Zelesia MCP server
{
"mcpServers": {
"zelesia": {
"type": "http",
"url": "https://mcp.zelesia.com/mcp"
}
}
}{
"mcpServers": {
"zelesia": {
"type": "http",
"url": "https://mcp.zelesia.com/mcp"
}
}
}{
"mcpServers": {
"zelesia": {
"type": "http",
"url": "https://mcp.zelesia.com/mcp"
}
}
}{
"servers": {
"zelesia": {
"type": "http",
"url": "https://mcp.zelesia.com/mcp"
}
}
}{
"mcpServers": {
"zelesia": {
"type": "http",
"url": "https://mcp.zelesia.com/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.1
What it does
Zelesia is a hosted MCP server that makes your saved LinkedIn posts searchable by AI assistants. Save posts on LinkedIn, and Claude, ChatGPT, or other MCP clients can search your library by meaning and keyword, then cite the original posts in their answers.
- Ask your AI assistant about topics from LinkedIn posts you saved, and get answers with citations back to the original posts.
- Search your LinkedIn library by topic or keyword without opening LinkedIn, using natural language queries through your AI assistant.
- Build a knowledge base from LinkedIn content you found valuable, accessible to multiple AI tools you use.
Tools this server exposes
| Tool | Does |
|---|---|
| library_map | Returns an index of your library showing the number of saved posts, date range, topics covered, and headlines. |
| search_library | Searches your saved posts by meaning and keyword, returning topic, link to the original post, and excerpts with pagination by cursor. |
| search | ChatGPT-compatible search tool that queries your saved posts library. |
| fetch | ChatGPT-compatible fetch tool that retrieves details from your saved posts library. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.