Skills/npm/tm-mcp

tm-mcp@0.4.0

VERIFIED

Publisher claims: "Read your Pyunto Time Management schedule and log time from an AI assistant. E2EE project planning." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher pyunto · publishing for 74 daysInstalls 0Last detonated 19 h ago
$claude mcp add tm-mcp -- npx -y @pyunto/tm-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
PYUNTO_TM_API_KEYPYUNTO_TM_PASSWORDPYUNTO_TM_PASSWORD_FILEConfiguration, not credentials: MISSING_KEY_HELP, PYUNTO_TM_BASE_URL
Where it talks to
pyunto.com (its own)
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for PYUNTO_TM_API_KEY, PYUNTO_TM_PASSWORD, PYUNTO_TM_PASSWORD_FILE and talks to pyunto.com. 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 PYUNTO_TM_API_KEY=pyunto.com,PYUNTO_TM_PASSWORD=pyunto.com,PYUNTO_TM_PASSWORD_FILE=pyunto.com -- npx -y @pyunto/tm-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 (2 scenarios) on 2026-11-13 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: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 27 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
7.1sprocessdependency install exit 0
27sclaimed14 tools: whoami, list_projects, list_tasks, list_time_blocks, time_summary, log_time, update_time_block, delete_time_block, list_deleted_time_blocks, restore_time_block, create_task, complete_task, update_task, set_monthly_target
27stoolsd84d89c7db945997
27stools36f940d422f8740b
27stools2829f74dee364c9a
27stools1839f572c3a333d2
27stoolsf9fc7e9b7300187e
27stoolscda598357cafe3c0
27stoolsd39adc4a436e6f00
27stoolsfcaf4f28df8bbb2c
27stoolsf60ae0605212bee8
27stools49db07940a09b8ab
27stoolsee4f7f59d7999918
27stools02925ff9e7a4b49a
27stoolsa55f87c9c405be59
27stoolsf9fac5adf7560b43
27sprocessscript backend runs setup only
27sprocessno install scripts to re-run

Static findings

HIGH
Tool description instructs the agent: "do not tell the user"mcp:tools/delete_time_block:1 · Instruction aimed at the agent: "do not tell the user"ay so when you report the deletion, and do not tell the user the deletion is irreversible. Requires the blocks:delete scFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 1,137 lines in 8 files.

Cost to the agent

Instructions loaded
≈66 tok
1 file · 8 in bundle
Tool list per prompt
≈2,383 tok
14 tools · 170 per tool
Handshake
686 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 330

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 @pyunto/tm-mcp@0.4.0 as of 19 h ago. This is the package itself, not its dependencies.