Smithery is now a part of Arcade.dev! Read more in our announcement here
Statistical analysis platform — upload CSV or connect GA4/GSC, run 77+ validated R-based analysis modules (regression, ML, time series, churn prediction, marketing attribution, RFM segmentation). Interactive HTML reports with AI insights and PDF export. Pay per report, no subscription.
ConvRadar is an MCP server that turns your Google Analytics 4 data into a working conversation about conversion rate optimization. Instead of staring at dashboards trying to figure out why revenue dropped last week, you ask Claude — and Claude pulls the data, finds the real problem, and tells you what to do about it. Most analytics tools stop at "your conversion rate is down 12%." ConvRadar continues: which segment caused it, which traffic source is leaking budget, which landing page is underperforming, which device tier is broken, and what to fix first. Every recommendation is tied to specific numbers from your own GA4 data — not generic best practices. What you can ask: "Why did conversions drop last week?" → diagnoses which segment is responsible "Run a full CRO audit on my store" → headline KPIs, funnel breakdown, traffic quality, top problems ranked by impact "Which traffic sources are wasting my budget?" → relative efficiency analysis across paid sources "What's broken on mobile
Your AI marketing analyst, connected to live data. 40 MCP tools across Google Ads, Meta Ads, GA4, Search Console, Keyword Planner, and Stripe. Read, analyze, manage campaigns, and run AI monitoring agents that watch your accounts 24/7. What you can do Connect in 2 minutes, then ask Claude: "Where am I wasting ad spend?" — Claude pulls 30 days of search terms, keyword performance, and conversion data. Returns ranked waste sources with fix recommendations. "Audit my top-spending Google Ads campaign" — 7-category scoring (structure, ad quality, keywords, budget, performance, negatives, audiences). 0-100 score + critical/warning/suggestion issues. "Set up monitoring agents that alert me if CPA spikes" — Claude analyzes your baseline, proposes data-grounded thresholds. SaaS-side evaluator runs every 6h, emails alerts on breach. "Create a Meta Ads campaign with $20/day budget targeting young moms" — Claude builds the full campaign
A managed AI marketing agent that plugs into all your AI tools. Ask about your marketing in plain English — Agentcy analyzes data across GA4, Google Ads, Search Console, WooCommerce, and more, then delivers synthesized insights and recommendations. Not a data dump. An agent that thinks. One connection. All your marketing data sources. Switch between domains instantly. Works with Claude, ChatGPT, Cursor, VS Code, OpenClaw, and any MCP client. Sign up at goagentcy.com to configure your domains and data sources. Free plan includes 50 requests/month — paid plans start at $29/mo.
19 free website QA and AI-visibility tools as MCP tools: AI visibility checker, robots.txt AI checker, llms.txt generator, page-to-Markdown, JSON-LD validator and generator, social preview checker, tech stack detector, full page screenshot, alt text generator, UTM builder, and more. Remote HTTP server, no account, no API key.
PaidSync is an MCP server with over 309 verified tools across 8 platforms (Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, Google Tag Manager, Google Analytics 4, Google Search Console, Google Merchant Center). Full read+write on every ad platform plus tracking infrastructure setup and Shopping feed control. Operator-confirmation gate on every write action. Verified Google Premier Partner, Meta Business Partner, LinkedIn Marketing Partner, and TikTok Marketing Partner concurrently. The only MCP for advertising holding all four verifications. Founded by Ahmed Ashraf with over $500M in managed advertising spend. Lean MCP runtime exposes 20 tools at session start with over 309 callable via the paidsync_exec sandbox, reducing context overhead by 95% compared to traditional MCP servers. Free tier: 15 calls/month, no credit card. Paid plans start at $49/month with full write access on every platform.
Your AI Board of Directors. Run multi-model debates where GPT-4o, Claude, Gemini, and more discuss your question, then a moderator synthesizes their perspectives into actionable insight.
Train gradient boosting models quickly and export portable artifacts for smooth deployment. Run fast predictions from newly trained models or existing artifacts. Upload datasets, browse available backends, and access a practical guide with best practices and troubleshooting.
Authorized website audits for security, technical SEO, AI visibility, integrations, accessibility, and performance.
Explore drug-target associations and disease-gene evidence. Search targets, diseases, and drugs with genetics and literature-backed data.
Search and analyze 700+ DeFi vaults across Morpho, Aave, Spark, Yearn, Beefy, Compound, Uniswap and others. Multi-vector risk scoring (Asset 40%, Platform 40%, Governance 20%) with Prime/Core/Edge.
The GEO check every vibe coder runs before they launch. Synapse is the GEO (Generative Engine Optimization) growth layer for new products. This MCP server gives any coding agent — Cursor, Claude Code, Windsurf, Cline, Continue, Zed — the ability to audit, fix, and track how AI agents discover and recommend a project. Tools geocheck — Run the 24-rule GEO linter on a URL or local path. Returns a 0–100 Growth Score and a list of failing rules with evidence. geofix — Apply auto-fixers: writes llms.txt, robots.txt (with the AI-bot allowlist), and /.well-known/agent-answer.json to the project. Never touches your content. geotrackinit — Register the site with the Synapse dashboard to start tracking AI-agent referrals. geoprompts — Generate a visibility-test prompt pack for ChatGPT / Claude / Perplexity. geostatus — Live Growth Score, agent mentions, and visits for an installed site. geocorpusquery — Query the public Syna
Free SEO & AI-search (AEO/GEO/LLMO) audits for any website or Shopify store: 12-signal AI-readiness score, full SEO audit, emailed reports with weekly score tracking, and one-click inxy subscription links. Tools: aisearchdiagnostic, fullseoaudit, emailseoreport, subscribetoinxy, getmystore_audit.
One API Key to access 6 AI models (DeepSeek, GPT-4o, Claude). Pay-per-use, OpenAI compatible. MCP protocol support. Web search at 5 ATEX/call.
Clean US equity total returns + institutional risk decomposition, via MCP. RiskModels gives agents dividend-adjusted total return series for any US stock or ETF — and decomposes both the return and its risk into market → sector → subsector → residual layers, with executable ETF hedge ratios for each. Built on ERM3, a hierarchical factor model with orthogonalized factor construction over ~3,000 US equities (16k-name historical panel), daily history back to 2006. One MCP call covers performance tracking, return attribution, manager-skill / 13F review, hedging, stat-arb, or feeding clean returns into your own models. Capabilities Returns — daily dividend-adjusted total (gross) return series, point-in-time / time-safe Return attribution — gross return split into L1/L2/L3 factor vs residual; isolates the residual (stock-picking / alpha) series Risk decomposition — additive market / sector / subsector / residual variance shares (su
NVIDIA AI developer stack as a traversable knowledge graph — 20 domains (NIM, NeMo, TensorRT-Triton, Isaac, Cosmos, DRIVE, Clara, Jetson, Riva, OpenShell and more), 998 nodes, typed edges. 11× fewer tokens than RAG. MCP-native — drops into Claude Desktop, Cursor, Claude Code CLI.
DeFi yield aggregator API for AI agents. Find the best lending, staking, and LP yields across 100+ protocols (Aave, Compound, Morpho, Lido, Yearn, Curve, Convex). Powered by DeFiLlama with TVL, risk scoring, and historical APY. Tools: defifindbestyields. Use this when looking for yield opportunities, comparing protocols, or building DeFi portfolio strategies. IMPORTANT: For swap quotes, use dexgetswapquote. For gas costs, use gasgetcurrent_price. Returns yields sorted by APY with TVL and risk. No API key required — x402 micropayment $0.002/call on Base L2.
Omnicall is the all-in-one agent gateway: 248 LLMs (GPT, Claude, Gemini, Grok, DeepSeek, Llama, Qwen, Mistral) plus image, video, voice & music generation, live crypto / DEX / DeFi / prediction-market data, web search, multi-platform research, X profiles and on-chain reads — one keyless endpoint, pay per call in USDC on Base or Solana. No API keys, no subscriptions. Free tier to try instantly.
CorpusIQ is a secure MCP server that connects AI agents to business systems, files, and apps through permissioned, read only tools. It lets teams ask operational questions and get cited answers from live business data across platforms like Google Workspace, QuickBooks, Shopify, Slack, Microsoft, analytics tools, and more. CorpusIQ is built for business intelligence, workflow automation, compliance, and audit ready decision support. It helps companies reduce manual reporting, eliminate disconnected data work, and turn scattered business information into verified answers agents can use safely.
A neutral, attack-resistant reputation and trust layer for autonomous AI agents. Agent Guild lets an agent ask "who is the safest agent for this job?", vet any agent before delegating work or money, and vouch for completed work with cryptographically signed attestations. Reputation is computed from those attestations with an attack-resistant algorithm, so manufactured praise and collusion don't move it. Free writes (register, attest), metered reads (discovery, risk). Tools: guildsearch, guildbestagent, guildriskscore, guildregister, guild_attest.
Opus Growth turns your AI assistant into a full ad operator across Google, Meta, Microsoft, TikTok and LinkedIn Ads — plus Google Analytics, Search Console, Business Profile, YouTube and Tag Manager. Audit accounts, cut wasted spend, build and optimize campaigns, and manage conversion tracking — all by chatting. Every change is previewed and applied only on your approval. Works with Claude, ChatGPT, Cursor, Windsurf, Codex and any MCP client. 200+ tools.
