# silverbullet-ai-mcp

Connects SilverBullet note spaces and silverbullet-ai tools to MCP clients. It lets coding assistants inspect and search your personal workspace directly.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 107
- Author: justyns
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/justyns/silverbullet-ai/tree/HEAD/mcp-bridge
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/silverbullet-ai-mcp

## What it does

This server bridges external coding agents with a SilverBullet personal knowledge base. It surfaces tools from the silverbullet-ai extension over MCP, giving assistants like Claude Code and Cursor direct access to space contents.

Execution relies on Node.js 20 or higher. The package runs via `npx` and configures remote access using the `SB_URL` variable, alongside optional `SB_AUTH_TOKEN` and `SB_SPACE_ID` parameters.

A running SilverBullet instance without Runtime API enabled will reject requests. The silverbullet-ai plug must also be installed in the target space, ideally matching the MCP package version.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `SB_URL`, `SB_AUTH_TOKEN`, `SB_SPACE_ID` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env SB_URL=<SB_URL> --env SB_AUTH_TOKEN=<SB_AUTH_TOKEN> --env SB_SPACE_ID=<SB_SPACE_ID> --transport stdio mcp-bridge -- npx -y silverbullet-ai-mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add mcp-bridge --env SB_URL=<SB_URL> --env SB_AUTH_TOKEN=<SB_AUTH_TOKEN> --env SB_SPACE_ID=<SB_SPACE_ID> -- npx -y silverbullet-ai-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mcp-bridge": {
            "command": "npx",
            "args": [
                "-y",
                "silverbullet-ai-mcp"
            ],
            "env": {
                "SB_URL": "<SB_URL>",
                "SB_AUTH_TOKEN": "<SB_AUTH_TOKEN>",
                "SB_SPACE_ID": "<SB_SPACE_ID>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mcp-bridge": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "silverbullet-ai-mcp"
            ],
            "env": {
                "SB_URL": "<SB_URL>",
                "SB_AUTH_TOKEN": "<SB_AUTH_TOKEN>",
                "SB_SPACE_ID": "<SB_SPACE_ID>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e SB_URL=<SB_URL> -e SB_AUTH_TOKEN=<SB_AUTH_TOKEN> -e SB_SPACE_ID=<SB_SPACE_ID> mcp-bridge npx -y silverbullet-ai-mcp
```
Replace <…> with your own values

## When to use it
- query SilverBullet notes inside Claude Code and Cursor
- expose silverbullet-ai space actions to MCP-compatible assistants
- configure remote SilverBullet access via environment variables

## Example prompts
- Search my SilverBullet workspace for deployment instructions
- Review the linked notes in my SilverBullet space and outline the next steps

## Similar
- [Reactive Resume](https://affpapa.org/en/nevibecode/mcp/reactive-resume.md) — MCP server · ★ 44874
- [screenpipe](https://affpapa.org/en/nevibecode/mcp/screenpipe.md) — MCP server · ★ 22053
- [Inbox Zero](https://affpapa.org/en/nevibecode/mcp/inbox-zero.md) — MCP server · ★ 12791
- [kaneo](https://affpapa.org/en/nevibecode/mcp/kaneo.md) — MCP server · ★ 9602
- [Mindwtr](https://affpapa.org/en/nevibecode/mcp/mindwtr.md) — MCP server · ★ 2318
- [Azure DevOps (ADO)](https://affpapa.org/en/nevibecode/mcp/azure-devops-ado.md) — MCP server · ★ 2067

---
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
