sast-mcp-server@0.8.3
VERIFIED· not startedPublisher claims: "A standard MCP server for SAST/DAST tools (Bandit, njsscan, Bearer, Semgrep, Trivy, CodeQL, Checkov, Gitleaks, OSV-Scanner, Grype, OWASP ZAP) — scan code for security vulnerabilities from any AI agent" 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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso cyclonedx.org, oasis-open.org, githubusercontent.com, bearer.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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
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 2026-11-16 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 · 0 s · 2 scenarios · 0 deviationsStatic findings
return subprocess.call(cmd, shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.context="subprocess.call(cmd, shell=True)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."sast_mcp_server.integrations._http.httpx.AsyncClient", factoryFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."sast_mcp_server.integrations._http.httpx.AsyncClient", factoryFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.Each scanner lives in `sast_mcp_server/scanners/<name>.py` and subclasses `BaseScanner`Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.assert args[0] == "https://hooks.slack.com/x"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."sast_mcp_server.integrations._http.httpx.AsyncClient", factoryFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.monkeypatch.setenv("SLACK_WEBHOOK_URL", "https://hooks.slack.com/x")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."sast_mcp_server.integrations._http.httpx.AsyncClient", factoryFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.RUN curl -sfL https://raw.githubusercontent.com/Bearer/bearer/main/contrib/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.RUN curl -sfL https://raw.githubusercontent.com/Bearer/bearer/main/contrib/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.mock_proc.kill = MagicMock()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.context="subprocess.call(x, shell=True)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.RUN curl -sfL https://raw.githubusercontent.com/Bearer/bearer/main/contrib/install.sh | shFix: Pin versions and sources; vendor anything fetched at install time.# SAST_MCP_JWT_SECRET (or SAST_MCP_API_KEY) in a .env file next to this file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from sast_mcp_server.integrations._http import post_with_retryFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.sast-mcp-server --transport streamable-http --host 0.0.0.0 --port 8080Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.mock_proc.kill = MagicMock()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc.kill = MagicMock()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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 sast-mcp-server@0.8.3 as of 34 min ago. This is the package itself, not its dependencies.