Query social, search, scrape, and news APIs through a single OAuth-authenticated MCP gateway, bringing UnifAPI's public-data skills into agent workflows. Includes a pre-built skill to analyze X/Twitter KOLs for creator marketing campaigns, applying a pricing/ROI framework and generating outreach briefs.
Use when working with UnifAPI public-data APIs or the UnifAPI MCP server: connecting OAuth MCP clients, discovering operations, calling social/search/scrape/news APIs, troubleshooting UnifAPI auth, or deciding between MCP OAuth and API-key fallback. Always use before asking for UnifAPI credentials or calling UnifAPI tools.
When the user wants to find the prompts where their brand should be cited in AI answers but isn't — and who owns the answer instead — prioritized by AI search volume so content can attack the biggest gaps first. Also use on "AI answer gap," "AI content gap," "where am I missing from AI answers," "what prompts am I losing in AI," "GEO content gaps," "prompts I should own but don't," or "find my AI visibility gaps." For the full diagnostic audit, see ai-visibility-audit. For ongoing tracking, see llm-mention-tracking.
When the user wants to know whether their brand or domain is cited in AI answers — AI Overviews, ChatGPT, or AI search — for the queries that matter, and how they stack up against competitors. Also use on "AI visibility audit," "am I cited in AI answers," "do I show up in ChatGPT," "AI Overviews audit," "GEO audit," "answer engine audit," "AEO audit," "why isn't my brand in AI results," or "who gets cited instead of me." The GEO equivalent of an SEO audit. For ongoing mention tracking, see llm-mention-tracking. For prioritizing the gaps, see ai-answer-gap.
When the user has AI visibility, GEO, AI answer gap, or AI citation evidence and wants a prioritized plan to improve where the brand is cited or mentioned in AI answers. Also use on "AI visibility fixes," "AI visibility fix plan," "generative engine optimization fixes," "AI citation fixes," "answer engine optimization fixes," "fix AI answer gaps," or "how do we get cited in ChatGPT/AI Overviews." For finding gaps from scratch, run ai-visibility-audit or ai-answer-gap first.
When the user wants to track how often their brand or domain gets mentioned across ChatGPT and AI search engines over a set of prompts, and how that share of voice compares to named competitors over time. Also use on "LLM mention tracking," "track AI mentions," "share of voice in AI," "AI share of voice," "brand mentions in ChatGPT," "am I being mentioned more or less," "AI visibility trend," or "monitor AI citations over time." For a one-time audit of a prompt set, see ai-visibility-audit.
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Open-source marketing agents for Claude, ChatGPT, Codex, OpenClaw, Hermes, and any MCP client. Install one plugin and your assistant runs SEO audits, generative engine optimization (GEO) / AI-visibility checks, local SEO, KOL pricing, social listening, competitive intelligence, and industry marketing from live public data. Each agent is a folder of SKILL.md skills over UnifAPI's public-data APIs. Read-only — eyes, not hands — they research and price; they never post.
Agents · Skills · Install · Connect a client · API catalog · Docs
These skills are generated and versioned — to suggest a change, open an issue or PR (see CONTRIBUTING.md).
One install gives your agent both the marketing-agent skills and the public-data MCP server — no manual server config, no API key to paste. Sign in once with OAuth (new workspaces get free trial credits); everything is read-only.
Claude Code · Claude Desktop · OpenClaw — recommended (Claude-compatible plugin):
/plugin marketplace add unifapi-agent/agents
/plugin install unifapi@unifapi # that's plugin@marketplace
Hermes:
hermes plugins install unifapi-agent/agents
Codex — this repo ships a .codex-plugin/plugin.json (the same skills and the OAuth MCP server) for Codex's plugin system, so one install gives you both. To wire it up manually instead, add the server to ~/.codex/config.toml and run codex mcp login unifapi:
[mcp_servers.unifapi]
url = "https://mcp.unifapi.com"
ChatGPT (Developer Mode — Plus/Pro/Team/Enterprise): Settings → Connectors → Advanced → enable Developer Mode → Create, set the MCP server URL to https://mcp.unifapi.com with OAuth.
Any other agent-skills client (npx skills) — the universal fallback when you're not on a plugin host above. The skills.sh CLI installs the skills into any supported agent:
npx skills add unifapi-agent/agents
This installs the skills only; add https://mcp.unifapi.com as an MCP server in your client (OAuth) for live data.
Setting up a specific client? Step-by-step pages for every supported client live in connect/.
After installing, sign in when prompted and ask your assistant:
Audit example.com for "unified api" and "public data api": pull our live organic and
AI-answer positions, the competing pages, and a prioritized fix list — cite every finding.
Role Agents own the skills; Vertical and Platform Agents recombine them by industry and by source. Full agent → skill → API map in AGENTS.md.
npx claudepluginhub unifapi-agent/agents --plugin unifapiCommunity collection of Apify agent skills for web scraping, data extraction, and automation
AI-powered marketing intelligence for brand analysis, content strategy, and competitive research
SEO AEO Pro — Professional SEO and AI search optimization toolkit for agencies. Keyword research, technical audits, content optimization, local SEO, backlink analysis, and AEO (AI Engine Optimization). Multi-client support with structured data output.
Free SEO + AEO + GEO toolkit by Akii. All skills run on your Claude Code session model (Claude Sonnet / Opus / etc). Aligned with Google's AI Optimization Guide for Google AI Overviews + AI Mode. Audit sites, plan content, optimize pages, generate schema, cluster keywords. AI Visibility Score specifically calls the Akii backend (Llama 4 / DeepSeek as LLM judge against public footprint) + per-engine public-signal proxy — not direct queries of ChatGPT / Claude / Gemini / Perplexity / Copilot (those are an Akii platform feature). Auto-detects Ahrefs, GSC, Apify MCPs for richer data. Sends anonymized telemetry (plugin version + hashed machine UUID + OS, once per 24h) to akii.com — see PRIVACY.md, opt out via AKII_PLUGIN_DISABLE_TELEMETRY=1.
Claude SEO Skills for the SE Ranking MCP server. Turns raw API data into finished deliverables across keyword research, content briefing, page intelligence, technical and content audits, structured data, drift monitoring, SXO diagnostics, competitive analysis, paid search, AI-search optimization, sitemap analysis, subdomain mapping, content opportunity mining, strategic roadmap planning, Google APIs (GSC, PSI, CrUX, Indexing, GA4, YouTube, NLP), and SE Ranking API integration recipes (Data API + Project API).
20 SEO/GEO skills and 5 commands on one shared contract for keyword research, content creation, technical audits, schema markup, monitoring, quality gates, entity truth, and campaign memory.