Skills/PyPI/meta-ads-mcp-server

meta-ads-mcp-server@0.1.0

VERIFIED· not started

Publisher claims: "Model Context Protocol server exposing the Meta Ads Graph API — 300+ tools for Facebook & Instagram Ads." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher mattyu-dev · publishing for 271 daysInstalls 52Last detonated 3d ago
$claude mcp add meta-ads-mcp-server -- uvx meta-ads-mcp-server
WatchReport an issue

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
AUTH_BROKER_API_KEYAUTH_BROKER_TIMEOUT_SECONDSAUTH_BROKER_URLMETA_ACCESS_TOKENMETA_APP_SECRETMETA_OAUTH_HOSTMETA_OAUTH_SCOPESMETA_TOKEN_CACHE_PATHConfiguration, not credentials: META_API_TIMEOUT_SECONDS, META_API_VERSION, META_APP_ID, META_GRAPH_BASE_URL, META_LOGIN_TIMEOUT_SECONDS, META_MAX_CONCURRENCY, OTEL_EXPORTER_OTLP_ENDPOINT, OTEL_EXPORTER_OTLP_INSECURE
Where it talks to
no vendor host named in the codeAlso facebook.com, google.com, apple.com, wa.me — 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 facebook.com, google.com, apple.com, wa.me as well as its own vendor. The guard injects AUTH_BROKER_API_KEY, AUTH_BROKER_TIMEOUT_SECONDS, AUTH_BROKER_URL, META_ACCESS_TOKEN, META_APP_SECRET, META_OAUTH_HOST, META_OAUTH_SCOPES, META_TOKEN_CACHE_PATH only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx meta-ads-mcp-server

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 2026-11-11 and scored it 82/100 (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 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 pathssrc/config.py:79 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=".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 pathssrc/config.py:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesAll configuration is loaded from environment variables with optional .env file support.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/catalog_mastery.py:219 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"auto_update_enabled": arguments.get("auto_update", False),Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandsrc/tools/scale.py:158 · Process kill command — agent can terminate processesdescription="Emergency stop to immediately pause all active campaigns. Instant kill switch for runaway spend or crisis situations. Use for emergency cost control.",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/catalog_mastery.py:157 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"auto_update": true,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈66 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-server@0.1.0 as of 3d ago. This is the package itself, not its dependencies.