SilverBulletSAFE
A Model Context Protocol (MCP) server to interact with your SilverBullet notes and data.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
This project provides a Model Context Protocol (MCP) server that acts as a bridge to your SilverBullet instance. It enables Large Language Models (LLMs) and other MCP-compatible clients to interact with your SilverBullet notes and data by exposing them through standardized MCP tools and resources.
The server is designed to be run via Docker Compose alongside your existing SilverBullet Docker container. It handles authentication and provides a secure way for external applications to access and manipulate your SilverBullet space.
Asking Claude to create a retirement projection, based on my notes.
Prerequisites
- Docker
- Docker Compose
Getting Started
- Clone the repository:
git clone https://github.com/Ahmad-A0/silverbullet-mcp.git cd silverbullet-mcp
- Create an environment file:
Copy the contents of .env.example to a new file named .env.
cp .env.example .env
Update the .env file with your specific values:
SB_AUTH_TOKEN: The token this MCP server uses to access SilverBullet. For multi-space servers, use a Dashboard-issued API token with access to the target space.MCP_TOKEN: A secure token for clients (e.g., your AI model) to authenticate with this MCP server.SB_API_BASE_URL: (Optional if running via docker-compose as defined) The base URL for the SilverBullet API. Defaults tohttp://silverbullet:3000in thedocker-compose.yml.PORT: (Optional if running via docker-compose as defined) The port the MCP server will listen on. Defaults to4000.
- Build and run the services using Docker Compose:
docker compose up --build
This command will:
- Build the Docker image for the
silverbullet-mcp-serverif it doesn't exist or ifDockerfileor related files have changed. - Pull t
1704717ebe98OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add silverbullet-mcp-server --env MCP_TOKEN=${MCP_TOKEN} --env SB_AUTH_TOKEN=${SB_AUTH_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"silverbullet-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"MCP_TOKEN": "${MCP_TOKEN}",
"SB_AUTH_TOKEN": "${SB_AUTH_TOKEN}"
}
}
}
}Exposed tools (8)
5 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
create-note | write | |
delete-note | destructive | |
edit-note | write | |
list-notes | read | |
read-multiple-notes | read | |
read-note | read | |
search-notes | read | |
search-replace-note | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (6)
delete-note
env: { PATH: process.env.PATH, PORT: String(port), MCP_TOKEN: 'fixture-mcp-token', SB_AUTH_TOKEN: external.token || 'fixture-sb-token', SB_API_BASE_URL: external.url || `http://127.0.0.1:${backend.addconst base = `http://127.0.0.1:${port}`;@modelcontextprotocol/sdk, diff, express, zod, @types/express, @types/node, ajv, typescript
retirement-prompt.gif
and test-only tokens; it does not read `.env` or access your `space/` directory.
Gates applied: no_behavioural_pass.
1704717ebe98full audit observations/trust-audit/mcp-server/ahmad-a0__silverbullet.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 1704717ebe98 | SAFE | B | 89 | first audit |
Questions
What is the SilverBullet MCP server?
A Model Context Protocol (MCP) server to interact with your SilverBullet notes and data.
What tools does SilverBullet expose?
8 in total: 5 read-only, 2 that write, and 1 that can delete or overwrite (delete-note). Every one is listed on this page with its risk.
Is SilverBullet safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does SilverBullet need?
It reads MCP_TOKEN and SB_AUTH_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does SilverBullet run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as silverbullet-mcp-server at 1.2.0.
How current is this page?
The grade is for one exact copy of the source (1704717ebe98), read on 2026-10-08. The repository is watched and re-audited when it changes.