mcpshield@0.3.3
VERIFIED· not startedPublisher claims: "MCPShield - Secure infrastructure access for AI agents (databases, APIs, cloud) with deterministic policy enforcement and AI-powered policy generation" 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
DATABASE_URLDSNMCPSHIELD_API_KEYPG_DSNConfiguration, not credentials: API_BASE_URL, BACKEND, BATCH_SIZE, BATCH_TIMEOUT, INFRASTRUCTURE_TYPES, LOG_DECISIONS, MCPSHIELD_BACKEND, POLICY_CACHE_DIR, POLICY_FILE, POLICY_REFRESH_SECONDS, POLICY_SOURCE, PROJECT_ID, SPOOL_DIR- Where it talks to
- mcpshield.xyz (its own)
- 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. It asks for DATABASE_URL, DSN, MCPSHIELD_API_KEY, PG_DSN and talks to mcpshield.xyz. 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. What the tools do with a real credential was not observed.
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 2026-11-11 and scored it 86/100 (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
env_file: Optional path to .env file to load firstFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_file: Optional path to .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Load .env file if providedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env*",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."*.env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.backup_path = env_path.parent / f".env.backup.{int(Path.home().stat().st_mtime)}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.print(" 4. Manual setup (just create .env file)")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Create .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_path = Path.home() / ".mcpshield" / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_path = Path.home() / ".mcpshield" / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.raise FileNotFoundError(f".env file not found: {env_path}")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Load environment variables from .env file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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 mcpshield@0.3.3 as of 3d ago. This is the package itself, not its dependencies.