J
jmamodeo/benchling-toolkit
Safe, auditable AI-agent writes to Benchling notebooks: preview-then-apply CLI and a read-only-by-default MCP server.
更新 2026-11-19
在 GitHub 查看 ↗直链 · 无中转页
装完之后怎么算装好了
- 装完该看到什么 — 命令正常结束时退出码为 0,终端里没有 "command not found" 或 "permission denied"。
- 一行自检 — 按该仓库 README 里给出的最小用法跑一次;能按 README 的描述输出就是通了。
- 答不出来怎么办 — 这个项目没有写排错说明,去仓库的 Issues 搜 install。
安装命令取自该仓库;以上判据只描述可观察到的结果,不替代项目自己的文档。
- ★ 数取值
- 0 ★ · jmamodeo/benchling-toolkit · 取自 GitHub 搜索 API · (2026-11-19 20:00:48 核对)
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型:开源项目
- 收录与活跃
- 收录于 2026-11-20 · 最近见到 2026-11-20 · 共见到 1 次 · 被 2 个来源列出
- 评分构成
- 综合分 203 · 2 个来源 · repo
- 安装
- 安装命令见上方「安装与配置」。
常见问题(答案都来自我们的记录)
它适合谁 / 用来做什么?
我们把它归在这些标签下: 开源项目。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库
jmamodeo/benchling-toolkit;我们收录于 2026-11-20;最近见到 2026-11-20。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。README 原文(英文,未翻译) · 在 GitHub 读完整 README →
# benchling-toolkit
以下摘录自该仓库的 README(片段)
Safe, auditable tools for AI agents working in Benchling.
> Unofficial; not affiliated with or endorsed by Benchling, Inc. Benchling is a trademark of Benchling, Inc.
## Why this exists
An electronic lab notebook is a scientific record, so letting an AI agent write to one directly is hard to trust. benchling-toolkit is a toolkit of safe, auditable tools that AI agents use to work with a Benchling tenant: a JSON-first CLI and a local Model Context Protocol (MCP) server that is read-only by default. Every change is first previewed as an immutable, checksummed plan that records what will change and the version preconditions it depends on. A separate, explicit step applies it: that step re-checks the preconditions, refuses stale or already-used plans, and records each stage in a local execution journal. The MCP server cannot apply writes unless an operator opts a specific environment in with --allow-writes.
Public Benchling API only; it never automates the browser.
Four change families: document text, unstructured tables, entry fields, and assay results.
Several environments at once. Each one is saved with benchling auth login; the client secret stays in the OS keychain.
One versioned JSON envelope and stable exit codes for both interfaces.
## Demo
The picture and the asciinema cast are a scripted playback of one run of uv run python scripts/demo.py. scripts/render_demo.py builds both files from that script's stdout. The script runs the real CLI and MCP server against the offline fake API in tests/fake_benchling.py, through an in-process HTTP mock. No credentials are used and no network call is made. The cast is an asciinema v2 file assembled from that transcript. It is not a capture from the asciinema recorder, and it is not a live tenant. Plan IDs differ on every run. The transcript below is the same run as the picture.
console
# 1. Read an entry (envelope trimmed for readability)
$ benchling --env demo entry inspect etr_abc123
"ok": true,
"data": {
"version_id": "ver_1",
"project_id": "src_abc123"
[exit 0]
# 2. Preview: reads Benchling, writes nothing remotely
$ benchling --env demo changes plan --entry etr_abc123 --family table --spec set-cell-b2.json
"ok": true,
"data": {
"id": "9268199dd92c49a3b0df5be26ebb3dc8",
"family": "table",
"env": "demo",
"preconditions": {
"entry_version": "ver_1",
"entry_id": "etr_abc123"
},
"guarantees": [
"server-enforced document version check"
],
"warnings": [
"Updating a cell or appending rows resets table evaluation until Benchling evaluates the table again"
[exit 0]
remote writes so far: 0
# 3. Apply the first plan
$ benchling --env demo changes apply 9268199dd92c49a3b0df5be26ebb3dc8
"ok": true,
"data": {
"journal": {
"status": "succeeded",
"events": [
"stage": "apply",
"status": "started"
},
"stage": "update_table_cells",
"status": "succeeded"
},
"stage": "apply",
"status": "succeeded"
[exit 0]
# 4. The second plan was previewed against the old entry version: apply is refused
$ benchling --env demo changes apply f76d9ec52ca7410a91955867a495b3f5
"ok": false,
"error": {
"code": "conflict",
"message": "Entry version changed after the plan was created",
"retryable": false,
"details": {
"expected": "ver_1",
> Unofficial; not affiliated with or endorsed by Benchling, Inc. Benchling is a trademark of Benchling, Inc.
## Why this exists
An electronic lab notebook is a scientific record, so letting an AI agent write to one directly is hard to trust. benchling-toolkit is a toolkit of safe, auditable tools that AI agents use to work with a Benchling tenant: a JSON-first CLI and a local Model Context Protocol (MCP) server that is read-only by default. Every change is first previewed as an immutable, checksummed plan that records what will change and the version preconditions it depends on. A separate, explicit step applies it: that step re-checks the preconditions, refuses stale or already-used plans, and records each stage in a local execution journal. The MCP server cannot apply writes unless an operator opts a specific environment in with --allow-writes.
Public Benchling API only; it never automates the browser.
Four change families: document text, unstructured tables, entry fields, and assay results.
Several environments at once. Each one is saved with benchling auth login; the client secret stays in the OS keychain.
One versioned JSON envelope and stable exit codes for both interfaces.
## Demo
The picture and the asciinema cast are a scripted playback of one run of uv run python scripts/demo.py. scripts/render_demo.py builds both files from that script's stdout. The script runs the real CLI and MCP server against the offline fake API in tests/fake_benchling.py, through an in-process HTTP mock. No credentials are used and no network call is made. The cast is an asciinema v2 file assembled from that transcript. It is not a capture from the asciinema recorder, and it is not a live tenant. Plan IDs differ on every run. The transcript below is the same run as the picture.
console
# 1. Read an entry (envelope trimmed for readability)
$ benchling --env demo entry inspect etr_abc123
"ok": true,
"data": {
"version_id": "ver_1",
"project_id": "src_abc123"
[exit 0]
# 2. Preview: reads Benchling, writes nothing remotely
$ benchling --env demo changes plan --entry etr_abc123 --family table --spec set-cell-b2.json
"ok": true,
"data": {
"id": "9268199dd92c49a3b0df5be26ebb3dc8",
"family": "table",
"env": "demo",
"preconditions": {
"entry_version": "ver_1",
"entry_id": "etr_abc123"
},
"guarantees": [
"server-enforced document version check"
],
"warnings": [
"Updating a cell or appending rows resets table evaluation until Benchling evaluates the table again"
[exit 0]
remote writes so far: 0
# 3. Apply the first plan
$ benchling --env demo changes apply 9268199dd92c49a3b0df5be26ebb3dc8
"ok": true,
"data": {
"journal": {
"status": "succeeded",
"events": [
"stage": "apply",
"status": "started"
},
"stage": "update_table_cells",
"status": "succeeded"
},
"stage": "apply",
"status": "succeeded"
[exit 0]
# 4. The second plan was previewed against the old entry version: apply is refused
$ benchling --env demo changes apply f76d9ec52ca7410a91955867a495b3f5
"ok": false,
"error": {
"code": "conflict",
"message": "Entry version changed after the plan was created",
"retryable": false,
"details": {
"expected": "ver_1",
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/jmamodeo-benchling-toolkit/)
- 来源
- github · https://github.com/jmamodeo/benchling-toolkit
- 按领域浏览
- 开源项目
- 收录来源
- 2 个独立来源
- 收录于
- 今天
更多条目
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。