Blackmount Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Blackmount Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Your AI assistant is blind to your browsing life. Claude doesn't know what you researched yesterday, what tabs you have open, or what articles you bookmarked. blackmount-mcp fixes that.
Connect your local browser history, bookmarks, open tabs, and downloads directly to Claude, Cursor, or any MCP client. All data stays on your machine — nothing leaves your disk.
pip install blackmount-mcpAdd to claude_desktop_config.json:
{
"mcpServers": {
"blackmount": {
"command": "blackmount-mcp"
}
}
}Restart Claude Desktop. Done.
Once connected, try these in Claude:
| Tool | Description | Example Prompt |
|---|---|---|
search_history | Search browsing history by keyword | "Find that React article I read last week" |
list_history | Recent browsing history | "What sites did I visit today?" |
find_page | Natural language page search | "That TypeScript tutorial I read" |
search_bookmarks | Search bookmarks by title/URL | "Find my saved Python tutorials" |
list_bookmarks | Browse bookmark folders | "What's in my Work bookmarks folder?" |
get_open_tabs | List currently open tabs | "What tabs do I have open?" |
find_tab | Find a specific open tab | "Find that GitHub PR tab" |
list_downloads | Recent file downloads | "What did I download this week?" |
| Tool | Description | Example Prompt |
|---|---|---|
browsing_summary | Daily browsing summary | "Summarize my browsing today" |
daily_digest | Daily digest of local browsing | "What did I do online yesterday?" |
productivity_report | Weekly productivity summary | "How productive was I this week?" |
domain_time | Time spent per domain | "Where do I spend my time online?" |
distraction_score | Focus vs distraction ratio | "Am I getting distracted?" |
most_visited | Top domains by visits | "My most visited sites this month" |
research_topics | Clustered research topics | "What have I been researching?" |
browsing_patterns | Peak hours, trends | "When do I browse the most?" |
{
"mcpServers": {
"blackmount": {
"command": "blackmount-mcp"
}
}
}Config file locations:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.jsonOne-click install via the badge at the top of this README, or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"blackmount": {
"command": "blackmount-mcp"
}
}
}| Tool family | Browsers |
|---|---|
| History | Chrome, Firefox, Safari, Edge, Brave, Opera, Vivaldi |
| Bookmarks | Chrome, Firefox, Safari |
| Downloads | Chrome, Firefox, Safari |
| Open tabs | Chrome, Safari (macOS via AppleScript; Chrome session-file fallback elsewhere) |
git clone https://github.com/BlackMount-ai/blackmount-mcp.git
cd blackmount-mcp
pip install -e .
pytest tests/ -v
blackmount-mcpPull requests welcome. Open an issue to discuss larger changes.
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.