Skills/PyPI/meta-ads-mcp

meta-ads-mcp@1.0.128

CAUTION· not started

Publisher claims: "Model Context Protocol (MCP) server for Meta Ads - Use Remote MCP at pipeboard.co for easiest setup" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pipeboard-co · publishing for 582 daysInstalls 8,736Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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
META_ACCESS_TOKENMETA_APP_SECRETPIPEBOARD_API_TOKENConfiguration, not credentials: META_ADS_DISABLE_ADS_LIBRARY, META_ADS_DISABLE_CALLBACK_SERVER, META_ADS_DISABLE_LOGIN_LINK, META_ADS_ENABLE_DUPLICATION, META_ADS_ENABLE_REPORTS, META_ADS_ENABLE_SAVE_AD_IMAGE_LOCALLY, META_ADS_IMAGE_OUTPUT_DIR, META_ADS_LOG_LEVEL, META_APP_ID, META_MCP_DISABLE_DELIVERY_FALLBACK, PIPEBOARD_API_BASE_URL
Where it talks to
no vendor host named in the codeAlso pipeboard.co, facebook.com, fb.me, apple.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 pipeboard.co, facebook.com, fb.me, apple.com as well as its own vendor. The guard injects META_ACCESS_TOKEN, META_APP_SECRET, PIPEBOARD_API_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx meta-ads-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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-11 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: URL to the cloud instance metadata address. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'
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
0.2sprocesssecond launch, clock +45 days, CI unset
0.2sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'

Static findings

MEDIUM
Access to sensitive file pathstests/test_targeting_search_e2e.py:28 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprint("✅ Loaded environment variables from .env file")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandtests/README.md:109 · Process kill command — agent can terminate processeskill $SERVER_PIDFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandmeta_ads_mcp/core/utils.py:62 · File permission modification command — agent changes file ownership/permissionsPOSIX only: on Windows chmod cannot express "owner only", and access isFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/test_budget_update_e2e.py:23 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)meta_ads_mcp/core/server.py:347 · MCP server using network transport (SSE/HTTP) — data sent over networklogger.info(f" - Streamable HTTP Path: {mcp_server.settings.streamable_http_path}")Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)meta_ads_mcp/core/server.py:307 · MCP server using network transport (SSE/HTTP) — data sent over networkmcp_server.settings.stateless_http = TrueFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)meta_ads_mcp/core/server.py:353 · MCP server using network transport (SSE/HTTP) — data sent over networkprint(f" URL: http://{args.host}:{args.port}{mcp_server.settings.streamable_http_path}")Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
URL to a private-network addresstests/test_ssrf_url_validation.py:42 · URL to a private-network address — a LAN or development target"http://10.255.255.255/", # RFC 1918Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Access to sensitive file pathstests/test_targeting_search_e2e.py:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
URL to a private-network addresstests/test_ssrf_url_validation.py:43 · URL to a private-network address — a LAN or development target"http://192.168.1.1/admin", # RFC 1918Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL to the cloud instance metadata addresstests/test_ssrf_url_validation.py:40 · URL to the cloud instance metadata address — reads the VM's credentials"http://169.254.169.254/latest/meta-data/", # cloud metadata (link-local)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Access to sensitive file pathstests/test_budget_update_e2e.py:27 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprint("✅ Loaded environment variables from .env file")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive file system command detectedDockerfile:6 · Destructive file system command detectedrm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)meta_ads_mcp/core/server.py:345 · MCP server using network transport (SSE/HTTP) — data sent over networklogger.info(f" - Stateless HTTP: {mcp_server.settings.stateless_http}")Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
CRITICAL
URL to the cloud instance metadata addressmeta_ads_mcp/core/utils.py:223 · URL to the cloud instance metadata address — reads the VM's credentials# or the cloud metadata endpoint (http://169.254.169.254/) and use the serverFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Access to sensitive file pathstests/test_ssrf_url_validation.py:75 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"file:///etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)meta_ads_mcp/core/server.py:308 · MCP server using network transport (SSE/HTTP) — data sent over networkmcp_server.settings.json_response = not args.sse_responseFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
URL to a private-network addresstests/test_ssrf_url_validation.py:41 · URL to a private-network address — a LAN or development target"http://10.0.0.1/internal", # RFC 1918Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addresstests/test_ssrf_url_validation.py:44 · URL to a private-network address — a LAN or development target"http://172.16.0.1/", # RFC 1918Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈62 tok
1 file · 81 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 meta-ads-mcp@1.0.128 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim pipeboard-co: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. 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.
  6. URL to the cloud instance metadata address≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pipeboard-coPropose a patch to the maintainer