Skills/npm/makehybrid-mcp

makehybrid-mcp@1.0.0

VERIFIED

Publisher claims: "LinkedIn, the messaging channels and the work trackers of a MakeHybrid account, as tools." Observed in sandbox: calls makehybrid.com only, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher makehybrid · publishing for 17 daysInstalls 0Last detonated 3d ago
$claude mcp add makehybrid-mcp -- npx -y makehybrid-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
makehybrid.com (its own)
What the honeypot saw
no credential files read · reached only makehybrid.com (its own)
What we could not test
what the tools do when called with real credentials

Reasonable to connect. No credential asked for, no third-party host named, Server started and answered tools/list.

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 86/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: calls makehybrid.com only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 25 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.9sprocessdependency install exit 0
25snetworkCONNECT tcp://makehybrid.com:443
25sclaimed28 tools: makehybrid_list_operations, makehybrid_describe_operation, makehybrid_call, makehybrid_status, complete_connect_credentials, complete_connect_cookie, complete_connect_accounts, complete_linkedin_search_people, complete_linkedin_search_posts, complete_users, complete_chats, complete_chats_messages_send, complete_posts, complete_webhooks_inbox, complete_connect_link, complete_inbox_v1_inboxes, complete_inbox_v1_conversations, complete_inbox_v1_conversations_messages, complete_x_v1_messages, complete_rooms, complete_rooms_2, complete_rooms_tasks, complete_rooms_tasks_2, complete_rooms_messages, complete_rooms_messages_2
25sprocessscript backend runs setup only
25sprocessno install scripts to re-run

Static findings

HIGH
URL with embedded credentialsdist/http.js:183 · URL with embedded credentials — may be phishing or credential leaking* A URI with credentials in its authority -- `https://user:secret@host/...`.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Tool description instructs the agent: credential exfiltration instructionmcp:tools/complete_connect_credentials:1 · Instruction aimed at the agent: credential exfiltration instructionect/checkpoint. -- MakeHybrid API plan, POST /linkedin/connect/credentials, group connect. {"type":"object","properties":{"query":{"tyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST01

Cost to the agent

Instructions loaded
≈66 tok
1 file · 11 in bundle
Tool list per prompt
≈5,781 tok
28 tools · 206 per tool
Handshake
912 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 285

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 makehybrid-mcp@1.0.0 as of 3d ago. This is the package itself, not its dependencies.