# ZelesIA

Connects your saved LinkedIn posts to your coding agent. Searches your personal library by keywords or meaning and supplies citations with original post links.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: ZelesIA-AI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ZelesIA-AI/zelesia-mcp
- Updated: 2026-09-02
- HTML: https://affpapa.org/en/nevibecode/mcp/zelesia

## What it does

ZelesIA operates as a hosted service at `https://mcp.zelesia.com/mcp` using Streamable HTTP. You do not need to install local packages or run background processes. Authentication relies on an OAuth 2.1 screen, so you avoid pasting API keys into client configuration files. Access revocation takes a single click in your personal account settings.

The server gives your agent tools to query saved content. The `library_map` tool summarizes available topics and date ranges so the model checks scope first. For queries, `search_library` retrieves excerpts and source URLs using cursor-based pagination. For ChatGPT environments, the endpoint also exposes standard `search` and `fetch` methods. All tools are read-only.

Connecting this server does nothing if your ZelesIA account is empty, because the remote service only queries posts you personally saved.

## Requirements
- Remote server: `https://mcp.zelesia.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http zelesia https://mcp.zelesia.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add zelesia --url https://mcp.zelesia.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "zelesia": {
            "url": "https://mcp.zelesia.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "zelesia": {
            "type": "http",
            "url": "https://mcp.zelesia.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http zelesia https://mcp.zelesia.com/mcp
```

## When to use it
- search saved LinkedIn posts by topic or semantic meaning
- cite original LinkedIn post URLs directly in assistant replies
- check library scope with `library_map` before running detailed queries
- connect external bookmarks without managing static API keys

## Example prompts
- Search my saved LinkedIn posts for takeaways on database scaling.
- Check `library_map` to see what topics I have saved in my account.
- Find the post about prompt engineering tips and give me the link to it.

## Similar
- [Quberi](https://affpapa.org/en/nevibecode/mcp/quberi.md) — MCP server
- [Gurusup](https://affpapa.org/en/nevibecode/mcp/gurusup.md) — MCP server
- [knowledge-synthesis](https://affpapa.org/en/nevibecode/skills/knowledge-synthesis.md) — skill · 6400 installs
- [second-brain-query](https://affpapa.org/en/nevibecode/skills/second-brain-query.md) — skill · 2500 installs
- [llm-wiki](https://affpapa.org/en/nevibecode/skills/nashsu-llm-wiki.md) — skill · 1800 installs
- [tela](https://affpapa.org/en/nevibecode/mcp/tela.md) — MCP server · ★ 87

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md