tools@0.10.0
VERIFIED· startup onlyPublisher claims: "Streamkap CLI & MCP server - manage CDC pipelines, sources, destinations, and transforms" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
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
KAFKA_API_KEYKAFKA_API_SECRETMCP_CATALOG_REQUIRE_AUTHMCP_METRICS_TOKENMCP_OAUTH_ALLOWED_REDIRECT_URISMCP_OAUTH_AUDIENCEMCP_OAUTH_BASE_URLMCP_OAUTH_ENABLEDMCP_OAUTH_ENCRYPTION_KEYMCP_OAUTH_JWT_SIGNING_KEYMCP_OAUTH_REDIS_URLMCP_OAUTH_SCOPESMCP_OAUTH_UPSTREAM_AUTHORIZATION_ENDPOINTMCP_OAUTH_UPSTREAM_CLIENT_IDMCP_OAUTH_UPSTREAM_CLIENT_SECRETMCP_OAUTH_UPSTREAM_TOKEN_ENDPOINTMCP_OPENAI_APPS_CHALLENGE_TOKENSENTRY_DSNSTREAMKAP_CLIENT_SECRETor--client-secretConfiguration, not credentials: DO_NOT_TRACK, KAFKA_BOOTSTRAP_SERVERS, KAFKAJS_NO_PARTITIONER_WARNING, MCP_ALLOW_TOOLS, MCP_ALLOWED_HOSTS, MCP_BLOCK_TOOLS, MCP_CATALOG, MCP_KAFKA_ALLOWED_TOPICS, MCP_KAFKA_CONSUME_RATE_LIMIT, MCP_KAFKA_PRODUCE_RATE_LIMIT, MCP_MAX_SSE_CONNECTIONS_PER_CLIENT, MCP_PORT, MCP_PUBLIC_URL, MCP_SESSION_CACHE_TTL_SECONDS, MCP_TOOL_PROFILE, MCP_TOOLSETS, MCP_TRANSPORT, OTEL_SERVICE_NAME, STREAMKAP_AGENT_ID, STREAMKAP_ALLOWED_API_HOSTS, STREAMKAP_API_URL- Where it talks to
- streamkap.com (its own)Also claude.com, evil.com, pstmn.io, claude.ai, chatgpt.com, vercel.com, cursor.com, devin.ai, docker.com, smithery.ai, antigravity.google, perplexity.ai, mistral.ai, grok.com, vscode.dev — 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
- the tool list (the server exited before answering) · 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 claude.com, evil.com, pstmn.io, claude.ai, chatgpt.com, vercel.com, cursor.com, devin.ai, docker.com, smithery.ai, antigravity.google, perplexity.ai, mistral.ai, grok.com, vscode.dev as well as its own vendor. The guard injects KAFKA_API_KEY, KAFKA_API_SECRET, MCP_CATALOG_REQUIRE_AUTH, MCP_METRICS_TOKEN, MCP_OAUTH_ALLOWED_REDIRECT_URIS, MCP_OAUTH_AUDIENCE, MCP_OAUTH_BASE_URL, MCP_OAUTH_ENABLED, MCP_OAUTH_ENCRYPTION_KEY, MCP_OAUTH_JWT_SIGNING_KEY, MCP_OAUTH_REDIS_URL, MCP_OAUTH_SCOPES, MCP_OAUTH_UPSTREAM_AUTHORIZATION_ENDPOINT, MCP_OAUTH_UPSTREAM_CLIENT_ID, MCP_OAUTH_UPSTREAM_CLIENT_SECRET, MCP_OAUTH_UPSTREAM_TOKEN_ENDPOINT, MCP_OPENAI_APPS_CHALLENGE_TOKEN, SENTRY_DSN, STREAMKAP_CLIENT_SECRET only into requests to streamkap.com (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; startup only; authenticated tool behavior not tested) on 2026-11-15 and scored it 85/100 (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 · 41 s · 2 scenarios · 0 deviationsStatic findings
**MCP:** `npx -y @streamkap/tools` (stdio) or remote HTTP at `mcp.streamkap.com/mcp`Fix: Pin versions and sources; vendor anything fetched at install time.…uild/ && cp -r dist mcpb-build/dist && npm ci --omit=dev --prefix mcpb-build && npx --yes @anthropic-ai/[email protected] validate mcpb/manifest.json && npx --yes @anthropic-ai…Fix: Pin versions and sources; vendor anything fetched at install time.* `http://localhost:[email protected]/cb`, which parses to host `evil.com` — it isFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* `https://user:pass@host/…` — RFC 3986 userinfo. Named by neither key norFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."build": "rm -rf dist && tsc && cp src/favicon.ico dist/favicon.ico && cp src/streamkap-logo.svg dist/streamkap-logo.svg && chmod +x dist/index.js dist/cli/index.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.…admin/favicon.ico && cp src/streamkap-logo.svg dist-admin/streamkap-logo.svg && chmod +x dist-admin/index.js dist-admin/cli/index.js", "check:leak": "npm run buil…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.return `Config file permissions are too open (${mode.toString(8)}). Run: chmod 600 ${getConfigPath()}`;Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.* `http://localhost:[email protected]/cb`, which parses to host `evil.com` — it isFix: 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 @streamkap/tools@0.10.0 as of 49 min ago. This is the package itself, not its dependencies.