keboola-mcp-server@1.117.1
CAUTION· install onlyPublisher claims: "MCP server for interacting with Keboola Connection" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Caution 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
KBC_KUBERNETES_TOKEN_PATHKEBOOLA_MCP_SERVER_OAUTH_LOG_ALLor--storage-token/--show-tokenConfiguration, not credentials: APP_ENV, APP_VERSION, HOSTNAME_SUFFIX, KBC_PKCE_CLIENT_ID, KBC_STORAGE_API_URL, LOG_CONFIG- Where it talks to
- keboola.com (its own)Also gofastmcp.com, claude.ai, chatgpt.com, cursor.com, evil.example — 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
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names gofastmcp.com, claude.ai, chatgpt.com, cursor.com, evil.example as well as its own vendor. The guard injects KBC_KUBERNETES_TOKEN_PATH, KEBOOLA_MCP_SERVER_OAUTH_LOG_ALL only into requests to keboola.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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; URL with embedded credentials; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
"""Leases a PAT: introspect (or use the caller's explicit ``project_ids``) → sudo (MFA) →Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.'`https://kai:<secret>@<host>/<path>.git`). Only populated on the **draft create path** — the 'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.help='Recovery MFA code for the sudo elevation (--pat); alternative to --totp. Single-use and 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.(sudo with the MFA code → create PAT) and prints it.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.'`https://kai:<secret>@<host>/<path>.git`). Pass directly to `git clone`.'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Returns a ready-to-use `git_clone_url` of the form `https://kai:<secret>@<host>/<path>.git`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.help='TOTP MFA code for the sudo elevation (--pat). Visible in shell history/`ps` for the 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.def create_anonymous_app(mcp_server: FastMCP, *, config: Config, stateless_http: bool) -> StarletteWithLifespan | None:Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.from keboola_mcp_server.mcp import get_http_request_or_none, is_read_only_tool, is_strict_workspace_scopeFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.# Best-effort: a failed progress notification must not kill the running query.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.from keboola_mcp_server.session_store.repository import PostgresSessionStoreFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.from keboola_mcp_server.mcp import CONVERSATION_ID, AggregateError, ServerState, get_http_request_or_noneFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.http_app: StarletteWithLifespan = mcp_server.http_app(Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.anonymous_app=create_anonymous_app(mcp_server, config=config, stateless_http=stateless_http),Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.mcp_server, app = create_http_app(config, stateless_http=parsed_args.stateless_http)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.self._own_resources = [urljoin(mcp_server_url, own_path + path) for path in ('', _MCP_PATH, '/sse')]Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.from keboola_mcp_server.mcp import get_http_request_or_noneFix: 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. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for keboola-mcp-server@1.117.1 as of 4d ago. This is the package itself, not its dependencies.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim keboola-devel: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.