scout-mcp-server@1.8.1
CAUTION· not startedPublisher claims: "MCP server for browser automation with anti-detection. Scout pages, find elements, interact with websites, and monitor network traffic." 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: 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
ANTHROPIC_API_KEYOPENAI_API_KEYConfiguration, not credentials: SCOUT_ALLOW_LOCALHOST, SCOUT_BROWSE_MAX_LENGTH, SCOUT_BROWSE_MODEL, SCOUT_BROWSE_TIMEOUT, SCOUT_CHROME_NM_PATH, SCOUT_ENV_FILE, SCOUT_EXTENSION_ID, SCOUT_PROFILE_DIR- Where it talks to
- no vendor host named in the codeAlso astral.sh, pypa.io, linkedin.com, twilio.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 with a scoped credential, under the guard, and read the third-party hosts first. The code names astral.sh, pypa.io, linkedin.com, twilio.com as well as its own vendor. The guard injects ANTHROPIC_API_KEY, OPENAI_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; not started: dependency install failed; the server itself was not observed) on 2026-11-17 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Privileged sudo command; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
…lidation happens. **Secret isolation** — `fill_secret` reads credentials from `.env` server-side and types them via the driver. The MCP response only reports chara…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.User-level only (no root/sudo required).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Search order for the .env file:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- `SCOUT_ENV_FILE` — Explicit path to `.env` file for secretsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_var: str = Field(description="Name of the .env variable used")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.3. ``.env`` in the current working directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Raised when the .env file cannot be located or loaded."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Load credentials from .env files for fill_secret.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Lazy-load .env file on first use.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Scrub values matching .env keys (case-insensitive key match in body)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_keys: Set of .env key names (case-insensitive match against body field names).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Determine which .env file to load using the three-level search order."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log("[Scout] WebSocket connected, sending auth");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.The cache is permanent for the server's lifetime. Changes to .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# The thread may continue running — asyncio cannot kill threads.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.self.send_header("Location", "http://169.254.169.254/latest/meta-data/")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.The server reads the value from the .env file and types it directly into theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Type a secret value from .env into a form field without exposing it in the conversation.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.… `pipx`. It has zero Python logic — it's purely a distribution convenience for `npx -y scout-mcp-server`. ## Environment Variables - `SCOUT_ALLOW_LOCALHOST` — Enabl…Fix: Pin versions and sources; vendor anything fetched at install time.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.env_var: Name of the environment variable in .env (e.g., 'APP_PASSWORD').Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proxy: Optional proxy URL (e.g., 'http://user:pass@host:port').Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.1. Open `chrome://extensions`, enable Developer mode, click "Load unpacked", select the `extension/` directory from the Scout repoFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.result = await browse("http://192.0.2.1/")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.result = await browse("http://192.0.2.1/")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.2. Enable **Developer mode** (top-right toggle)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.behavior — e.g., "ignore previous instructions", "navigate to evil.com",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.2. Enable **Developer mode** (top-right toggle)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.result = await browse("http://169.254.169.254/latest/meta-data/")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.npx remotion render src/index.ts ScoutDemo \Fix: Pin versions and sources; vendor anything fetched at install time.1. Open `chrome://extensions`, enable Developer mode, click "Load unpacked", select the `extension/` directory from the Scout repoFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.1. Open `chrome://extensions`, enable Developer mode, click "Load unpacked", select the `extension/` directory from the Scout repoFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.request = httpx.Request("GET", "http://169.254.169.254/latest/meta-data/")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 scout-mcp-server@1.8.1 as of 21 min ago. This is the package itself, not its dependencies.
What would make this Verified
9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim stemado: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- 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.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.