MCP
GTM intelligence for humans and agents
Thirty-two GTM-intelligence tools inside Claude, Cursor, and ChatGPT — stack scans, swaps, vendor comparisons, RevOps benchmarks, and revenue analysis. The same stack-intelligence that powers StackSwap, in your AI client. Free, one install command.
Free · Start here
MCP — for Claude, Cursor & ChatGPT
Thirty-two GTM-intelligence tools inside your AI client. Ask it about stacks, swaps, vendors, and RevOps benchmarks — or feed it your own deals and accounts to rank — in plain language. No API key, one install command.
Free · Flagship tool
AEO audit — see how AI reads your site
Run the free AEO audit: how answer engines like ChatGPT, Perplexity, and Google AI Overviews see your site — and what to fix to get cited. No signup to see your score.
MCP — thirty-two tools inside your AI client
The StackSwap MCP is a free Model Context Protocol server. One install command puts thirty-two GTM-intelligence tools directly inside Claude Code, Claude Desktop, ChatGPT Desktop, or Cursor. Free, no API key, stateless JSON-RPC.
Install
Claude Code (CLI)
One command in any terminal:
claude mcp add --transport http stackswap https://stackswap.ai/api/mcpClaude Desktop
Add this block to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop:
{
"mcpServers": {
"stackswap": {
"url": "https://stackswap.ai/api/mcp",
"transport": "http"
}
}
}Cursor / ChatGPT Desktop / other MCP clients
Add a new HTTP MCP server with URL https://stackswap.ai/api/mcp. No authentication. The endpoint responds to GET with a server descriptor for sanity-checking and to POST with JSON-RPC requests. A working TypeScript example client lives in the public docs repo.
https://stackswap.ai/api/mcpWhat can I actually ask it?
Once it’s installed, just ask in plain language. Your AI client picks the right tool and answers from the StackSwap engine. A few to try:
The thirty-two tools, by domain
Stack Intelligence
find_overlaps— Find curated overlap pairs in a stack with savings estimates.suggest_swaps— AI-native replacement recommendations for legacy tools.scan_stack— Preview StackScan — monthly/annual recoverable spend + top 5 opportunities.recommend_stack— Greenfield reference stack for an industry vertical.
Research
search_tools— Fuzzy-search the StackSwap catalog of ~400 GTM tools by name.get_tool_details— Full profile for a single tool including partner link.compare_tools— Head-to-head comparison of two tools.compare_tools_n_way— Side-by-side matrix of 2–6 tools in one shot.get_vendor_fact_sheet— Full GTM Decision Schema doc — pricing tiers, gotchas, AI capabilities, affiliate terms.get_category_landscape— Full map of one GTM category — leaders, runner-ups, skip list.
Knowledge Base
search_content— Full-text search across the StackSwap operator KB (~50 articles).get_kb_article— Fetch a KB article body as markdown by slug.
Procurement
get_buyer_questions— Operator-authored questions to ask before signing — per-vendor gotchas.get_renewal_strategy— Renewal-negotiation playbook with leverage points and walkaway script.recommend_partner— Best-fit affiliate partner for a given GTM need.
RevOps
get_revops_benchmark— Operator read on a RevOps metric — healthy range, how to read it, common mistakes.get_revops_playbook— Repeatable RevOps motion — measure tool ROI, win-rate-by-signal, forecast cadence.
Calculators
compute_pipeline_coverage— Weighted + raw pipeline coverage vs quota, judged against the 2.5x–4x band.compute_cac_payback— Gross-margin CAC payback period in months, with the segment verdict.compute_nrr— Net + gross revenue retention from your cohort numbers, with a fragility flag.
Revenue analysis
prioritize_pipeline— Rank your own open deals by expected value + velocity into Work-now / Soon / Watch.rank_renewals_at_risk— Rank your own accounts by ARR × churn risk, with a save play for each.score_account_fit— ICP Match + Intent fit score across your own book of accounts.score_expansion_opportunities— Rank your accounts by upsell/cross-sell propensity × modeled value, with the lever.find_whitespace— Product-penetration map of your book vs a catalog — which products are unsold where.build_forecast— Weighted Commit / Best-case / Pipeline forecast from your deals, vs quota.analyze_win_loss— Which attributes predict wins across your closed deals, with sample sizes.segment_revenue— ARR and NRR/GRR by segment across your book — where revenue grows vs leaks.analyze_concentration_risk— Top-N ARR share, HHI, whale dependency, and at-risk ARR across your accounts.audit_pipeline_hygiene— 0–100 cleanliness score + the dirty deals (stale, no next step, missing fields).
Detect & Contribute
detect_stack_from_text— Infer a GTM stack from a careers page, JD, or site HTML.submit_correction— Queue a pricing, feature, or gotcha correction for admin review.
Endpoint: POST https://stackswap.ai/api/mcp · Server descriptor: GET https://stackswap.ai/api/mcp
Protocol versions: 2025-06-18, 2025-03-26, 2024-11-05
Source: docs + schemas + example client at StonesofCreation/stackswap-mcp (MIT). MCP server implementation is closed-source.
FAQ
Start with the free tools
The MCP is free and live — start there. Then run the free AEO audit to see how AI answer engines read your site.