Skills/npm/terms-mcp

terms-mcp@0.4.1

VERIFIED

Publisher claims: "The buyer gate's operations as MCP tools, with a skill for the agent that uses them." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher integraledger · publishing for 53 daysInstalls 414Last detonated 2 h ago
$claude mcp add terms-mcp -- npx -y @integraledger/terms-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
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 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.

What changed since 0.4.0

vet-skills diff terms-mcp 0.4.0 0.4.1

In the sandbox, this version reached for nothing 0.4.0 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-18 and scored it 92/100 (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 · 26 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
5.8sprocessdependency install exit 0
26sclaimed5 tools: atr_confirm, atr_finish, atr_check, atr_channel_open, atr_channel_record_charge
26stoolsb9621333196696ce
26stools63005873ad0b5ee7
26stoolse8a9d24fc7668d9d
26stools5c776ca0a724a724
26stools63dc620b8f552272
26sprocessscript backend runs setup only
26sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionskills/confirming-the-atr-hash-before-paying/SKILL.md:89 · File type combined with upload action — agent may exfiltrate local data files12. A discovery listing (`/.well-known/legal-context.json`), or a hash you compute yourself, is not a confirmation. TheFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

No other findings across 1,471 lines in 14 files.

Cost to the agent

Instructions loaded
≈2,340 tok
1 file · 14 in bundle
Tool list per prompt
≈3,079 tok
5 tools · 616 per tool
Handshake
662 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 439

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 @integraledger/terms-mcp@0.4.1 as of 1 h ago. This is the package itself, not its dependencies.