jev-mcp@0.14.8
VERIFIEDPublisher claims: "MCP server exposing TypeSafe Jev as purpose-built judgment tools: verify claims, screen for injection, find, rerank, classify, decide, compare passages, extract fields, review patches, and gate completion claims, each with typed probabilities." 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
AI_GATEWAY_API_KEYCLOUDFLARE_API_TOKENJEV_API_KEYJEV_CLOUDFLARE_API_TOKENJEV_MCP_AUTH_TOKENJEV_MCP_PATH_TOKENOPENROUTER_API_KEYTYPESAFE_API_KEYConfiguration, not credentials: CLOUDFLARE_ACCOUNT_ID, JEV_API_BASE_URL, JEV_CLOUDFLARE_BASE_URL, JEV_MCP_MAX_CONCURRENCY, JEV_MCP_MODEL, JEV_MCP_TRANSPORT, JEV_OPENROUTER_BASE_URL, JEV_PROVIDER- Where it talks to
- no vendor host named in the codeAlso openrouter.ai, cloudflare.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 openrouter.ai, cloudflare.com as well as its own vendor. The guard injects AI_GATEWAY_API_KEY, CLOUDFLARE_API_TOKEN, JEV_API_KEY, JEV_CLOUDFLARE_API_TOKEN, JEV_MCP_AUTH_TOKEN, JEV_MCP_PATH_TOKEN, OPENROUTER_API_KEY, TYPESAFE_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) on 2026-11-15 and scored it 87/100 (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 · 25 s · 2 scenarios · 0 deviationsStatic findings
return resolveTransport({ ...env, JEV_PROVIDER: explicit || "auto" }).name;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.command: npxFix: Pin versions and sources; vendor anything fetched at install time.export declare function serveHttp(factory: () => McpServer, env?: NodeJS.ProcessEnv): Promise<{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 @jkudish/jev-mcp@0.14.8 as of 12 min ago. This is the package itself, not its dependencies.