Submit to Anthropic Connectors Directory
Get your MCP server listed alongside Gmail, Notion, and Slack in Claude's official connector marketplace. This covers the complete submission process — from technical requirements to filling out the 6-page form.
Prerequisites checklist
Before submitting, your server must meet ALL of these. Missing any one will delay or reject your submission.
- - [ ] MCP server is live, deployed, and accessible via HTTPS
- [ ] OAuth 2.0 implemented (if auth required)
- [ ] All tools have safety annotations (
readOnlyHint, destructiveHint) - [ ] All tools have human-readable titles
- [ ] Privacy policy published at a public URL
- [ ] Terms of service published at a public URL
- [ ] Support channel (GitHub issues or email)
- [ ] At least 3 example prompts prepared
- [ ] Test account with sample data ready
- [ ] Server tested end-to-end on Claude Desktop or claude.ai
The submission form
Submit at: https://docs.google.com/forms/d/e/1FAIpQLSeafJF2NDI7oYx1r8o0ycivCSVLNq92Mpc1FPxMKSw1CzDkqA/viewform
The form has 6 pages. Here's what to put in each field.
Page 1: Submission Details
Company Information:
- - Company/Organization Name — Your name or company
- Company/Organization URL — Your website
- Primary Contact Name — Your full name
- Primary Contact Email — Your email (reviewers will contact you here)
- Primary Contact Role — e.g., "Creator & Maintainer"
- Anthropic Point of Contact — Leave blank unless you know someone
Server Details:
- - MCP Server Name — Short name, no "MCP" or "Server" in it (e.g., "Tidal", not "Tidal MCP Server")
- MCP Server URL — Select "Universal URL", then enter your endpoint (e.g.,
https://example.com/api/mcp) - Tagline — Max 55 characters. Format: "Verb your thing with Claude" (e.g., "Search, play, and manage your Tidal music library")
MCP Server Description (50-100 words, shown in-app):
Template: "[Action] your [service] directly from Claude. [Key capabilities in 2-3 sentences]. [Number] tools covering [categories]. OAuth authentication with your own [service] account."
Use Cases + Examples (minimum 3):
Each example should show a realistic user prompt and explain what tools fire. Template:
CODEBLOCK0
Good examples show multi-step orchestration — not just single tool calls.
Connection requirements:
State what users need (e.g., "Requires a [Service] subscription. Available worldwide.")
Read/Write Capabilities: Select "Read + Write" if you have any write tools.
Is this an MCP App: Select "No" unless you have interactive UI elements.
Third-party Connections: Check what applies:
- - "Third-party data retrieval" — if you fetch from an external API
- "Third-party data modification" — if you write to an external API
Data Handling: Check all that apply (typically all 4):
- - Server only accesses data explicitly requested by user
- No data is stored beyond session requirements
- Data transmission is encrypted (HTTPS/TLS)
- GDPR compliant
Personal health data: "No" (unless your service handles health data)
Categories: Pick the closest (e.g., "Media & Entertainment", "Business & Productivity")
Sponsored content: "No, there is no sponsored content or advertisements"
Authentication:
- - Authentication Type: "OAuth 2.0"
- Auth Client: "Dynamic OAuth Client (e.g., DCR, CIMD)"
- Static Client ID/Secret: Leave blank for dynamic registration
- Transport Support: Check "Streamable HTTP"
Documentation & Support:
- - Documentation Link — Your GitHub repo or docs site
- Privacy Policy — URL to your privacy policy page
- Data Processing Agreement URL — Leave blank unless you have one
- Support Channel — GitHub issues URL or support email
Page 2: Testing
Testing Account Credentials:
If your server requires auth, provide credentials. Recommended: "Test account credentials will be shared via 1Password secure link. Contact [email] to receive the link."
Test Account Setup Instructions:
Write clear steps:
CODEBLOCK1
Test Data Availability: Check both:
- - Test account includes sample data
- All tools can be tested with provided data
List of tools:
Comma-separated, format: INLINECODE3
Tool Titles & Annotations: Check both:
- - I've specified user-friendly titles for all tools
- I've specified accurate tool annotations for all tools
List of resources: Leave blank (unless you expose MCP resources)
List of prompts: Leave blank (unless you expose MCP prompts, which are optional)
Page 3: Launch Readiness & Media
Timeline - Server GA Date: Today's date (your server should already be live)
Testing complete: Check where you've tested:
- - Claude.ai (web)
- Claude Desktop
Server Logo: Provide your SVG logo URL or upload it. Square, 1:1 aspect ratio.
Server Logo URL: Verify that https://www.google.com/s2/favicons?domain=YOUR_DOMAIN&sz=64 returns your icon. Check the box to confirm.
Promotional Images: Upload 3-5 screenshots of your MCP server in use on Claude. Show:
- 1. A search/discovery interaction
- A create/write operation
- A multi-step orchestration
Tips for screenshots:
- - Use wide window (1000px+)
- Start conversation with "Respond in English. Format with clear headings and tables."
- Show the tool calls and results clearly
Link to Promotional Materials: Optional. Your website URL.
Page 4: Skills & Plugins (Optional)
If you have a SKILL.md file for Claude Code:
- - Skill Name — Your skill name
- Skill Description — Short description
- GitHub URL of Skill — Public repo URL
- Extra Information — Mention other marketplaces (ClawHub, skills.sh)
Page 5: Submission Requirements Checklist
Policy Compliance — Check all 5 (all are required):
- - I have reviewed and agree to the Software Directory Policy
- My server does NOT enable cross-service automation
- My server does NOT transfer money
- My MCP server is live and ready for production traffic
- I work for the company that owns/controls the API endpoints
Note: The last checkbox is about YOUR MCP server endpoint, not the upstream API.
Technical Requirements — Check all 6:
- - OAuth 2.0 fully implemented
- All tools include safety annotations
- Server accessible via HTTPS
- CORS configured
- Claude IPs allowlisted (check if behind firewall)
- Tested on latest Claude build
Documentation Requirements — Check all 4:
- - Documentation published and accessible
- Includes setup instructions and tool descriptions
- Privacy policy published
- Terms of service published
Testing Requirements — Check all 3:
- - Test account with sample data ready
- Test credentials valid for 30+ days
- All tools functional and tested
Additional Information: Optional. Good place to mention:
- - Open source status and license
- Where else the server is available (Smithery, ClawHub)
- Any unique value proposition
After submission
- - Anthropic reviews submissions but cannot guarantee inclusion or timeline
- For updates to an existing listing, email mcp-review@anthropic.com
- Check back in 2-3 weeks if no response
Privacy policy template
Your privacy policy should cover:
- - What data is collected (OAuth tokens, user queries)
- Where data is stored (Redis/database, TTL/retention)
- What third-party services are used (upstream API, hosting)
- How to delete data (revoke access, delete session files)
- Contact information
Terms of service template
Your ToS should cover:
- - Service description
- Requirements (subscription needed, acceptable use)
- Disclaimer of warranties ("as is")
- Limitation of liability
- Third-party services and their terms
- Open source license
Also publish on Smithery
After submitting to Anthropic, also publish on Smithery for immediate distribution:
- 1. Go to https://smithery.ai/new
- Enter your MCP server URL
- Smithery scans tools automatically
- Configure display name, description, homepage, icon
- Uncheck "Unlisted" to appear in search
Smithery gives you instant visibility while waiting for Anthropic's review.
提交至 Anthropic 连接器目录
让你的 MCP 服务器与 Gmail、Notion 和 Slack 一同出现在 Claude 官方连接器市场中。本文涵盖完整的提交流程——从技术要求到填写 6 页表单。
前提条件清单
提交前,你的服务器必须满足以下所有条件。任何一项缺失都会导致提交延迟或拒绝。
- - [ ] MCP 服务器已上线、部署完毕,可通过 HTTPS 访问
- [ ] 已实现 OAuth 2.0(如需身份验证)
- [ ] 所有工具均包含安全注释(readOnlyHint、destructiveHint)
- [ ] 所有工具均有人类可读的标题
- [ ] 隐私政策已发布在公开 URL 上
- [ ] 服务条款已发布在公开 URL 上
- [ ] 支持渠道(GitHub Issues 或电子邮件)
- [ ] 至少准备了 3 个示例提示词
- [ ] 测试账户已准备好,包含示例数据
- [ ] 服务器已在 Claude Desktop 或 claude.ai 上完成端到端测试
提交表单
提交地址:https://docs.google.com/forms/d/e/1FAIpQLSeafJF2NDI7oYx1r8o0ycivCSVLNq92Mpc1FPxMKSw1CzDkqA/viewform
该表单共 6 页。以下是每个字段的填写说明。
第 1 页:提交详情
公司信息:
- - 公司/组织名称 — 你的姓名或公司名称
- 公司/组织网址 — 你的网站
- 主要联系人姓名 — 你的全名
- 主要联系人邮箱 — 你的电子邮件(审核人员将通过此邮箱联系你)
- 主要联系人角色 — 例如创建者与维护者
- Anthropic 联系人 — 除非你认识相关人员,否则留空
服务器详情:
- - MCP 服务器名称 — 简短名称,不要包含MCP或Server字样(例如Tidal,而非Tidal MCP Server)
- MCP 服务器 URL — 选择通用 URL,然后输入你的端点(例如 https://example.com/api/mcp)
- 标语 — 最多 55 个字符。格式:用 Claude [动词] 你的 [事物](例如搜索、播放和管理你的 Tidal 音乐库)
MCP 服务器描述(50-100 字,在应用内显示):
模板:直接在 Claude 中[操作]你的[服务]。[2-3 句话描述关键功能]。涵盖[类别]的[数量]个工具。使用你自己的[服务]账户进行 OAuth 身份验证。
用例 + 示例(至少 3 个):
每个示例应展示一个真实的用户提示词,并说明会触发哪些工具。模板:
[用例类别]
[真实用户提示词]
[调用哪些工具以及发生了什么,用 1-2 句话说明]
好的示例应展示多步骤编排——而不仅仅是单个工具调用。
连接要求:
说明用户需要什么(例如需要 [服务] 订阅。全球可用。)
读/写能力: 如果有任何写入工具,选择读取 + 写入。
是否为 MCP 应用: 除非有交互式 UI 元素,否则选择否。
第三方连接: 勾选适用的选项:
- - 第三方数据检索 — 如果从外部 API 获取数据
- 第三方数据修改 — 如果向外部 API 写入数据
数据处理: 勾选所有适用的选项(通常全部 4 项):
- - 服务器仅访问用户明确请求的数据
- 不存储超出会话需求的数据
- 数据传输已加密(HTTPS/TLS)
- 符合 GDPR 要求
个人健康数据: 否(除非你的服务处理健康数据)
类别: 选择最接近的类别(例如媒体与娱乐、商业与生产力)
赞助内容: 否,没有赞助内容或广告
身份验证:
- - 身份验证类型: OAuth 2.0
- 身份验证客户端: 动态 OAuth 客户端(例如 DCR、CIMD)
- 静态客户端 ID/密钥: 动态注册时留空
- 传输支持: 勾选可流式 HTTP
文档与支持:
- - 文档链接 — 你的 GitHub 仓库或文档网站
- 隐私政策 — 隐私政策页面的 URL
- 数据处理协议 URL — 除非你有相关协议,否则留空
- 支持渠道 — GitHub Issues URL 或支持邮箱
第 2 页:测试
测试账户凭据:
如果你的服务器需要身份验证,请提供凭据。建议:测试账户凭据将通过 1Password 安全链接共享。请联系 [邮箱] 获取链接。
测试账户设置说明:
编写清晰的步骤:
- 1. 在 Claude 中点击 [名称] 连接器上的连接
- 使用提供的测试凭据登录
- 尝试:[示例提示词] 以验证
测试账户包含 [预加载了哪些数据]
测试数据可用性: 勾选两项:
- - 测试账户包含示例数据
- 所有工具均可使用提供的数据进行测试
工具列表:
以逗号分隔,格式:tool_name (人类可读名称)
工具标题与注释: 勾选两项:
- - 我已为所有工具指定了用户友好的标题
- 我已为所有工具指定了准确的工具注释
资源列表: 留空(除非你公开了 MCP 资源)
提示词列表: 留空(除非你公开了 MCP 提示词,此为可选)
第 3 页:发布准备与媒体
时间线 - 服务器正式发布日期: 今天的日期(你的服务器应已上线)
测试完成: 勾选你已测试的平台:
- - Claude.ai(网页版)
- Claude Desktop
服务器徽标: 提供你的 SVG 徽标 URL 或上传文件。正方形,1:1 宽高比。
服务器徽标 URL: 验证 https://www.google.com/s2/favicons?domain=YOUR_DOMAIN&sz=64 是否返回你的图标。勾选确认框。
宣传图片: 上传 3-5 张你的 MCP 服务器在 Claude 上使用的截图。展示:
- 1. 搜索/发现交互
- 创建/写入操作
- 多步骤编排
截图技巧:
- - 使用宽窗口(1000px 以上)
- 以请用英文回复。使用清晰的标题和表格进行格式化。开始对话
- 清晰展示工具调用和结果
宣传材料链接: 可选。你的网站 URL。
第 4 页:技能与插件(可选)
如果你有适用于 Claude Code 的 SKILL.md 文件:
- - 技能名称 — 你的技能名称
- 技能描述 — 简短描述
- 技能 GitHub URL — 公开仓库 URL
- 额外信息 — 提及其他市场(ClawHub、skills.sh)
第 5 页:提交要求清单
政策合规性 — 勾选全部 5 项(均为必填):
- - 我已阅读并同意《软件目录政策》
- 我的服务器不启用跨服务自动化
- 我的服务器不涉及资金转账
- 我的 MCP 服务器已上线并准备好处理生产流量
- 我为拥有/控制 API 端点的公司工作
注意:最后一个复选框指的是你的 MCP 服务器端点,而非上游 API。
技术要求 — 勾选全部 6 项:
- - OAuth 2.0 已完全实现
- 所有工具均包含安全注释
- 服务器可通过 HTTPS 访问
- 已配置 CORS
- 已添加 Claude IP 白名单(如果位于防火墙后)
- 已在最新版 Claude 上测试
文档要求 — 勾选全部 4 项:
- - 文档已发布并可访问
- 包含设置说明和工具描述
- 隐私政策已发布
- 服务条款已发布
测试要求 — 勾选全部 3 项:
- - 测试账户已准备好,包含示例数据
- 测试凭据有效期超过 30 天
- 所有工具功能正常且已测试
附加信息: 可选。适合在此处提及:
- - 开源状态和许可证
- 服务器还可在哪些地方使用(Smithery、ClawHub)
- 任何独特的价值主张
提交后
- - Anthropic 会审核提交内容,但无法保证收录或时间安排
- 如需更新已有列表,请发送邮件至 mcp-review@anthropic.com
- 如未收到回复,请在 2-3 周后再次查看
隐私政策模板
你的隐私政策应涵盖: