developer-toolsproductivity

Adspirer

amekala

by amekala

Adspirer — streamline campaign planning, research, and cross-platform ad creation with powerful tools and Google Ads Key

Campaign planning, research, and cross-platform ad creation

github stars

15

0 commentsdiscussion

Both formats append explainx.ai attribution and the canonical URL for this MCP server listing.

100+ tools across 4 ad platformsStrategy persistence across sessionsOAuth 2.1 authentication

best for

  • / Digital marketers managing multi-platform campaigns
  • / Agencies running ads for multiple clients
  • / Businesses automating ad creation and optimization

capabilities

  • / Create Google Ads Search and Performance Max campaigns
  • / Research keywords with real CPC data
  • / Launch Meta, TikTok, and LinkedIn ad campaigns
  • / Analyze campaign performance across platforms
  • / Generate ad copy and creative assets
  • / Manage multiple ad accounts from one interface

what it does

Connects AI assistants to Google Ads, Meta Ads, TikTok Ads, and LinkedIn Ads for campaign creation, keyword research, and performance analysis across platforms.

about

Adspirer is an official MCP server published by amekala that provides AI assistants with tools and capabilities via the Model Context Protocol. Adspirer — streamline campaign planning, research, and cross-platform ad creation with powerful tools and Google Ads Key It is categorized under developer tools, productivity.

how to install

You can install Adspirer in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server supports remote connections over HTTP, so no local installation is required.

license

MIT

Adspirer is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

readme

Ads MCP

Remote Model Context Protocol (MCP) server for cross-platform ad management. Create, analyze, and optimize campaigns across Google Ads, Meta Ads, TikTok Ads, and LinkedIn Ads from any MCP-compatible AI assistant.

Quick Links

What It Does

  • Strategy-aware execution — strategic decisions persist to STRATEGY.md and guide all future campaign creation, keyword research, and ad copy across sessions and subagents
  • 100+ tools across 4 ad platforms for campaign creation, performance analysis, and optimization
  • Plan and validate campaigns using structured prompts
  • Research keywords with real CPC data and competitive analysis
  • Create Google Ads Search and Performance Max campaigns end-to-end
  • Launch Meta, TikTok, and LinkedIn ad campaigns
  • Analyze performance with actionable optimization recommendations
  • Manage multiple ad accounts across platforms

Platforms & Tools

PlatformToolsCapabilities
Google Ads39Search campaigns, Performance Max, keyword research, performance analysis, asset management, ad extensions
LinkedIn Ads28Sponsored content, lead gen forms, audience targeting, campaign analytics
Meta Ads20Image campaigns, carousel campaigns, audience targeting, performance tracking
TikTok Ads4In-feed video/image campaigns, asset validation
Total100+Plus 2 resources and 6 prompts

How to Connect

See CONNECTING.md for detailed setup instructions for each platform.

Claude (Recommended)

  1. Open Settings > Connectors > Add custom connector
  2. Name: Ads MCP
  3. URL: https://mcp.adspirer.com/mcp
  4. Complete OAuth 2.1 sign-in
  5. Link your ad accounts on first use

Claude Code

Install the full Adspirer plugin (agent + skills + commands + MCP server):

  1. Open Claude Code
  2. Run /plugin marketplace add amekala/ads-mcp
  3. Run /plugin install adspirer
  4. Run /mcp — find plugin:adspirer:adspirer and click to authenticate
  5. Run /adspirer:setup to pull your campaign data and create your brand workspace

This gives you a brand-aware performance marketing agent with persistent memory, competitive research via web search, campaign creation with ad extensions, and slash commands for common workflows. Enabling subagent usage does not change this installation flow.

MCP-only (no plugin): If you just want the raw MCP tools without the agent:

claude mcp add --transport http adspirer https://mcp.adspirer.com/mcp

ChatGPT

  1. Open Settings > Connectors > Add custom connector
  2. Name: Ads MCP
  3. URL: https://mcp.adspirer.com/mcp
  4. Follow OAuth 2.1 sign-in flow

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "adspirer": {
      "url": "https://mcp.adspirer.com/mcp"
    }
  }
}

OpenAI Codex

Add to ~/.codex/config.toml:

[mcp_servers.adspirer]
url = "https://mcp.adspirer.com/mcp"

OpenClaw

openclaw plugins install openclaw-adspirer
openclaw adspirer login
openclaw adspirer connect

Or install from ClawHub.

Example Prompts

Keyword Research:

Research keywords for my emergency plumbing business in Chicago.
Show me high-intent keywords with real CPC data and budget recommendations.

Performance Analysis:

Show me campaign performance for the last 30 days across all platforms.
Which campaigns are converting best and what should I optimize?

Campaign Creation:

Create a Google Performance Max campaign for luxury watches targeting
New York with a $50/day budget.

Multi-Platform Strategy:

I want to advertise my handmade jewelry business across Google and LinkedIn.
Research keywords for Google Ads and create a LinkedIn sponsored content campaign
targeting small business owners.

Technical Details

  • Protocol: MCP 2025-03-26 (with fallback to 2024-11-05)
  • Transport: Streamable HTTP
  • OAuth: RFC 8252 (Authorization Code + PKCE) with RFC 7591 (Dynamic Client Registration) and RFC 9728 (Protected Resource Metadata)
  • Tool Annotations: All tools include MCP safety metadata (readOnlyHint, destructiveHint)

Security

  • HTTPS/TLS for all data transmission
  • OAuth 2.1 with PKCE for authentication
  • Dynamic client registration for CLI tools (Claude Code, Cursor, Codex)
  • Encrypted token storage
  • No conversation logging -- only tool requests are processed

See SECURITY.md for vulnerability reporting.

Documentation

Support

Supported Plugins

This repo distributes plugins for 4 AI platforms from a single monorepo:

PlatformDirectorySkillsInstall Method
Claude CodeRepo root1 generated + 5 slash commands/plugin marketplace add
Cursorplugins/cursor/adspirer/5 generated from templatesinstall.sh (one-command)
Codexplugins/codex/adspirer/5 generated from templatesinstall.sh (one-command)
OpenClawplugins/openclaw/1 standalone (self-contained)openclaw plugins install

Skills for Claude Code, Cursor, and Codex are authored once in shared/skills/ as templates, then compiled into IDE-specific versions by scripts/sync-skills.sh. The performance marketing agent prompt is also authored once in shared/agents/performance-marketing-agent/PROMPT.md and compiled into Claude Code, Cursor, and Codex agent files by the same sync script. OpenClaw uses its own standalone skill. See Architecture for the full design.

Shared Update Wireframe

Edit once (source of truth)
  ├─ shared/skills/adspirer-*/SKILL.md
  └─ shared/agents/performance-marketing-agent/PROMPT.md
                |
                v
        ./scripts/sync-skills.sh
                |
                +--> Claude Code outputs
                |     ├─ skills/ad-campaign-management/SKILL.md
                |     └─ agents/performance-marketing-agent.md
                |
                +--> Cursor outputs
                |     ├─ plugins/cursor/adspirer/.cursor/skills/adspirer-*/SKILL.md
                |     └─ plugins/cursor/adspirer/.cursor/agents/performance-marketing-agent.md
                |
                +--> Codex outputs
                |     ├─ plugins/codex/adspirer/skills/adspirer-*/SKILL.md
                |     └─ plugins/codex/adspirer/agents/performance-marketing-agent.toml
                |
                └--> OpenClaw (standalone, not generated)
                      └─ plugins/openclaw/SKILL.md

Client Roots and Install Targets

AI ClientRepo Source RootGenerated/Runtime Root in RepoUser Installation Path/Method
Claude CodeRepo root + shared/skills/ + shared/agents/skills/, agents/, commands/, .claude-plugin//plugin marketplace add amekala/ads-mcp then /plugin install adspirer
Cursorplugins/cursor/adspirer/ + shared sourcesplugins/cursor/adspirer/.cursor/skills/, plugins/cursor/adspirer/.cursor/agents/bash <(curl -fsSL https://raw.githubusercontent.com/amekala/ads-mcp/main/plugins/cursor/adspirer/install.sh)
Codexplugins/codex/adspirer/ + shared sourcesplugins/codex/adspirer/skills/, plugins/codex/adspirer/agents/bash <(curl -fsSL https://raw.githubusercontent.com/amekala/ads-mcp/main/plugins/codex/adspirer/install.sh)
OpenClawplugins/openclaw/plugins/openclaw/ (standalone, no sync generation)openclaw plugins install openclaw-adspirer

Developer Guide

If you're contributing to this repo or adding new ad platforms/IDE support:

Quick reference

./scripts/sync-skills.sh          # Generate IDE-specific skills from templates
./scripts/sync-skills.sh --check  # Verify generated files match committed (CI mode)
./scripts/validate.sh             # Run all 48 offline validation checks
./scripts/validate.sh --live      # Also test MCP endpoint connectivity

Never edit files in plugins/*/skills/, skills/, agents/, or plugins/*/agents/ directly — they will be overwritten by the sync script. Edit templates in shared/skills/ and shared prompts in shared/agents/ instead.

License

Proprietary -- See Terms of Service for usage terms.

FAQ

What is the Adspirer MCP server?
Adspirer is a Model Context Protocol (MCP) server profile on explainx.ai. MCP lets AI hosts (e.g. Claude Desktop, Cursor) call tools and resources through a standard interface; this page summarizes categories, install hints, and community ratings.
How do MCP servers relate to agent skills?
Skills are reusable instruction packages (often SKILL.md); MCP servers expose live capabilities. Teams frequently combine both—skills for workflows, MCP for APIs and data. See explainx.ai/skills and explainx.ai/mcp-servers for parallel directories.
How are reviews shown for Adspirer?
This profile displays 46 aggregated ratings (sample rows for discoverability plus signed-in user reviews). Average score is about 4.7 out of 5—verify behavior in your own environment before production use.

Use Cases

Extended AI Capabilities

Add new capabilities to Claude beyond text generation

Example

Access external data sources, execute code, interact with tools and services

Transform Claude from chatbot to action-taking agent

Context Enhancement

Provide Claude with access to relevant context and data

Example

Load project documentation, access knowledge bases, query databases

Get more accurate, context-aware responses

Workflow Automation

Automate multi-step workflows combining AI and external tools

Example

Research → Summarize → Create document → Send notification

Complete complex tasks end-to-end without manual steps

Implementation Guide

Prerequisites

  • Claude Desktop 0.7.0+ or Cursor IDE with MCP support
  • Basic understanding of MCP architecture and capabilities
  • Access credentials for integrated services (if required)
  • Willingness to experiment and iterate on configuration

Time Estimate

15-60 minutes depending on server complexity

Installation Steps

  1. 1.Install MCP server: npm install -g [package-name] or via GitHub
  2. 2.Add server configuration to ~/.claude/mcp.json
  3. 3.Provide required credentials and configuration
  4. 4.Restart Claude Desktop to load new server
  5. 5.Test basic functionality with simple prompts
  6. 6.Explore capabilities and experiment with use cases
  7. 7.Document successful patterns for reuse

Troubleshooting

  • MCP server not loading: Check config syntax, verify installation
  • Connection errors: Check network, firewall, credentials
  • Feature not working: Read server docs, check required parameters
  • Performance issues: Monitor resource usage, check for network latency
  • Conflicts with other servers: Check port assignments, namespace collisions

Best Practices

✓ Do

  • +Read server documentation thoroughly before setup
  • +Start with simple use cases to validate functionality
  • +Test in non-production environment first
  • +Monitor resource usage and performance
  • +Keep servers updated for bug fixes and new features
  • +Document configuration for team members
  • +Use environment variables for sensitive configuration

✗ Don't

  • Don't grant overly permissive access to MCP servers
  • Don't skip reading security considerations in docs
  • Don't expose sensitive data without proper controls
  • Don't run untrusted MCP servers without code review
  • Don't ignore error messages—investigate root cause

💡 Pro Tips

  • Combine multiple MCP servers for powerful workflows
  • Create custom MCP servers for your specific needs
  • Share successful configurations with team
  • Use MCP inspector for debugging
  • Join MCP community for tips and troubleshooting

Technical Details

Architecture

Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.

Protocols

  • Model Context Protocol (MCP)
  • JSON-RPC 2.0
  • stdio or HTTP transport

Compatibility

  • Claude Desktop
  • Cursor IDE
  • Custom MCP clients

When to Use This

✓ Use When

Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.

✗ Avoid When

Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.

Integration

  • Tool composition: Chain multiple MCP tools in workflows
  • Context augmentation: Provide AI with relevant external data
  • Action delegation: Let AI execute tasks on external systems
  • Bidirectional sync: Keep AI context and external systems in sync

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.

List & Promote Your MCP Server

Share your MCP server with the developer community

GET_STARTED →
MCP server reviews

Ratings

4.746 reviews
  • Chaitanya Patil· Dec 28, 2024

    Adspirer is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.

  • Charlotte Tandon· Dec 28, 2024

    Adspirer has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.

  • Kabir Jain· Dec 24, 2024

    According to our notes, Adspirer benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.

  • Sofia Torres· Dec 24, 2024

    I recommend Adspirer for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.

  • Hassan Nasser· Dec 16, 2024

    Adspirer reduced integration guesswork — categories and install configs on the listing matched the upstream repo.

  • Piyush G· Nov 19, 2024

    Adspirer is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.

  • Min Martinez· Nov 15, 2024

    Adspirer reduced integration guesswork — categories and install configs on the listing matched the upstream repo.

  • Hassan Farah· Nov 15, 2024

    Useful MCP listing: Adspirer is the kind of server we cite when onboarding engineers to host + tool permissions.

  • Naina Khan· Nov 7, 2024

    I recommend Adspirer for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.

  • Aisha Brown· Oct 26, 2024

    Strong directory entry: Adspirer surfaces stars and publisher context so we could sanity-check maintenance before adopting.

showing 1-10 of 46

1 / 5