Skills/PyPI/scope-analytics-mcp

scope-analytics-mcp@0.2.1

CAUTION· not started

Publisher claims: "Scope MCP server — install + query tools for AI coding agents (the Scope analytics connector)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 726 daysInstalls 1,050Last detonated 52 min ago

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
SCOPE_API_KEYConfiguration, not credentials: NEXT_RUNTIME, SCOPE_API_BASE, SCOPE_DASHBOARD_URL, SCOPE_PUBLIC_KEY, SCOPE_TEAMMATE_TOOLS
Where it talks to
no vendor host named in the codeAlso scopeai.dev, scope.example, groq.com, mistral.ai — 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 scopeai.dev, scope.example, groq.com, mistral.ai as well as its own vendor. The guard injects SCOPE_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx scope-analytics-mcp

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 73/100 (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; Access to sensitive file paths; URL with embedded credentials. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsscope_mcp/config.py:42 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# only a regular file: a named pipe (some secret managers mount .env as one) would blockFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscope_mcp/agent_keys.py:312 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesAPP_ENV_FILES = (".env.local", ".env", ".env.development.local", ".env.development", ".env.production.local", ".env.production")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
URL with embedded credentialsscope_mcp/agent_tools.py:298 · URL with embedded credentials — may be phishing or credential leakinghttps://user:token@host/x?t=1 → https://host/x; [email protected]:org/repo → github.com:org/repo."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathsscope_mcp/agent_keys.py:311 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# looked for in all of them, so one kept in .env.production is seen.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscope_mcp/install.py:112 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"body": "In your host's environment settings (or a local .env for testing):",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscope_mcp/config.py:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesENV_FILES = (".env.local", ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagescope_mcp/agent_tools.py:50 · npx invocation of non-well-known package — may execute untrusted code"A link the person approves (scope_link_project, or `npx @scope-analytics/cli link`) makes this agent "Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST06
HIGH
Access to sensitive file pathsscope_mcp/server.py:7 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesa link saved in the folder's .env.local / .env, else a link the person approves (scope_link_project).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_agent_tools.py:681 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env.local").mkdir()Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_agent_tools.py:493 · Python subprocess execution detectedprocs.append(subprocess.Popen([sys.executable, "-c",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_agent_tools.py:491 · Python subprocess execution detectedprocs.append(subprocess.Popen(["node", "--input-type=module", "-e",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscope_mcp/server.py:674 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"app's server, ask the person, then call scope_save_key with the env file (for example .env; "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscope_mcp/setup.py:67 · Python subprocess execution detectedtracked = subprocess.run(["git", "ls-files", "--error-unmatch", path.name], cwd=path.parent, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_agent_tools.py:682 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env").write_text("SCOPE_API_KEY=sk_first\nSCOPE_API_KEY=sk_last\n", encoding="utf-8")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscope_mcp/setup.py:122 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfile sets, and not beside one that .env.local or .env in the same folder sets (a key in .env.localFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscope_mcp/setup.py:62 · Python subprocess execution detectedignore = subprocess.run(["git", "check-ignore", "-q", path.name], cwd=path.parent, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_agent_tools.py:682 · Hidden zero-width characters detected — may conceal content(tmp_path / ".env").write_text("SCOPE_API_KEY=sk_first\nSCOPE_API_KEY=sk_last\n", encoding="utf-8")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Hidden zero-width characters detectedscope_mcp/setup.py:98 · Hidden zero-width characters detected — may conceal contentfor line in (text or "").lstrip("").splitlines():Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedtests/test_agent_tools.py:456 · Python subprocess execution detectedprocs.append(subprocess.Popen([sys.executable, "-c",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscope_mcp/tool_meta.py:326 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"need it too. This MCP reads SCOPE_API_KEY from .env.local or .env in the folder it "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscope_mcp/server.py:761 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesSCOPE_API_KEY from .env.local or .env in the folder it starts in, so a key saved there keeps theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscope_mcp/tool_meta.py:329 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files" env_file: Path to the env file the app's server loads, e.g. /path/to/app/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscope_mcp/setup.py:131 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn {"saved": False, "message": f"{path} is a folder. Name the env file, for example {path / '.env'}."}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscope_mcp/setup.py:123 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesshadows .env, and this MCP reads them in that order — the CLI's link checks the same files). SuchFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagescope_mcp/install.py:119 · npx invocation of non-well-known package — may execute untrusted code"code": "npm run build && npx @scope-analytics/browser install --key=$SCOPE_PUBLIC_KEY",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST06
MEDIUM
Access to sensitive file pathstests/test_agent_tools.py:617 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env.production").write_text("SCOPE_API_KEY=sk_prod_app\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with embedded credentialstests/test_agent_tools.py:236 · URL with embedded credentials — may be phishing or credential leaking("remote", "get-url", "origin"): R(0, "https://wally:[email protected]/acme/app.git\n"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedtests/test_agent_tools.py:513 · Python subprocess execution detectedout = subprocess.run(["node", "--input-type=module", "-e",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscope_mcp/server.py:675 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env.local for Next.js). "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_agent_tools.py:454 · Python subprocess execution detectedprocs.append(subprocess.Popen(["node", "--input-type=module", "-e",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_agent_tools.py:481 · Python subprocess execution detecteddead = subprocess.Popen([sys.executable, "-c", "pass"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_agent_tools.py:684 · Hidden zero-width characters detected — may conceal content(tmp_path / ".env").write_text("SCOPE_API_KEY=sk_only\n", encoding="utf-8")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Stripe-like API key pattern detectedtests/test_setup_tools.py:362 · Stripe-like API key pattern detected — possible hardcoded or harvested key(app / ".env").write_bytes(b"SCOPE_API_KEY=sk_live_the_apps_own\n")Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
npx invocation of non-well-known packagetests/test_install_tools.py:41 · npx invocation of non-well-known package — may execute untrusted codeassert "npx @scope-analytics/browser install --key=$SCOPE_PUBLIC_KEY" in flatFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Dynamic module loadingtests/test_integrations_manifest.py:226 · Dynamic module loadingmod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_setup_tools.py:68 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"app's server, ask the person, then call scope_save_key with the env file (for example .env; .env.local "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Stripe-like API key pattern detectedtests/test_setup_tools.py:539 · Stripe-like API key pattern detected — possible hardcoded or harvested key(tmp_path / ".env").write_text("SCOPE_API_KEY=sk_live_the_apps_own\n")Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Access to sensitive file pathstests/test_coverage_tools.py:78 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env.local").write_text("SCOPE_API_KEY=\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Stripe-like API key pattern detectedtests/test_setup_tools.py:382 · Stripe-like API key pattern detected — possible hardcoded or harvested keyassert (app / ".env").read_bytes() == b"SCOPE_API_KEY=sk_live_the_apps_own\n"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
LOW
Dynamic module loadingtests/test_integrations_manifest.py:207 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_coverage_tools.py:77 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert ScopeConfig.from_env().api_key == "sk_local" # .env.local first, as the CLIFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Stripe-like API key pattern detectedtests/test_setup_tools.py:380 · Stripe-like API key pattern detected — possible hardcoded or harvested keyassert entry["sdk_keys"] == [agent_keys.fingerprint("sk_live_the_apps_own")] # the app's key in useFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Access to sensitive file pathstests/test_coverage_tools.py:80 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env.local").unlink()Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Dynamic module loadingtests/test_integrations_manifest.py:206 · Dynamic module loadingmod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_coverage_tools.py:74 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env").write_text("OTHER=1\nexport SCOPE_API_KEY='sk_env' # from scope link\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_setup_tools.py:123 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv = tmp_path / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Stripe-like API key pattern detectedtests/test_setup_tools.py:321 · Stripe-like API key pattern detected — possible hardcoded or harvested keyPROJECT_OF = {"sk_live_secret": "p1", "sk_live_the_apps_own": "p1", "sk_live_x": "p1", "sk_live_other": "p2"}Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
LOW
Dynamic module loadingtests/test_integrations_manifest.py:227 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_agent_tools.py:684 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env").write_text("SCOPE_API_KEY=sk_only\n", encoding="utf-8")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_coverage_tools.py:76 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env.local").write_text('SCOPE_API_KEY="sk_local"\n')Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagetests/test_agent_tools.py:209 · npx invocation of non-well-known package — may execute untrusted code"links it (npx @scope-analytics/cli link) and approves it in Scope.")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Access to sensitive file pathstests/test_setup_tools.py:107 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv = tmp_path / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_setup_tools.py:134 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv = tmp_path / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈63 tok
1 file · 38 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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 scope-analytics-mcp@0.2.1 as of 6 min ago. This is the package itself, not its dependencies.

What would make this Verified

7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim pypi: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. 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.
  4. npx invocation of non-well-known package≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Hidden zero-width characters detected≈ +2 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pypiPropose a patch to the maintainer