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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.