slivingdoc
A distributed durable notebook MCP server for high-scale agents, providing git-like pull and commit tools with automatic conflict resolution.
README
Test coverage: 83.7% 😍👌
<div align="center"> <p>Distributed durable notebook built for high scale agents.</p> </div>
Features
- Gitlike semantics:
slivingdocuses terminology we (and agents) all know, designed for ease of use - Automatic conflict resolution: commit without fear, trust that all conflicts must be resolved before being accepted
- High speed processing: the solution is quite simple conceptually, allowing for very high scale and parallelism
- Plug-and-play: setup the bucket, point at it, and start syncing notes!
docs/slivingdoc-v1.md is the full accepted
contract behind these guarantees.
Get started
Add it to your agentic harness:
{
"mcpServers": {
"slivingdoc": {
"command": "npx",
"args": [
"-y",
"slivingdoc",
"serve",
"--bucket",
"my-notes",
"--workspace-root",
"/srv/notes"
],
"env": {
"AWS_ACCESS_KEY_ID": "<your-access-key-id>",
"AWS_SECRET_ACCESS_KEY": "<your-secret-access-key>",
"AWS_REGION": "us-east-1"
}
}
}
}
The bucket must exist, and credentials come from the normal AWS chain.
No S3 account yet? examples/seaweedfs/ runs a local
SeaweedFS container with a step-by-step walkthrough. You can also download
a native binary directly from the
GitHub release
(slivingdoc-v<semver>-<os>-<arch>) and run it in place.
Supported platforms: Linux (amd64, 32-bit ARMv7, arm64), macOS (amd64, arm64), and Windows (amd64). The 32-bit Linux ARM artifact supports Raspberry Pi OS armhf.
How it works
The server exposes two MCP tools over stdio:
| Tool | Inputs | Success result |
|---|---|---|
notes_pull |
path |
OK |
notes_commit |
path, message |
OK |
notes_pull writes the current notebook into your directory.
notes_commit publishes your changes and incorporates concurrent
non-conflicting changes. Between calls there is no protocol at all —
agents edit the files with the tools they already have, and humans can
write in the same directory with any editor. The next commit carries
their changes too.
Humans can also drive both operations directly, without an MCP host. A relative path resolves against the working directory:
slivingdoc pull notes
# edit UTF-8 text files under notes/
slivingdoc commit notes -m "meeting summary"
Success prints the unified result report: the OK status, the accepted
remote generation, per-file insertion and deletion counts, and a totals
trailer. A domain error exits nonzero and prints a candid report: the
error category, the retryable verdict, and every conflicted file with its
line ranges. Colour appears only on a real terminal and is disabled by
any non-empty NO_COLOR.
The git part
Letting all agents write at once would work, but they would get overrun by race conditions.
So slivingdoc has built-in git via libgit2 which effectively
does:
git pull- (potential conflict resolution locally)
git add .git commit -m "<agent message>"git push- (potential conflict resolution locally)
All of these git operations are handled locally within a private mirror of the notes directory
leaving a "streamlined" git sequence. This works due to two compromises, firstly that the local
notes directory is prone to be changed on notes_pull, precedence goes to the remote state, leaving
conflict markers. Secondly, the system only works for text (clean UTF-8).
Configuration
serve, pull, and commit read the same flags and environment
variables. --bucket is required. The most common flags:
| Flag | Environment | Default |
|---|---|---|
--bucket |
SLIVINGDOC_BUCKET |
— (required) |
--workspace-root |
SLIVINGDOC_WORKSPACE_ROOT |
startup working dir |
--endpoint |
AWS_ENDPOINT_URL_S3 |
AWS resolution |
--region |
AWS_REGION |
us-east-1 |
slivingdoc serve -h prints the full reference, and
docs/running.md covers everything an operator
needs: all flags, the exact S3 permissions, logging (LOG_LEVEL on
stderr), the notebook rules, conflict recovery, and checkpoint
retention. The Terraform module in terraform/
provisions a bucket and a least-privilege IAM user for one notebook.
Development
AGENTS.md— the developer and agent guide: package map, operation flows, conventions, and the QA gates.docs/slivingdoc-v1.md— the accepted architecture contract.docs/build.md— the native build, from pinned libgit2 source to dependency inspection.docs/testing.md— the test commands, the test layers, and the no-live-AWS rule.docs/releasing.md— release artifacts, npm trusted publishing, andmake release.
make qa #lint plus the full Go and npm test suites
License
MIT — see LICENSE. Third-party notices for the statically linked libgit2 are in NOTICE.
<sub>Not affiliated with Paris Hilton.</sub>
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。