mcp@4.7.2
VERIFIEDPublisher claims: "Model Context Protocol (MCP) native server for AI-SDLC tools, resources, and governance" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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 we saw when it ran
- 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 4.6.0
vet-skills diff mcp 4.6.0 4.7.2In the sandbox, this version reached for nothing 4.6.0 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 2026-11-21 and scored it 83/100 (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 · 32 s · 2 scenarios · 0 deviationsStatic findings
tes progressive friction rules and anti-bypass guardrails. {"type":"object","properties":{"change":{"type":"string"},Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…cpServer(options?: CreateMcpServerOptions): Promise<void>; export { type CreateMcpServerOptions, MUTATION_TOOLS, type McpAuditLogEntry, type McpRole, READONLY_ROLES, REVIEWER_ONLY_TOOLS, type RegisterResourcesOptions, type RegisterToolsOpt…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.…(string)* | | `verify_friction` | Evaluates progressive friction rules and anti-bypass guardrails (prevents patch-profile changes from modifying protected paths). | `change` *(…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
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
Not checked against OSV yet; the weekly check has not reached this version.