mcp-server@3.5.3
VERIFIEDPublisher claims: "MCP server for FireCMS Cloud — manage projects, collections, users, and AI features via the Model Context Protocol" 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
SECURE_TOKEN_URLConfiguration, not credentials: FIRECMS_API_URL- Where it talks to
- firecms.co (its own)Also google.com — not the publisher's domain; check what for before connecting.
- 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, and read the third-party hosts first. The code names google.com as well as its own vendor. The guard injects SECURE_TOKEN_URL only into requests to firecms.co (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 3.5.1
vet-skills diff mcp-server 3.5.1 3.5.3This version reaches for something 3.5.1 did not: 6 rewritten tool descriptors (delete_property, list_documents, save_property, update_default_locale, …). Compared from the two recorded runs, not from source.
- Rewritten tool descriptors
- delete_property, list_documents, save_property, update_default_locale, update_project_colors, update_project_name
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 2026-11-15 and scored it 93/100 (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 · 33 s · 2 scenarios · 0 deviationsStatic findings
export function registerCurrentUserTool(server: McpServer, session: FireCMSSession, mode: FireCMSServerMode) {Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.export declare function registerCurrentUserTool(server: McpServer, session: FireCMSSession, mode: FireCMSServerMode): void;Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.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.