Skills/PyPI/rusticai-mcp

rusticai-mcp@2.1.3

VERIFIED· install only

Publisher claims: "support for mcps" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher dragonscale-ai · publishing for 66 daysInstalls 108Last detonated 42 min ago
$claude mcp add rusticai-mcp -- uvx rusticai-mcp
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
MCP_TOKEN
Where it talks to
no vendor host named in the codeAlso airtable.com, alltrails.com, atlassian.com, atlassian.net, bitly.com, blockscout.com, datacommons.org, exa.ai, fiscal.ai, githubcopilot.com, godaddy.com, goo.gl, google.com, unicode.org, huggingface.co, linear.app, lunarcrush.ai, monday.com, wkf.ms, peek.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
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names airtable.com, alltrails.com, atlassian.com, atlassian.net, bitly.com, blockscout.com, datacommons.org, exa.ai, fiscal.ai, githubcopilot.com, godaddy.com, goo.gl, google.com, unicode.org, huggingface.co, linear.app, lunarcrush.ai, monday.com, wkf.ms, peek.com as well as its own vendor. The guard injects MCP_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx rusticai-mcp

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-16 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionsrc/rustic_ai/mcp/connectors/fiscal.py:19 · File type combined with upload action — agent may exfiltrate local data files…{ ... }`\nAPI functions are available as `codemode.<name>({...})`.\nUse `console.log()` to return data \u2014 this is the only output channel.\nChain multiple calls in one invocation for efficiency.\n\ndeclare const codemode: {\n /** Get a…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Destructive file system command detectedsrc/rustic_ai/mcp/connectors/monday.py:319 · Destructive file system command detected…nWhen viewing the section \"Completed by Assignee\", you'll see user IDs in the format \"@user-12345678\". the 8 digits after the @is the user ID. To retrieve the actua…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈40 tok
1 file · 31 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.