mcp-server-scf@5.0.0
VERIFIEDPublisher claims: "MCP server for the SCF Controls Platform — security compliance controls, frameworks, evidence, and risk management for AI agents" 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
SCF_API_KEYConfiguration, not credentials: MCP_ALLOWED_HOSTS, MCP_ALLOWED_ORIGINS, MCP_HTTP_HOST, MCP_JSON_RESPONSE, MCP_MAX_BODY_BYTES, MCP_REQUEST_TIMEOUT_MS, SCF_API_TIMEOUT_MS, SCF_API_URL- 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
Connect it with a scoped credential, under the guard. It asks for SCF_API_KEY and talks to its vendor. 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.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 4.1.0
vet-skills diff mcp-server-scf 4.1.0 5.0.0This version reaches for something 4.1.0 did not: 6 rewritten tool descriptors (scf_catalog_read, scf_control_write, scf_load_tools, scf_risk_read, …). Compared from the two recorded runs, not from source.
- Rewritten tool descriptors
- scf_catalog_read, scf_control_write, scf_load_tools, scf_risk_read, scf_risk_write, scf_update_org_settings
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 91/100 (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 · 36 s · 2 scenarios · 0 deviationsStatic findings
"build": "tsc && chmod 755 build/index.js build/http.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.* McpServer per request, so it collects once per process and passes it in.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."mcp-server-scf-http": "./build/http.js"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.* McpServer per request, so it collects once per process and passes it in.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
No advisories in OSV for mcp-server-scf@5.0.0 as of 25 min ago. This is the package itself, not its dependencies.