SalesTouch
MCP server for AI-native LinkedIn prospecting. It enables lead research, audience building, conversation management, and controlled outreach actions such as messaging and publishing through an OAuth-protected remote endpoint.
README
SalesTouch
SalesTouch is an AI-native GTM prospecting platform. It helps agents research and qualify prospects, build audiences, start conversations, manage follow-ups, and execute controlled LinkedIn outreach. It provides account, conversation, lookup, outreach, engagement, publishing, queue, and paginated extraction tools through an OAuth-protected remote endpoint.
SalesTouch is not affiliated with, endorsed by, or sponsored by LinkedIn.
Install
Claude Desktop, Cowork, or Claude Code
In Claude Desktop or Cowork, add the marketplace antoinedsh/salestouch, then
enable the salestouch plugin and complete OAuth from /mcp.
In Claude Code:
/plugin marketplace add antoinedsh/salestouch
/plugin install salestouch@salestouch
/mcp
Cursor
Install this repository as a Cursor plugin, or add the following remote MCP configuration:
{
"mcpServers": {
"salestouch": {
"url": "https://www.salestouch.io/api/mcp"
}
}
}
Any Streamable HTTP client
Use https://www.salestouch.io/api/mcp and name the server salestouch. The
client discovers the SalesTouch OAuth flow automatically; no static API key or
LinkedIn credential belongs in the MCP configuration.
OAuth and first check
The browser authorization flow grants scoped SalesTouch access. LinkedIn passwords, cookies, and authentication secrets are never shared with the AI client.
Verify the connection with a read-only request:
List the LinkedIn accounts connected to my SalesTouch workspace.
Three complete workflows
1. Research a lead without changing external state
- Ask SalesTouch to look up a profile URL.
- Ask for the profile's recent posts.
- Ask the agent to summarize useful context and draft a message.
- Review the draft; no message is sent until a mutation tool is authorized.
2. Review a conversation and send an exact reply
- Search the conversation by profile URL.
- Read the bounded message history.
- Ask the agent to draft a reply without sending.
- Confirm the recipient and exact text, then authorize
linkedin_message.
3. Turn post engagement into a paginated result
- Provide a LinkedIn post URL.
- Run
scrape_linkedin_post_reactionsorscrape_linkedin_post_comments. - Read the bounded preview and stored result id.
- Continue with
scrape_result_pageuntil the result is complete.
Safety and limitations
- Read tools are non-destructive and idempotent.
- Messages, invitations, likes, comments, and publications modify LinkedIn and are non-idempotent.
- Cancelling a queued action modifies SalesTouch state and cannot be assumed idempotent.
- Availability depends on an active SalesTouch plan, a connected LinkedIn account, platform availability, permissions, and usage limits.
- SalesTouch does not bypass LinkedIn safeguards. Users are responsible for reviewing targets and content and for complying with applicable platform rules and law.
Troubleshooting
If OAuth fails, reconnect from the MCP client, confirm the endpoint, verify the SalesTouch plan and connected account, then retry the read-only account check. Never paste credentials, cookies, OAuth tokens, private messages, or prospect data into a support request.
Documentation and support
- Documentation
- Getting started
- Authentication and scopes
- Troubleshooting
- OpenAI plugin submission
- Claude directory submission
- Support
- Security
- Privacy
- Terms
- Email: support@salestouch.io
The files in this public distribution wrapper are licensed under the MIT License. The hosted SalesTouch backend remains proprietary.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。