git section missing from a session | repository_path was omitted or is not a Git repository; that is non-fatal |
| Unexpected stdout noise | Only MCP JSON-RPC should use stdout; logs belong on stderr |
License
MIT. See LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。