Slack MCP Server
Slack 模型上下文协议服务器
这是一个连接器,允许 Claude Desktop(或任何 MCP 客户端)与您的 Slack 工作区交互以发布消息和查询所有用户的列表。
本地开发
为了在本地运行此客户端,请将以下配置添加到您的 Claude Desktop MCP Server 配置文件中:
{
"mcpServers": {
"mcp-slack-local": {
"command": "node",
"args": ["/path/to/project/dist/index.js"], <---- replace this with your project path
"env": {
"SLACK_BOT_USER_OAUTH_TOKEN": "test-bot-token",
"SLACK_TEAM_ID": "test-team-id"
}
},
}
}在此之后,您应该能够使用以下示例提示在 Claude 桌面应用程序中测试此实现:
“你能列出我的 Slack 团队的所有用户吗?”
“您能向我的 ID 为
<channel id>Slack 频道发送一条欢迎消息吗?”
在本地运行服务器:
node dist/index.js在另一个终端中构建
npm run watchRelated MCP server: Slack MCP Server by CData
Slack 权限范围
以下权限已经实现:
允许 | 描述 | 实施的 |
app_configurations:读取 | 通过 App Manifest API 读取应用配置信息 | ❌ |
应用程序配置:写入 | 通过 App Manifest API 编写应用配置信息并创建应用 | ❌ |
app_mentions:阅读 | 查看在应用所在的对话中直接提及 @your_slack_app 的消息 | ❌ |
助理:写 | 让你的 Slack 应用充当 AI 助手 | ❌ |
书签:阅读 | 列出书签 | ❌ |
书签:写 | 创建、编辑和删除书签 | ❌ |
调用:读取 | 查看正在进行的通话和过去的通话信息 | ❌ |
调用:写入 | 在工作区中开始和管理通话 | ❌ |
画布:阅读 | 您的 Slack 应用程序将能够访问在 Slack 内部创建的画布的内容。 | ❌ |
画布:书写 | 您的 Slack 应用程序将能够创建、编辑和删除画布。 | ❌ |
频道:历史 | 查看已添加 Slack 应用的公共频道中的消息和其他内容 | ❌ |
频道:加入 | 加入工作区中的公共频道 | ❌ |
频道:管理 | 管理已添加 Slack 应用的公共频道并创建新的频道 | ❌ |
频道:阅读 | 查看工作区中公共频道的基本信息 | ❌ |
渠道:写邀请 | 邀请成员加入公共频道 | ❌ |
频道:写入主题 | 设置公共频道的描述 | ❌ |
聊天:写 | 在批准的频道和对话中发布消息 | ✅ |
聊天:写入.自定义 | 使用自定义用户名和头像以 @your_slack_app 身份发送消息 | ❌ |
聊天:写入.公共 | 向 @your_slack_app 不属于的频道发送消息 | ❌ |
命令 | 添加人们可以使用的快捷方式和/或斜线命令 | ❌ |
对话.连接:管理 | 允许您的 Slack 应用管理 Slack Connect 频道 | ❌ |
对话.连接:读取 | 接收发送到您的 Slack 应用所在频道的 Slack Connect 邀请事件 | ❌ |
对话.连接:写入 | 为已添加 Slack 应用的频道创建 Slack Connect 邀请,并接受发送到 Slack 应用的邀请 | ❌ |
数据存储:读取 | 查看 Slack App Datastore 中的数据 | ❌ |
数据存储:写入 | 将数据写入 Slack App Datastore | ❌ |
dnd:阅读 | 查看工作区中人员的“请勿打扰”设置 | ❌ |
表情符号:阅读 | 在工作区中查看自定义表情符号 | ❌ |
文件:读取 | 查看已添加 Slack 应用的频道和对话中共享的文件 | ❌ |
文件:写入 | 以 Slack 应用的形式上传、编辑和删除文件 | ❌ |
群组:历史 | 查看已添加 Slack 应用的私人频道中的消息和其他内容 | ❌ |
群组:阅读 | 查看已添加 Slack 应用的私人频道的基本信息 | ❌ |
组:写 | 管理已添加 Slack 应用的私人频道并创建新频道 | ❌ |
群组:写邀请 | 邀请成员加入私人频道 | ❌ |
群组:写主题 | 设置私人频道的描述 | ❌ |
im:历史 | 查看已添加 Slack 应用的直接消息中的消息和其他内容 | ❌ |
im:阅读 | 查看已添加 Slack 应用的私信的基本信息 | ❌ |
im:写 | 开始与他人直接发送消息 | ❌ |
im:写主题 | 在直接消息中设置描述 | ❌ |
传入 webhook | 创建单向 webhook 以将消息发布到特定频道 | ❌ |
links.embed:写入 | 在消息和应用程序界面中嵌入视频播放器 URL | ❌ |
链接:阅读 | 查看消息中的 URL | ❌ |
链接:写 | 在消息中显示 URL 预览 | ❌ |
元数据.消息:读取 | 允许您的 Slack 应用读取已添加 Slack 应用的频道中的消息元数据 | ❌ |
mpim:历史 | 查看已添加 Slack 应用的群组私信中的消息和其他内容 | ❌ |
mpim:读取 | 查看已添加 Slack 应用的群组私信的基本信息 | ❌ |
mpim:写入 | 与他人开始群组直接消息 | ❌ |
mpim:写入主题 | 设置群组私信中的描述 | ❌ |
没有任何 | 无需作用域即可执行方法 | ❌ |
引脚:读取 | 查看已添加 Slack 应用的频道和对话中的固定内容 | ❌ |
引脚:写 | 添加和删除固定的消息和文件 | ❌ |
反应:阅读 | 在已添加 Slack 应用的频道和对话中查看表情符号反应及其相关内容 | ❌ |
反应:写 | 添加和编辑表情符号反应 | ❌ |
提醒:阅读 | 查看由 Slack 应用创建的提醒 | ❌ |
提醒:写 | 添加、删除提醒或将提醒标记为已完成 | ❌ |
远程文件:读取 | 查看应用程序在工作区中添加的远程文件 | ❌ |
远程文件:共享 | 代表用户共享远程文件 | ❌ |
远程文件:写入 | 代表用户添加、编辑和删除远程文件 | ❌ |
搜索:读取文件 | 在文件中搜索工作区的内容 | ❌ |
搜索:read.im | 在私信中搜索工作区的内容 | ❌ |
搜索:read.mpim | 在群组私信中搜索工作区的内容 | ❌ |
搜索:read.private | 在私人频道中搜索工作区的内容 | ❌ |
搜索:read.public | 在公共频道中搜索工作区的内容 | ❌ |
团队.计费:读取 | 允许您的 Slack 应用读取已安装 Slack 应用的工作区的计费计划 | ❌ |
团队.偏好设置:读取 | 允许您的 Slack 应用读取已安装 Slack 应用的工作区的首选项 | ❌ |
团队:阅读 | 查看 Slack 应用所连接的工作区的名称、电子邮件域和图标 | ❌ |
tokens.basic | 无需作用域即可执行方法 | ❌ |
触发器:读取 | 阅读新的平台触发器 | ❌ |
触发器:写入 | 创建新的平台触发器 | ❌ |
用户组:阅读 | 查看工作区中的用户组 | ❌ |
用户组:写 | 创建和管理用户组 | ❌ |
用户.个人资料:阅读 | 查看工作区中人员的个人资料详细信息 | ❌ |
用户:阅读 | 查看工作区中的人员 | ✅ |
用户:阅读.电子邮件 | 查看工作区中人员的电子邮件地址 | ❌ |
用户:写 | 设置 Slack 应用的状态 | ❌ |
工作流程.步骤:执行 | 添加人们可以在 Workflow Builder 中使用的步骤 | ❌ |
工作流程.模板:读取 | 阅读工作流模板 | ❌ |
工作流.模板:写入 | 编写工作流模板 | ❌ |
接触
如果您有任何疑问,请随时通过AVIMBU联系我们。
Available Tools
2 toolsslack_get_usersB
Get a list of all users in the workspace with basic information
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | Pagination cursor for next page of results | |
| limit | No | Maximum number of users to return (default 100, max 200) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. While it indicates this is a read operation ('Get'), it doesn't mention important behavioral aspects like authentication requirements, rate limits, error conditions, or what 'basic information' specifically includes. For a tool that presumably accesses workspace data, this leaves significant gaps in understanding how it behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that communicates the core purpose without any wasted words. It's appropriately sized for a straightforward list operation and front-loads the essential information. Every word earns its place in this concise formulation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a relatively simple list operation with 2 parameters and no output schema, the description provides adequate but minimal context. It covers what the tool does but lacks important operational details like authentication requirements, rate limits, and what specific user information is returned. Without annotations or output schema, the description should ideally provide more complete guidance about the tool's behavior and results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with both parameters ('cursor' and 'limit') fully documented in the schema. The description doesn't add any additional parameter semantics beyond what's already in the schema. According to the scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no parameter information in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Get') and resource ('list of all users in the workspace'), making the purpose immediately understandable. It specifies 'with basic information' which adds useful context about the scope of returned data. However, it doesn't explicitly differentiate from the sibling tool 'slack_post_message', which is a completely different operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites, appropriate contexts, or comparison with the sibling 'slack_post_message' tool. The agent must infer usage purely from the tool name and description without any explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
slack_post_messageC
Post a new message to a Slack channel
| Name | Required | Description | Default |
|---|---|---|---|
| channel_id | Yes | The Channel ID to post the message to | |
| text | Yes | The message text to post |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. While 'Post a new message' implies a write operation, it doesn't mention authentication requirements, rate limits, error conditions, or what happens if the channel doesn't exist. This leaves significant behavioral gaps for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that communicates the core purpose without any wasted words. It's appropriately sized for a simple tool and gets straight to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what the tool returns, error conditions, authentication requirements, or any behavioral details beyond the basic action. Given the complexity of posting to Slack (which involves permissions, formatting, etc.), more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with both parameters clearly documented in the schema. The description doesn't add any additional semantic context about the parameters beyond what's already in the schema, so it meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Post a new message') and target resource ('to a Slack channel'), making the purpose immediately understandable. However, it doesn't differentiate from its sibling tool 'slack_get_users' beyond the obvious difference in function, which is why it doesn't reach a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives or any prerequisites for usage. It simply states what the tool does without context about appropriate scenarios or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
The two tools have clearly distinct purposes: one retrieves user information and the other posts messages, with no overlap in functionality. An agent can easily differentiate between them based on their descriptions.
Both tools follow a consistent 'slack_verb_noun' pattern (slack_get_users, slack_post_message), using snake_case and clear action-object naming. This makes them predictable and easy to understand.
With only 2 tools, the server feels severely under-scoped for a Slack integration, lacking essential operations like reading messages, managing channels, or handling reactions. This minimal set limits agent capabilities significantly.
The tool surface is highly incomplete for a Slack server, missing core functionalities such as reading channel messages, listing channels, updating or deleting messages, and interacting with threads. This will cause frequent agent failures in typical Slack workflows.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Connect Claude AI to UluP Spaces via MCP — create projects, nodes, and tasks with OAuth 2.0.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
MCP connector that lets ChatGPT list, search, and run your Apple Shortcuts via a local Mac agent
Connect Claude to your Platform7n workspaces — chat, links, and tasks. One-click OAuth.
Related MCP Servers
- -licenseNot gradedqualityAmaintenanceMCP Server for the Slack API, enabling Claude to interact with Slack workspaces.87,50690,042MIT
- AlicenseNot gradedqualityDmaintenanceThis read-only MCP Server allows you to connect to Slack data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP-compatible clients to interact with Slack through Web API tools and subscribe to inbound Slack messages via Socket Mode notifications.202MIT
- FlicenseBqualityAmaintenanceMCP server for Slack workspace integration, exposing 40+ Slack operations as tools for Claude Desktop and providing a clean async Python API.641
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AVIMBU/slack-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server