StackSwap

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

B2B GTM stack intelligence: search ~400 tools, compare vendors, find overlaps, audit SaaS spend.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "StackSwap": {
      "url": "https://stackswap.ai/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (23)

• inspect_available_connections

  Identify available connected systems and the read-only evidence StackSwap needs. The server cannot introspect neighboring MCPs automatically.

  Parameters:

  • systems — array
  • auditGoal — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• request_system_connection

  Return a safe, read-only connection or export request for a named system when an audit lacks evidence.

  Parameters:

  • system (required) — string
  • purpose — string
  • preferredMode — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• start_stack_audit

  Start an adaptive GTM architecture audit and return the smallest discovery questionnaire needed before KEEP, SWAP, or BUILD recommendations.

  Parameters:

  • goal — string
  • stage — string
  • motion — string
  • systems — array

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• complete_stack_audit

  Turn user answers and connected-system evidence into explainable KEEP, SWAP, and BUILD recommendations with confidence, alternatives, and next prompts.

  Parameters:

  • systems (required) — array
  • goal — string
  • stage — string
  • motion — string
  • answers — object
  • constraints — array
  • connectedEvidence — array

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• generate_data_layer_blueprint

  Generate a case-specific GTM data-layer blueprint when systems mirror state, drift, or lack explicit ownership.

  Parameters:

  • systems (required) — array
  • problem (required) — string
  • entities — array
  • primarySourceOfTruth — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• generate_build_prompt

  Generate a copy-ready one-shot build or migration prompt from a StackSwap KEEP, SWAP, or BUILD recommendation.

  Parameters:

  • recommendation (required) — string
  • output — string
  • target — string
  • systems — array

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• search_tools

  Search StackSwap's catalog of ~400 GTM tools by name. Returns each match with its catalogued monthly cost and, when applicable, a StackSwap partner sign-up link.

  Parameters:

  • limit — integer — Max number of results to return.
  • query — string — Substring to match against tool names (case-insensitive). Omit to list top tools.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_tool_details

  Full StackSwap profile for a single tool: cost (catalog + per-seat with confidence; vendor fact sheet wins when fresh), AI-readiness score, category, common overlaps, swap-registry status, and partner sign-up link. Use when the user wants depth on one tool (more than search_tools' name + cost).

  Parameters:

  • name (required) — string — Tool name (fuzzy-matched against catalog).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_vendor_fact_sheet

  Return the full vendor fact sheet (per GTM Decision Schema v1.0.0) for a tool, when one exists. Includes pricing tiers with gotchas, integration depth scores, AI capabilities + customer-data-for-training disclosure, affiliate program terms, and self-disclosed conflicts (vendor-claim vs user-reported). Provenance is labeled (vendor / stackswap / community) and freshness is computed against a 90-day window. Use when an agent or buyer needs the structured machine-readable view of a tool — strictly more detail than `get_tool_details`. Returns a not-found message + a pointer to /vendors/submit-fact-sheet when no fact sheet exists.

  Parameters:

  • tool (required) — string — Tool name or slug (e.g. "Apollo.io", "apollo", "Smartlead"). Fuzzy-matched against the catalog.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• find_overlaps

  Given a list of tool names in a user's stack, return the redundant pairs StackSwap has curated (104 hand-verified overlaps) along with monthly/annual savings if one is consolidated.

  Parameters:

  • tools (required) — array — Tool names in the current stack (e.g. ["HubSpot", "Salesforce", "Outreach"]).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• suggest_swaps

  For each tool supplied, return StackSwap's AI-native replacement recommendation (when one exists) with annual savings and reasoning. Skews toward legacy → modern swaps (Outreach → Smartlead, ZoomInfo → Apollo, etc.).

  Parameters:

  • tools (required) — array — Tool names to evaluate for AI-native replacements.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scan_stack

  Run a preview StackScan: pass a list of tools + team size + industry, get back current spend, optimized spend, monthly/annual recoverable, headless gaps (tools with no MCP/API connection an owned head can call), and the top 5 replace/remove opportunities. Includes a link to the full paid audit on stackswap.ai.

  Parameters:

  • tools (required) — array — Tool names in the user's current stack.
  • industry — string — Industry slug or label. Recognised slugs: b2b_saas, revenue_sales_tech, marketing_tech, revops_operations, real_estate_tech, fintech_financial, dev_tools_plg, hr_recruiting_tech, agency_consultancy, healthtech, edtech, other. Unknown values default to 'other'.
  • teamSize — string — Team-size band. Defaults to 11-25 when omitted.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recommend_partner

  Given a need (e.g. 'outbound', 'CRM', 'automation'), return StackSwap's recommended affiliate partner(s) with sign-up URL and positioning.

  Parameters:

  • category (required) — string — Category keyword or need description (e.g. "outbound", "CRM for small team", "Zapier alternative").

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recommend_stack

  StackSwap's reference starter stack for a given industry vertical. Returns a curated tool list with per-tool cost, total monthly/annual spend, AI-readiness and headless-readiness scores, and partner sign-up links. Use for greenfield 'what stack should I buy?' queries — distinct from scan_stack (audits an existing stack) and recommend_partner (single category).

  Parameters:

  • industry (required) — string — Industry vertical. Recognised: 'SaaS / Tech', 'Marketing Agency', 'Finance / Fintech', 'Consulting'. Common slugs (b2b_saas, fintech, agency) and aliases also accepted; unknown values map to closest match.
  • budget — number — Optional monthly budget cap in USD. If exceeded, the response flags the overage but does not auto-swap tools.
  • teamSize — string — Team-size band for cost modeling. Defaults to 11-25.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compare_tools

  Head-to-head comparison of two GTM tools. Returns cost delta, AI-readiness and headless-readiness (MCP/API callability — can an agent or your own dashboard drive it) scores, overlap status, swap-registry signal, and StackSwap's recommended pick with reasoning. Use when the user is choosing between two specific vendors (e.g. 'Salesforce vs HubSpot', 'Outreach vs Smartlead').

  Parameters:

  • a (required) — string — First tool name (fuzzy-matched against catalog).
  • b (required) — string — Second tool name (fuzzy-matched against catalog).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compare_tools_n_way

  Side-by-side comparison of 2–6 GTM tools in one shot. Returns a markdown matrix (cost, AI-readiness, headless-readiness, overlaps within the set, swap-registry status, StackSwap pick) and per-tool partner sign-up links. Use for category bake-offs (e.g. 'Apollo vs ZoomInfo vs Cognism vs Clay'). Prefer the 2-way compare_tools for clean head-to-head pairs.

  Parameters:

  • tools (required) — array — Tool names to compare side-by-side (fuzzy-matched against catalog).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• search_content

  Full-text search across StackSwap's first-party GTM knowledge base — ~50 operator-narrative articles on stack architecture, AI-native swaps, RevOps, data ethics, and decision frameworks. Returns ranked articles with title, slug, category, summary, and URL. Use when the user asks a GTM strategy/architecture/methodology question that's been written about (e.g. 'how should I think about CRM migration', 'what's wrong with intent data', 'how to audit my stack'). Cite the URL in your reply. Pass slug to `get_kb_article` for the full body.

  Parameters:

  • query (required) — string — Free-text search query. Multi-word queries are scored on per-term hits.
  • limit — integer — Max number of results.
  • category — string — Optional category filter (slug or label). Known slugs: gtm-infrastructure, stack-design, ai-automation, data-ethics.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_kb_article

  Fetch the full body of a StackSwap knowledge base article as markdown. Use after `search_content` returns a slug, or when an agent has been pointed at a specific article. Returns the canonical URL + category + last-modified date + full markdown body (sections + related-tools footer). Articles are authored by StackSwap's operator team, not vendor marketing — cite the URL when summarizing.

  Parameters:

  • slug (required) — string — Article slug, as returned by `search_content` (e.g. "modern-gtm-architecture", "how-to-audit-gtm-stack").

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_category_landscape

  Full map of one GTM category — leaders, runner-ups, and skip/replace candidates. Returns every catalogued tool in the bucket with cost, AI-readiness, swap-registry status, and partner sign-up links. Use when the user wants to see the full landscape for a category (e.g. 'show me all CRMs', 'what outbound tools exist', 'map the analytics category') — strictly more comprehensive than `recommend_partner` (single best pick). Known buckets: crm, outbound, data, marketing-automation, analytics, meetings, support, scheduling, automation, seo, cdp, revenue-intelligence, chat, collaboration, phone, landing-pages, linkedin, ai-content, saas-mgmt, enablement, ai-tooling.

  Parameters:

  • category (required) — string — Category keyword (e.g. "crm", "outbound", "automation") or free-text need ("zapier alternative", "ai sdr").
  • limit — integer — Max number of tools to surface.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• detect_stack_from_text

  Infer a GTM stack from a freeform text blob (a careers page, job posting, public site HTML, RFP, 'What we use' doc, browser DevTools network tab, etc.). Returns ranked tool matches with confidence levels (high/medium/low) and evidence snippets, plus a ready-to-use array for chaining into `scan_stack` or `find_overlaps`. Use when the user says 'I don't know what we use' or pastes a competitor's careers page to scout. Conservative on ambiguous short tokens — multi-mention or canonical-name matches win.

  Parameters:

  • text (required) — string — The text to scan. Anything from a job post to raw HTML works. Max 50KB.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_buyer_questions

  Return 10-20 questions a B2B GTM buyer should ask a vendor before signing — with 'why it matters' and 'watch for' red-flag answers. Pass `vendor` for vendor-specific gotchas (e.g. Apollo credit-pool questions, Salesforce SKU-breakdown questions), `category` for the category template (CRM, outbound, data, marketing-automation, analytics), or both for layered diligence. Authored by StackSwap's operator team (Nick French, 10+ yrs B2B SaaS GTM). Use when the user is evaluating a vendor, prepping for a sales call, or building a procurement checklist.

  Parameters:

  • vendor — string — Optional vendor name or slug (e.g. "Apollo", "salesforce", "Outreach"). Layers vendor-specific gotchas on top of the category template.
  • category — string — Optional category bucket slug (crm, outbound, data, marketing-automation, analytics). Defaults to the vendor's primary category if omitted.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_renewal_strategy

  Return StackSwap's renewal-negotiation playbook for a specific vendor: leverage points (why they will discount), price-anchor alternatives to cite, a calibrated discount ask, a walkaway script, optimal timing window, and contract-trap callouts. Pass `monthlySpend` to compute target savings. Optional `contractEndsIn` flags compressed-timeline adjustments. Authored from operator experience across major B2B SaaS renewals (Salesforce, HubSpot, ZoomInfo, Apollo, Outreach, Smartlead, Gong, Clay). Use when the user mentions a renewal, a price increase, or 'we're up for renewal' conversations.

  Parameters:

  • vendor (required) — string — Vendor name or slug (e.g. "Salesforce", "zoominfo", "Outreach").
  • monthlySpend — number — Optional current monthly spend in USD. Used to compute target savings against the suggested discount ask.
  • contractEndsIn — string — Optional contract-end horizon. "days" or "weeks" triggers compressed-timeline guidance.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• submit_correction

  Submit a correction to the StackSwap catalog (pricing, feature list, gotcha, AI-readiness score, category, or other). Submissions queue for admin review and only propagate to user-facing surfaces after merge — they DO NOT immediately mutate the catalog. Use when the user notices a stale price, an inaccurate feature list, a gotcha that should be flagged, or wants to report a tool we don't cover. Two-way data flow that helps keep the catalog accurate. Returns a correction ID + reassurance that the submission is queued.

  Parameters:

  • tool (required) — string — Tool name (fuzzy-matched against catalog; new tools accepted too).
  • field (required) — string — Which aspect of the catalog entry the correction targets.
  • proposed_value (required) — string — The corrected value as the user would have it shown.
  • source_url — string — Optional: a public URL that backs the correction (vendor pricing page, doc, etc.). Strong signal for fast approval.
  • current_value — string — Optional: what the catalog currently shows (for reviewer context).
  • reporter_context — string — Optional: free-text context (e.g. "Smartlead just raised the entry tier from $39 to $49 on their pricing page").

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.