AdsAgent Meta MCP

Current contract version:0.7.66. The plugin slug isadsagent(marketplace keyadsagent). New Meta connections default to the v2 product profile; all three hosted endpoints negotiate modern MCP2026-07-28stateless discovery while retaining supported legacy initialize clients.

The local helperscripts/update_reminder.pycompares strict semantic versions and stores only bounded version/timestamp state in$XDG_CACHE_HOME/adsagent-ai-skills/update-reminder-v1.json(or~/.cache/...). Cache failure never blocks MCP work.

- A public Claude plugin marketplace package:behavior skillsplushosted MCP URLsvia.mcp.json.
- A behavior guide for Claude Code, Cursor, Codex, and other MCP-aware clients.
- A reliability and safety layer that tells agents when to retry, when to wait, and when to stop.
- A versioned GitHub distribution for AdsAgent user onboarding and agent behavior guidance.
- A data-minimization contract for AI agents that should not scan AdsAgent like a raw database.

- Not the Anthropic Connectors Directory MCP listing (that is registered separately on the hosted servers).
- Not a complete MCP tool reference.
- Not an SDK.
- Not a local transport relay.
- Not a disclosure of AdsAgent backend routes, schemas, database tables, or internal diagnostics.

For Claude Code plugin installs, OAuth MCP setup comes from this repo's.mcp.json. For clients without plugin support, the AdsAgent dashboard install prompt remains the manual fallback:

AdsAgent dashboard -> Settings -> MCP Access -> Copy install prompt

Use that copied prompt only when you are not installing the Claude plugin bundle. This repository teaches agent behavior after the MCP connection exists.

Agent clients load every Skill description for discovery, but should load only the selectedSKILL.mdbody. Each entrypoint is intentionally small and links to local reference files that are read only when the selected workflow needs those details.

The files underdocs/are human-facing product and operator documentation. They are not automatic agent context and are not part of Skill reference traversal. Agent behavior contracts live underskills/and are reached from the selectedSKILL.md.

Agents using AdsAgent should answer in Markdown by default:

## Answer One-sentence answer. ## Scope - Date: - Entity: - Grouping: - Attribution / channel: ## Results | Metric | Value | | --- | ---: | ## Notes - Data freshness: - Limits or missing fields: - Next safe action:

Do not dump JSON, CSV, hidden diagnostics, raw rows, or every returned field into chat. Clean the response into operator-facing tables and short bullets. If forensic raw inspection is needed, create an operator handoff instead of making raw rows the agent answer.

This repository intentionally documents outcomes and agent behavior, not the complete internal interface. Agents should:

- Read the live AdsAgent MCP guide after connecting.
- Use available tools through the authenticated MCP session.
- Avoid guessing hidden payload fields.
- Avoid probing rejected requests.
- Stop on operator-review responses and ask the AdsAgent operator to inspect internal diagnostics.
- Use the smallest safe data plan before making calls.
- Prefer grouped summaries and cleaned breakdowns over raw rows.

The external agent contract is: ask clear questions, respect limits, confirm before writes, and use dashboard-provided onboarding.

This repository contains only the client-readable behavior pack. AdsAgent server source, credentials, schemas, routing logic, and operational diagnostics are not distributed here.

Use AdsAgent to list my connected Meta products, Google Ads customers, or TikTok advertisers, then ask which scope's today data I want to inspect.

For Google Ads, inspect agent_method_profile, pick an enabled non-manager customer, and use one cached insights_query_consistent request when the profile is advertised.

For TikTok, inspect agent_method_profile and use one insights_query_consistent scopes request when advertised; otherwise use the native batch overview fallback.

Prepare a copy of this winning Meta ad into the target account, but ask me for confirmation before creating anything.

Group these distinct Meta Ads by language into the requested Campaign and AdSet layout. Prepare one grouped_plan, show every settings_source_ad_id and geography override, and wait for my approval before confirming once.

Run the local release contract and tests:

python scripts/validate_tri_channel_pack.py python -m pytest -q

Release validation is fail-closed against the three committed snapshots incontracts/manifests/. Each snapshot is copied byte-for-byte from a committed service artifact and locked to its channel, source revision, public artifact path, metadata, and SHA-256 incontracts/manifests/provenance.json. CI does not make live network requests.

python scripts/validate_public_tool_manifests.py

An operator can deterministically update all three snapshots after the service manifest changes. The command rejects uncommitted, dirty, missing, or contract-incompatible sources and never fetches from the network:

python scripts/sync_public_tool_manifests.py \ --source meta=/path/to/meta-tools.json \ --source google=/path/to/google-tools.json \ --source tiktok=/path/to/tiktok-tools.json

All three sources are mandatory. A missing referenced tool, an unproven required capability or gate, a stale provenance digest, or an absent channel fails release validation.--allow-missingexists only for explicit local diagnostics and is not used by release CI.

This repo ships as theadsagentClaude plugin(skills +.mcp.jsonMCP URLs). The GitHub repository name staysadsagent-ai-skills.

claude plugin marketplace add adsagents/adsagent-ai-skills claude plugin install adsagent@adsagent

claude plugin update --scope user adsagent@adsagent

Ifclaude plugin listshows duplicate local and user installs, keep user scope:

claude plugin uninstall --scope local adsagent@adsagent

Start a fresh Claude Code session after installing or updating.

Cloud / Cowork preinstall (settings snippet)

Connect your social media workflows directly to your AI agent to draft, schedule, publish, and analyze social content using natural language.

Connect AI assistants to SocialBu to create, schedule, publish, and analyze social media content from chat.

Connect Claude or any AI assistant to SocialPilot and let it schedule, publish, manage approvals, and monitor delivery across every account — from one conversation.

Run Facebook ad campaigns from any AI agent. Generate ads, research competitors, analyze markets, and launch Meta campaigns via API.

Apple Ads analytics, automation, and campaign management platform

Publish, schedule, and manage social media across 11 platforms with media uploads and analytics tracking.

MCP Server for LinkedIn Ads, powered by the CData JDBC Driver. Requires a separate license and configuration.

All-in-one marketing analytics MCP — Instagram, ads, web traffic, SEO and reviews for local businesses and the agencies that manage them.

Interact with Facebook and Instagram advertising data using the Meta Marketing API.