Skills/npm/mcp-server

mcp-server@1.24.6

VERIFIED

Publisher claims: "Contentful MCP Server - Model Context Protocol server for Contentful" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher contentful · publishing for 477 daysInstalls 40,128Last detonated 4d ago
$claude mcp add mcp-server -- npx -y @contentful/mcp-server
WatchReport an issue

Coverage

Started with a decoy CONTENTFUL_MANAGEMENT_ACCESS_TOKEN; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in CONTENTFUL_MANAGEMENT_ACCESS_TOKEN · 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
CONTENTFUL_MANAGEMENT_ACCESS_TOKEN — 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
no credential variables read in the code; at startup it asked for CONTENTFUL_MANAGEMENT_ACCESS_TOKEN
Where it talks to
no vendor host named in the code
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

Reasonable to connect. No credential asked for, no third-party host named, Started with a decoy CONTENTFUL_MANAGEMENT_ACCESS_TOKEN; tool list observed. Tool calls with a real credential not tested.

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 2026-11-10 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 · 64 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
23sprocessdependency install exit 0
43sprocessrelaunched with a decoy CONTENTFUL_MANAGEMENT_ACCESS_TOKEN (tagged; nothing real)
63sclaimed88 tools with a decoy CONTENTFUL_MANAGEMENT_ACCESS_TOKEN: create_ai_action, invoke_ai_action, get_ai_action_invocation, delete_ai_action, get_ai_action, list_ai_actions, publish_ai_action, unpublish_ai_action, update_ai_action, upload_asset, list_assets, get_asset, update_asset, delete_asset, publish_asset, unpublish_asset, archive_asset, unarchive_asset, list_content_previews, get_entry_preview_url, get_content_type, list_content_types, create_content_type, update_content_type, delete_content_type
63sprocessscript backend runs setup only
63sprocessno install scripts to re-run

Static findings

HIGH
Tool description instructs the agent: section addressed to the agentmcp:tools/update_ai_action:2 · Instruction aimed at the agent: section addressed to the agentnalProperties":false,"description":"The instruction for the AI action"},"configuration":{"type":"object","properties":{"moFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Tool description instructs the agent: section addressed to the agentmcp:tools/create_ai_action:2 · Instruction aimed at the agent: section addressed to the agentnalProperties":false,"description":"The instruction for the AI action"},"configuration":{"type":"object","properties":{"moFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈55 tok
1 file · 7 in bundle
Tool list per prompt
≈36,634 tok
88 tools · 416 per tool
Handshake
3036 ms
launch to tools/list, stdio
Undocumented tools
3
description under 20 chars · avg 239

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 @contentful/mcp-server@1.24.6 as of 4d ago. This is the package itself, not its dependencies.