
Claude Checkpoint Mcp
io.github.tenlean由 GitHub 帳號 tenlean 發布v0.1.0更新於 Oct 24, 2026
MCP server that checkpoints Claude Code session context to survive crashes and token limits
發布方自己的服務:Claude Platform Docs
概覽
本機 MCP 伺服器,把 Claude Code 工作階段的狀態存成專案內的 JSON 檢查點檔案,並在當機或上下文重置後以精簡的續接摘要重新載入。
- 可以做什麼
- 儲存工作階段檢查點:目標、含狀態的任務、現況摘要、後續步驟、決策、標註檔案與近期指令,寫入專案內的檢查點檔案。
- 以 Markdown 續接摘要或完整 JSON 形式載入檢查點,主檔案損毀時退回上一份備份。
- 偵測漂移:記錄 git 分支、HEAD 與未提交檔案的內容雜湊,載入時只標出儲存後內容真正變動的檔案。
- 以合併方式增量更新既有檢查點,追加任務、決策與指令,而非整份取代。
- 適用情境
- 適合長時間的 Claude Code 工作階段:終端機當機、SSH 斷線、上下文視窗用盡或執行清除後,助理不必重新讀檔、重跑探索來重建上下文。也方便把任務狀態交給新的工作階段接手。
- 執行需求
- 以本機 stdio 程序執行:需要 Node.js 20+ 與已建置的進入點檔案,或安裝為 Claude Code 外掛。git 為選用,但缺少它就沒有漂移偵測。CHECKPOINT_PROJECT_ROOT 可為沒有目前專案的用戶端(如 Claude Desktop)設定預設專案;否則專案根目錄由每次呼叫傳入、用戶端 roots 或工作目錄決定。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Claude Checkpoint Mcp,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
claude-checkpoint-mcp
Save your Claude Code session state locally, so a crash, /clear, or context limit doesn't make Claude rebuild context from scratch.
[License: MIT] [Node.js ≥ 20] [MCP] [M8ven Score]
claude-checkpoint-mcp is a local Model Context Protocol server with two tools:
save_session_checkpointwrites your session's working state to a small JSON file in the project.load_session_checkpointturns that file back into a compact resume brief.
It runs entirely on your machine. Nothing is sent anywhere.
Contents
- Why: stop paying twice for the same context
- How it works
- Installation
- Configuration
- Usage
- Tool reference & examples
- The
.claude-checkpointfile - Security & privacy
- Troubleshooting
- Development
Why: stop paying twice for the same context
A long Claude Code session builds up a lot of context:
- what you're trying to do;
- which approaches already failed;
- which files matter;
- which test is still red.
Several things can wipe that out mid-task:
- a terminal crash, SSH drop, or laptop sleep;
- running out of context window;
- a
/clearto get a fresh window.
The next session starts cold. To get back to where you were, Claude has to rebuild that context:
- Re-reading files to work out what was changed and why. Every file read is input tokens.
- Re-running exploration:
grep,git diff,ls, test runs, all just to rediscover state. - Re-explaining. You retype the goal, the constraints, and the dead ends, or Claude rediscovers the dead ends the hard way.
Each of those turns resends the growing conversation as input, so the cost compounds.
claude-checkpoint-mcp swaps that rebuild for one small, structured read:
The resume brief for a typical session is about 1.2 KB of markdown, a few hundred tokens. The example below is real output at that size.
The biggest saving comes from drift detection. At save time, the server records a content hash for every file with uncommitted changes. On load, it compares those hashes against the working tree and tells Claude exactly which files changed after the checkpoint. Everything else in the brief can be trusted as-is, so Claude re-reads only what it has to.
How it works
- Claude supplies the meaning: the goal, progress, decisions, next steps, and which commands mattered.
- The server supplies the facts: git branch and HEAD, every uncommitted or untracked file with its content hash, and timestamps.
- The server instructions teach Claude when to act. Claude is told to load at the start of a session and to save after milestones, before risky operations, and when the conversation gets long. It doesn't need to be prompted every time.
Installation
Requirements: Node.js 20+ and git. Git is optional, but without it you lose drift detection.
The server entry point is now at dist/index.js.
Configuration
Claude Code
As a plugin (easiest). This repo is also a Claude Code plugin marketplace. You don't need to clone or build anything:
Restart Claude Code, then /mcp should show plugin:claude-checkpoint-mcp:claude-checkpoint as connected.
Manual setup. If you cloned the repo, register the server once for your user account, so it's available in every project:
Use an absolute path. A user-scoped server is launched from whichever project you open Claude Code in. A relative path like
./dist/index.jswould resolve against that project, not this repo."$PWD/dist/index.js"expands to the absolute path when you run the command, which is what gets saved.
Check that it's registered:
Inside a session, /mcp should show checkpoint as connected.
Project-scoped alternative. To share the server with a team through version control, add it to the project's .mcp.json:
Either way, add the checkpoint files to the project's .gitignore, or to your global gitignore:
Claude Desktop (claude_desktop_config.json)
Open the config file:
Add the server under mcpServers, using the absolute path to your local build:
Restart Claude Desktop after saving the file.
Claude Desktop has no notion of a "current project". Use
CHECKPOINT_PROJECT_ROOTto set the default project, or have Claude passprojectRooton each call ("save a checkpoint for /home/me/code/my-app"). See project root resolution.
Other MCP clients
Any MCP client that supports the stdio transport can run the server:
Usage
The server's built-in instructions cover the common cases automatically. You can also ask Claude directly.
Save:
- "Checkpoint our progress."
- "Save a checkpoint before you run the migration."
- "Update the checkpoint. Merge in what we just did."
Resume (in a fresh session):
- "Resume where we left off."
- "Load the checkpoint and continue."
Example resume brief
This is real output from load_session_checkpoint. In the scenario, one file was committed unchanged after the save, and a teammate then edited session.ts:
callback.ts was committed after the save, but its content didn't change, so it isn't flagged. Only session.ts needs to be re-read.
Task markers: [x] done · [~] in progress · [ ] pending · [!] blocked.
Tool reference & examples
save_session_checkpoint
Writes <projectRoot>/.claude-checkpoint.
Full save:
Response (text shown to the model):
Incremental update with merge:
Structured output (structuredContent):
load_session_checkpoint
Read-only. Reads the checkpoint, checks for drift, and returns the brief.
Examples:
Structured output (structuredContent):
If no checkpoint exists, the tool returns found: false with a "nothing to resume" message. That isn't treated as an error.
How the project root is chosen
- The
projectRootargument - The
CHECKPOINT_PROJECT_ROOTenvironment variable - The client's first
file://root, if the client supports MCP roots - The server process's working directory
The path must be absolute and must be an existing directory. Symlinks are resolved. The file is always written at exactly <root>/.claude-checkpoint.
The .claude-checkpoint file
This is plain, versioned JSON, so it's easy to read, diff, or edit by hand. Real example:
Paths are always relative to the project root. The file never stores absolute paths.
Security & privacy
-
Local only. There are no network calls. The server reads git metadata and one file, and writes one file.
-
Secret redaction. The following are replaced with
«redacted»in commands, notes, summaries, tasks and decisions before anything touches disk:*_KEY=,*_TOKEN=,*_SECRET=,*PASSWORD=assignments, includingHeader: valueand JSON formsAuthorization: Bearer …headers- credentials in URLs (
postgres://user:pass@…) --password/--token/--api-key/--secretflags- bare
sk-…,ghp_…,github_pat_…,AKIA…andxox?-…tokens
Redaction is a safety net, not a guarantee, so keep the file out of version control.
-
Owner-only, crash-safe writes. Files are written with mode
0600. Each save writes a temp file, fsyncs it, and renames it into place, so a crash mid-save can't leave a half-written checkpoint. -
Automatic backup. The previous valid checkpoint is kept as
.claude-checkpoint.prev. If the main file is corrupt, load falls back to the backup and says so. A corrupt file never overwrites a good backup. -
Bounded size. Every field has a length cap, and the file is capped at 64 KB (the oldest commands are dropped first), so a checkpoint can't grow into a token sink.
-
No shell. Git runs through
execFilewith a 3-second timeout andGIT_OPTIONAL_LOCKS=0, so it never contends with your own git commands. -
Doesn't touch your config. If the checkpoint isn't git-ignored, the save response warns you. It never edits
.gitignorefor you. -
Safe with parallel tool calls. Tool calls are serialized inside the server, so concurrent
mergesaves can't lose updates.
Troubleshooting
Server logs go to stderr. Stdout is reserved for the MCP protocol.
Development
Built with the official @modelcontextprotocol/sdk and zod.
License
來源:README.md,提交 12b92ff
工具
0版本歷史
1- v0.1.0最新Oct 12, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分
其他 Claude 整合
Claude Platform Docs
com.claude.platform官方發布者
遠端 MCP 伺服器,讓助理搜尋並閱讀 Claude 平台文件與 API 參考。

Insta Edits for Claude
由 GitHub 帳號 faisalkhanzemi 發布
把 Claude Code 連上 Mac 版 Instagram Edits,同步完整的 274 個工具編輯器,讓助理剪輯 Reels。

Claude Checkpoint Mcp
由 GitHub 帳號 daniel-munoz 發布
本機 MCP 伺服器,把 Claude Code 工作階段的狀態存成專案內的 JSON 檔,並能還原成精簡的續接摘要。

Qwen DAP MCP — C/C++ Debugger for Claude Code, Codex & Qwen
由 GitHub 帳號 spk-c 發布
通過 GDB、LLDB 和 MCP 為 Claude Code、Codex 和 Qwen 提供 C/C++ 崩潰、掛起和轉儲除錯AI 翻譯

AVE for Claude Code — Local Video Editing
由 GitHub 帳號 lemberalla 發布
僅適用於 Claude Code 的本機 AVE 時間軸編輯與匯出。需要現有 AVE 連接。AI 翻譯