Scispot MCP
概览
作者提供的说明(英文原文)
Turn any LLM into your lab assistant: search samples, track experiments, analyze data with AI.
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i1 项中通过 1 项依据公开信息检查;尚未扫描代码
- 使用情况i非常新★ –
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在云端运行
- 传输方式: Streamable HTTP
- 分类: 搜索与 AI 记忆
安装
选择你使用的 AI 应用,然后复制设置。
安装之前
- 基础检查:1 项中通过 1 项
- 在作者的服务器上运行:你向它提出的内容会经过他们的服务器。
- 注册中心没有列出需要填写的密钥。
你需要
- 在云端运行无需安装任何东西,通过互联网连接
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
- 打开 Settings → Connectors
- 点击 Add custom connector
- 粘贴下面的地址,然后点击 Add
- 如果要求登录,请登录作者的服务
https://mcp.scispot.io/在终端中运行这条命令
claude mcp add --transport http scispot https://mcp.scispot.io/或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"scispot": {
"url": "https://mcp.scispot.io/"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"scispot": {
"type": "http",
"url": "https://mcp.scispot.io/"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
- 打开网页版 ChatGPT → Settings → Connectors (Apps)
- 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
- 粘贴下面的地址,起个名字,然后保存
- 如果要求登录,请登录作者的服务
https://mcp.scispot.io/菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它能做什么
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月10日
- ✓ 通过
作者与仓库一致
注册名称已通过域名 scispot.io 验证(注册中心会核实域名所有权)
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
端点有响应
尚未检查;我们会轮流检查各个端点
- … 尚未检查
使用 OAuth 登录
尚未检查;我们会轮流检查各个端点
- … 尚未检查
工具描述中没有隐藏指令
尚未检查;我们会在检查端点时读取工具列表
与“搜索与 AI 记忆”中的其他服务器比较i
- 星标数多于此分类中其他 5862 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 5862 个服务器的 6% 更新
- 基础检查结果等于或优于此分类中其他 5862 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Scispot MCP 安全吗?
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
它还在维护吗?
GitHub 仓库最后更新于–,最新版本(1.0.0)于8个月前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
有什么可以替代它?
同一分类中有:Context7, Codebase Memory, Exa
替代选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Exa
Connect AI agents to Exa for web search, content fetching, and multi-step research.
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Scispot MCP Server
Connect Claude, Cursor, or another MCP client to your Scispot lab workspace — query Labsheets, manage ELN experiments, protocols, documentation, storage locations, manifests, and more, all through natural language.
Use with Cursor
This repository is also a Cursor plugin. It connects Cursor's agent to Scispot's hosted MCP server at https://mcp.scispot.io/ (streamable HTTP).
Install
- Open Cursor Settings → Plugins.
- Search for Scispot and click Install.
- When Cursor connects to the server, it opens the Scispot sign-in page in your browser. Sign in with your Scispot account to authorize the connection (OAuth). There is no API key to paste into Cursor.
Or run /add-plugin scispot in chat.
The plugin adds this MCP server:
{
"mcpServers": { "scispot": { "type": "http", "url": "https://mcp.scispot.io/" } } }
Requirements
- A Scispot account with Super Admin access, or an account with Dry Lab access.
- Tool calls run with your Scispot permissions. The agent can see and change only what your account allows.
Example prompts
- "List my Scispot Labsheets."
- "Show the schema of the 'Cell Lines' Labsheet, then find rows where Status is 'Active'."
- "List the protocols in the 'Genomics' Labspace and summarize the 'DNA Extraction SOP' protocol."
- "Look up the manifest with barcode 'PLT-00142' and show which wells are filled."
- "Create an experiment called 'Western Blot Optimization Round 3' in the 'Protein Lab' Labspace and add a summary of today's run."
Start with a read-only request such as "List my Scispot Labsheets" to confirm the connection.
Write tools
Start with read-only requests. Review the data and the planned action before you approve a write.
For important records, ask the agent to summarize the proposed changes before it creates or updates data. Review the resulting record in Scispot after the action completes.
Eight tools are marked destructive because they overwrite existing rows or page content: update_labsheet_rows, update_labsheet_rows_by_id_column, write_to_experiment, write_to_protocol, write_to_documentation, and link_manifest_to_* (when position is replace).
For regulated workflows, make sure your use of Cursor and its data handling meets your organization's validation, review, and approval requirements.
Description
The Scispot MCP Server is a remote Model Context Protocol (MCP) server that integrates Scispot's Lab Operating System with AI assistants like Claude. It provides 55 tools spanning Labsheet data management, Electronic Lab Notebook (ELN) operations, inventory/storage lookups, Labflow sample tracking, and Jazz apps. The server runs as an AWS Lambda function and authenticates via OAuth 2.0 with PKCE.
Features
- Labsheet Management — List, search, and filter Labsheet rows; inspect schemas; add and update data; organize by folders.
- ELN Experiments — List, read, create, and write content to experiments; link Labsheet rows for traceability.
- ELN Protocols — List, read, create, and write structured content (text, sections, files, images) to protocols; link Labsheet rows.
- ELN Documentation — List, read, create, and write to documentation entries; link Labsheet rows.
- Storage & Inventory — Browse storage locations (freezers, rooms, cabinets) and fetch manifests (plates, boxes, racks) by ID or barcode.
- Labflows — List sample UUIDs associated with a Labflow for downstream analysis.
- Labspaces — Discover Labspaces and folders, and create folders for ELN pages.
- Tags — List tag categories, search tag values, and set tags on ELN pages.
- Jazz apps — Read the build guide, then list, create, upload, publish, and roll back custom Jazz apps.
Setup
Choose MCP or the REST API
Use the MCP Server when you want an AI assistant to work with Scispot conversationally. Use the REST API when you build a programmatic integration or automation.
Before you begin
You need:
- A Super Admin Scispot account, or an account with Dry Lab access
- An MCP-compatible AI client
The MCP Server uses https://mcp.scispot.io.
Security and permissions
The MCP Server respects your existing Scispot permissions. You can access only the data and actions that your Scispot account allows.
Web connectors use OAuth. Sign in with your Scispot account when the client asks you to authorize the connection.
Connect Claude.ai
Use Claude.ai's custom connector flow. Sign in with your Scispot account when prompted.
- In Claude.ai, open Settings, then Connectors. Select Add custom connector.
- Search for Scispot.io in the connector search bar.
- Click Connect to Claude.
- Complete authentication by logging in with your Scispot account.
Test the connection with a read-only request such as: "List my Scispot Labsheets."
Connect Claude Code
Claude Code supports remote MCP servers over HTTP. Add Scispot as an HTTP MCP server, then authenticate in the client.
- In your terminal, run:
claude mcp add --transport http scispot-mcp https://mcp.scispot.io/
- Open Claude Code with the
claudecommand. - Enter
/mcpto check your MCP connections. - Select the scispot-mcp connection, choose Authenticate, and log in with your Scispot account.
- Start or restart Claude Code. Ask it to list your Scispot Labsheets to confirm that it can discover the server tools.
Test the connection with a read-only request such as: "List my Scispot Labsheets."
Connect another MCP-compatible client
You can connect other clients that support remote HTTP MCP servers. The exact labels vary by client.
- Add a remote MCP server or connector in your client.
- Set the connection URL to
https://mcp.scispot.io. - Choose OAuth when your client supports the Scispot OAuth flow.
- When prompted, log in with your Scispot account.
- Confirm the connection with a read-only request before you perform a write operation.
Contact Customer Success at cs@scispot.io if your client cannot complete the OAuth flow or does not support custom HTTP headers.
Use write actions safely
Start with read-only requests. Review the data and the planned action before you approve a write.
For important records, ask the AI to summarize the proposed changes before it creates or updates data. Review the resulting record in Scispot after the action completes.
Tools that change data require the same permissions as the equivalent action in Scispot. Eight tools are marked destructive because they overwrite existing rows or page content: update_labsheet_rows, update_labsheet_rows_by_id_column, write_to_experiment, write_to_protocol, write_to_documentation, and link_manifest_to_* (when position is replace).
For regulated workflows, make sure your use of the AI client and its data handling meets your organization's validation, review, and approval requirements.
Troubleshooting
You cannot add the connector
Verify that you entered https://mcp.scispot.io exactly.
Authentication fails
Contact Customer Success at cs@scispot.io if you cannot authenticate.
You cannot see data or perform an action
The MCP Server uses your Scispot permissions. Confirm that you can complete the same action in Scispot with your account.
The AI proposes an unexpected change
Do not approve the action. Ask the AI to explain the proposed change, then verify the target records in Scispot before you continue.
Examples
Example 1: Explore and query Labsheet data
User prompt: "Show me all the Labsheets in my workspace, then find the schema for the 'Cell Lines' Labsheet and search for rows where the Status column equals 'Active'."
What happens:
- Server calls
list_labsheetsto return all available Labsheets - Server calls
get_labsheet_schemafor "Cell Lines" to discover column names and types - Server calls
search_labsheet_rowswith a mandatory filter on the Status column - Returns matching rows with all column data
Example 2: Create an experiment and write a protocol summary
User prompt: "Create a new experiment called 'Western Blot Optimization Round 3' in the 'Protein Lab' Labspace, then write a summary of the protocol steps I'll be using."
What happens:
- Server calls
list_labspacesto confirm "Protein Lab" exists and get its location - Server calls
create_experiment_stubwith the name and location - Server calls
write_to_experimentto append the protocol summary as HTML content - Returns confirmation with the new experiment details
Example 3: Link Labsheet samples to a protocol with structured content
User prompt: "Find all samples in the 'Reagent Inventory' Labsheet where the Lot Number is 'LOT-2025-001', link them to the 'Sample Preparation v2' protocol in the 'QC Lab' Labspace, and add a structured section to the protocol documenting the linked samples."
What happens:
- Server calls
search_labsheet_rowsto find matching rows in "Reagent Inventory" - Server calls
link_labsheet_to_protocolto create traceability links between the rows and the protocol - Server calls
write_to_protocolwithcontent_type='json'and a structured elements array containing a section header and text descriptions - Returns confirmation of linked rows and updated protocol content
Example 4: Browse storage locations and fetch a manifest
User prompt: "Show me all storage locations in my workspace, then look up the manifest with barcode 'PLT-00142'."
What happens:
- Server calls
list_locationsto return all root-level storage locations (freezers, rooms, cabinets) - Server calls
get_manifestwith the barcode to fetch the plate/container details including all wells or slots - Returns the full manifest layout with sample positions
Example 5: Navigate ELN structure and read documentation
User prompt: "List all Labspaces, then show me the protocols in the 'Genomics' Labspace, and read the full content of the 'DNA Extraction SOP' protocol."
What happens:
- Server calls
list_labspacesto discover available Labspaces - Server calls
list_protocolswith location "Genomics" to list all protocols - Server calls
get_protocolby name to fetch the full protocol content - Returns the complete protocol text with formatting
Available Tools
Tools below match the production server at https://mcp.scispot.io/ (55 tools). Destructive follows the server's destructiveHint: those calls can overwrite existing rows or page content.
Read-Only Tools (27)
| Tool | Description |
|---|---|
list_labsheets | List all Labsheets in the workspace |
get_labsheet_schema | Get column definitions for a Labsheet |
search_labsheet_rows | Search and filter Labsheet rows |
get_labsheet_row | Fetch a single row by UUID |
get_labsheet_row_by_id | Fetch a single row by its ID column value |
list_labsheet_folders | List Labsheet folders, or the Labsheets in a folder |
get_image_thumbnail | Download a row's image thumbnail |
list_labspaces | List all ELN Labspaces |
get_labspace | Fetch a Labspace by name |
get_labspace_folder | Fetch an ELN folder by name or UUID |
list_experiments | List experiments in a folder or location |
list_experiment_page_templates | List experiment templates available when creating an experiment |
get_experiment | Fetch full experiment content |
list_protocols | List protocols in a folder or location |
list_protocol_page_templates | List protocol templates available when creating a protocol |
get_protocol | Fetch full protocol content |
list_documentations | List documentation entries in a folder or location |
list_documentation_page_templates | List documentation templates available when creating an entry |
| `get_
只显示了开头部分;其余内容请在仓库中阅读