slm-mcp-hub@0.3.4
VERIFIED· not startedPublisher claims: "A local-first MCP gateway for federating stdio and HTTP servers through one endpoint." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
SLM_HUB_API_KEYConfiguration, not credentials: SLM_DAEMON_URL, SLM_HUB_AGENT_ID, SLM_HUB_CONFIG_DIR, SLM_HUB_HOST, SLM_HUB_IDLE_TTL_SECONDS, SLM_HUB_LOG_LEVEL, SLM_HUB_MAX_LIVE_BACKENDS, SLM_HUB_PORT, SLM_HUB_SDK_MODE, SLM_HUB_SESSION_RECOVERY, SLM_HUB_STARTUP_MAX_CONCURRENCY, SLM_HUB_STATELESS- Where it talks to
- no vendor host named in the codeAlso apple.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
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names apple.com as well as its own vendor. The guard injects SLM_HUB_API_KEY only into requests to the host you bind (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.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
subprocess.run(["launchctl", "unload", str(plist_path)], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Lifecycle module — runtime graph, config diffing, hot-reload, drain, notifications."""Fix: Pin versions and sources; vendor anything fetched at install time.result = subprocess.run(["launchctl", "load", "-w", str(plist_path)], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.This is the orchestrator for hot-reload. It is intentionally transport-Fix: Pin versions and sources; vendor anything fetched at install time.Future phases add hot-reload, config-diff, and notificationFix: Pin versions and sources; vendor anything fetched at install time.subprocess.run(["launchctl", "unload", str(plist_path)], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.config.json. CLI commands edit the file, then POST here.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.swallowed so one bad sweep can never kill the reaper for the life of theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.The ``url`` in MCPServerConfig must point to the SSE stream endpointFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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 slm-mcp-hub@0.3.4 as of 26 min ago. This is the package itself, not its dependencies.