# sensefold

Connects your private Markdown library of notes and web clips to AI agents. It enables semantic search and lets the model save new links directly from the conversation.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: SenseFoldLabs
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/SenseFoldLabs/sensefold-mcp
- Updated: 2026-09-13
- HTML: https://affpapa.org/en/nevibecode/mcp/sensefold

## What it does

The server runs in the cloud over Streamable HTTP at `https://api.sensefold.app/mcp`. There is no local service to host. It exposes your private Markdown storage to the assistant, covering personal notes and saved articles. The `search_hub` tool performs hybrid retrieval using both literal terms and semantic meaning, accepting tag or date constraints.

Large notes do not overwhelm the context window. The `get_item` tool fetches documents in windows of 8000 characters or via designated chunk offsets. For web collection, `save_link` accepts a URL and processes it in the background. Note that capturing web content consumes your account credits.

Authentication relies on OAuth 2.1 with PKCE or an agent bearer token for automated environments. If you connect with the `read_only` tier, the server hides all writing tools from the client.

## Requirements
- Remote server: `https://api.sensefold.app/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http sensefold https://api.sensefold.app/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add sensefold --url https://api.sensefold.app/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "sensefold": {
            "url": "https://api.sensefold.app/mcp"
        }
    }
}
```

### GitHub Copilot

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

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http sensefold https://api.sensefold.app/mcp
```

## When to use it
- Run hybrid semantic and keyword queries across personal Markdown notes
- Read large notes in windowed chunks to avoid filling the model context
- Save external web links into a personal library directly from agent chat
- Access a unified context across multiple AI assistants without duplicating files

## Example prompts
- Search my Sensefold notes for articles discussing database architecture.
- Save the link `https://sensefold.app/docs/` to my knowledge base.
- List recent items from my library using `list_items`.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
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