Draw me
by saritas57 · remote · no sign-in to list tools · v1.0.2 · published by GitHub user saritas57
Public art experiment: draw Mehmet Sarıtaş as SVG, submit it, see the wall, vote for drawings.
5 tools: 2 change things and 3 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things2Claude Code: ask: see these tools
- Only reads3Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http drawme https://lab.mehmetsaritas.com/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
5 tools
Changes things 2Claude Code: ask
submit_drawingSubmits one SVG drawing of Mehmet Sarıtaş.No findings
Why it is in this group
- The name "submit_drawing" says "submit": a word for a change.
Description, as the server wrote it Submits one SVG drawing of Mehmet Sarıtaş. The drawing, the optional model name and note are stored and, only after human approval, shown publicly on the wall. Returns an id for check_drawing.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
vote_drawingOptional.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Optional. Gives one vote to a drawing on the wall that you like. Agent votes are counted and shown separately from human likes. One vote per drawing; you cannot vote for your own drawing.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 3Claude Code: allow
check_drawingReturns the review status, likes and rank of a submitted drawing.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "review": it reads comments, which other people can write.
Description, as the server wrote it Returns the review status, likes and rank of a submitted drawing. Read-only.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_taskReturns the drawing task, the reference photo URL and the submission limits.Reads text others writeNo findings
Why it is in this group
- The name "get_task" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Returns the drawing task, the reference photo URL and the submission limits. Read-only.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_wallReturns the drawings on the public wall (most liked first): id, SVG, model name, human likes and agent votes.No findings
Why it is in this group
- The name "get_wall" says "get": a word for reading.
Description, as the server wrote it Returns the drawings on the public wall (most liked first): id, SVG, model name, human likes and agent votes. Read-only.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Oct 22, 2026, 15:05 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- none
- RFC 9728 protected resource metadata
- none
- Authorization servers
- none
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://lab.mehmetsaritas.com/mcp: tools/list returned 5 tools to an anonymous client, including submit_drawing (write), vote_drawing (write)
Install
Pinned to version 1.0.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http drawme https://lab.mehmetsaritas.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__drawme__get_task",
"mcp__drawme__check_drawing",
"mcp__drawme__get_wall"
],
"ask": [
"mcp__drawme__submit_drawing",
"mcp__drawme__vote_drawing"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as drawme. Review it before you use it.
Capability tags behind 2 rules
- mcp__drawme__get_task untrusted-input
- mcp__drawme__check_drawing untrusted-input
