Skills/npm/mcp-server

mcp-server@0.5.6

VERIFIED

Publisher claims: "MCP server for managing Sooshie via AI agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher sooshie · publishing for 255 daysInstalls 1,410Last detonated 5d ago
$claude mcp add mcp-server -- npx -y @sooshie/mcp-server
WatchReport an issue

Coverage

Started with a decoy SOOSHIE_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in SOOSHIE_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
SOOSHIE_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
SOOSHIE_API_KEYConfiguration, not credentials: SOOSHIE_URL
Where it talks to
sooshie.app (its own)
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard. It asks for SOOSHIE_API_KEY and talks to sooshie.app. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --secrets SOOSHIE_API_KEY=sooshie.app -- npx -y @sooshie/mcp-server

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 2026-11-09 and scored it 95/100 (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 · 49 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
9.1sprocessdependency install exit 0
29sprocessrelaunched with a decoy SOOSHIE_API_KEY (tagged; nothing real)
49sclaimed63 tools with a decoy SOOSHIE_API_KEY: list_posts, get_post, create_post, update_post, schedule_post, publish_post, get_post_comments, submit_post_for_review, get_queue_slots, get_next_queue_slot, add_post_to_queue, get_post_logs, get_failed_post_count, list_accounts, check_account_health, get_workspace, get_workspace_members, generate_content, rewrite_content, get_best_times, upload_media, crop_image, delete_media, list_media_libraries, get_media_library
49sprocessscript backend runs setup only
49sprocessno install scripts to re-run

Static findings

HIGH
Tool description instructs the agent: section addressed to the agentmcp:tools/create_automation_rule:2 · Instruction aimed at the agent: section addressed to the agentprompt":{"type":"string","description":"Instructions for AI content generation (1-1000 chars)"},"content_length":{"descFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 1,478 lines in 51 files.

Cost to the agent

Instructions loaded
≈48 tok
1 file · 51 in bundle
Tool list per prompt
≈11,912 tok
63 tools · 189 per tool
Handshake
905 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 264

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

No advisories in OSV for @sooshie/mcp-server@0.5.6 as of 5d ago. This is the package itself, not its dependencies.