SoloMDBLOCK
A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
The editor where agents live.
[](https://github.com/zhitongblog/solomd/releases/latest) [](LICENSE) [](https://github.com/zhitongblog/solomd/releases) [](https://solomd.app)
🌐 中文 · 日本語 · 한국어 · Deutsch · Français · Español · Português · Italiano · Polski · Nederlands · Türkçe · Svenska · Українська · 🪞 [Gitee mirror →](https://gitee.com/zhitong45/solomd) (faster downloads from China)
**Download the latest release** · **Launch post** · **How we built it** · **Website** · **Security**
### 🤖 Built and maintained by Claude SoloMD is written, tested and released almost entirely by Claude Code, Anthropic's coding agent, working under a human maintainer who sets the direction and decides what ships. Issues and pull requests are triaged and answered by Claude as well — the replies you get here are written by an AI, not typed by a person. We are telling you this for two reasons. You should know what you are trusting with your notes: read the code, it is MIT and all of it is public. And when a reply is confidently wrong — it happens — say so in the thread. That correction is the mechanism.
Your notes live in a folder. **SoloMD is the editor on top — with
b7c64ad6eb8fOBSERVED · 2026-09-28Connect
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 solomd-web --env ASC_KEY_ID=${ASC_KEY_ID} --env ASC_KEY_PATH=${ASC_KEY_PATH} --env KEY=${KEY} -- npx -y [email protected]{
"mcpServers": {
"solomd-web": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ASC_KEY_ID": "${ASC_KEY_ID}",
"ASC_KEY_PATH": "${ASC_KEY_PATH}",
"KEY": "${KEY}"
}
}
}
}Trust audit
BLOCKgrade F · trust 30/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (9 observation(s))
- Network
- declared (12 observation(s))
- Shell
- declared (6 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
dark-C2.png
dark-C2.svg
const parsed = yaml.load(inner);
parsed = yaml.load(raw);
parsed = yaml.load(text);
new Function('module', 'exports', code)(moduleScope, moduleScope.exports);- ``(零宽空格)、``(零宽非连接符)等不可见字符
file_icon.icns
icon.icns
banner.bmp
dialog.bmp
file_icon.icns
`http://127.0.0.1:9399`** (a real headless Chromium: JS rendering, anti-bot,
BASE="${UNZOO_BASE:-http://127.0.0.1:9399/api/v1}"`http://127.0.0.1:9399`** (a real headless Chromium: JS rendering, anti-bot,
BASE="${UNZOO_BASE:-http://127.0.0.1:9399/api/v1}"curl -s --noproxy '*' http://127.0.0.1:9399/api/v1/openapi.json
src: url("data:font/woff2;base64,d09GMgABAAAAAKnQAA0AAAABH1AAAKl5AAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAABmAqSACSZAqEmlCDqBkBNgIkA4MSC4MSAAQgBYMaByAXJBiDEhug47OipDcjNBIhbBwCQRjDrAg2DgAS8ori/3jcGAMK8vwLDiKyUnl'.tok-meta, .cm-formatting, .ͼe': {const bom = body.startsWith('') ? '' : '';const trimmed = body.startsWith('') ? body.slice(1) : body;const bom = doc.startsWith('') ? '' : '';const bom = doc.startsWith('') ? '' : '';const FRONT_MATTER_RE = /^?---\r?\n([\s\S]*?)\r?\n---/;
.last-scan
Gates applied: no_behavioural_pass.
b7c64ad6eb8ffull audit observations/trust-audit/mcp-server/zhitongblog__solomd.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 |
|---|---|---|---|---|---|
| 2026-09-28 | b7c64ad6eb8f | BLOCK | F | 30 | first audit |
Questions
What is the SoloMD MCP server?
A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
Is SoloMD safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (30/100) and found 7 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does SoloMD need?
It reads ASC_KEY_ID, ASC_KEY_PATH and KEY 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 SoloMD run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as solomd-web at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (b7c64ad6eb8f), read on 2026-09-28. The repository is watched and re-audited when it changes.