Skills/Glama/notion-desktop-mcp

notion-desktop-mcp@0.1.0

VERIFIED

Publisher claims: "an open-source MCP server that lets Claude Code (or Cursor, Codex, Gemini CLI) work inside the Notion Desktop app you’re already logged in to. No Company Authorise" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher felixhorobot · publishing for 3 daysInstalls 0Last detonated 3d ago
$npx skills add notion-desktop-mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso notion.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it under the guard; read the third-party hosts first. The code names notion.com as well as its own vendor. The guard pins the network to the hosts the honeypot saw.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-11 and scored it 84/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 24 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.1sprocessdependency install exit 0
24sclaimed15 tools: notion_launch, notion_status, notion_open, notion_outline, notion_read, notion_insert, notion_create_database, notion_delete_blocks, notion_list_deletions, notion_restore_blocks, notion_trash_page, notion_restore_page, notion_switch_workspace, notion_screenshot, notion_run_code
24sprocessscript backend runs setup only
24sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionskills/notion-desktop-mcp/SKILL.md:93 · File type combined with upload action — agent may exfiltrate local data files| `n.db.addRelation(target)`, `setFormula(col, expr)`, `setRollup(col, relCol, prop)` | computed properties |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageserver/start.mjs:2 · npx invocation of non-well-known package — may execute untrusted code// Entry point (also the npx bin). Plugin installs ship without node_modules, so the first run installsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Collapsed <details> block carrying instructionsREADME.md:71 · Collapsed <details> block carrying instructions<summary>Install from a clone, with desktop shortcuts (Windows)</summary> ```powershell git clone https://github.com/felixhorobot/Notion-Desktop-MCP cd Notion-DFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈7,850 tok
1 file · 24 in bundle
Tool list per prompt
≈1,590 tok
15 tools · 106 per tool
Handshake
858 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 156

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.