StackSwap MCP server
io.github.StonesofCreation/stackswapStonesofCreationstreamable-httpv1.1.0Scanned
B2B GTM stack intelligence: search ~400 tools, compare vendors, find overlaps, audit SaaS spend.
23 tools: 11 change things and 12 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
11 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the StackSwap MCP server can do
The StackSwap MCP server is published by the GitHub account StonesofCreation. It has 23 tools. It can create or change data (11 tools: request_system_connection, start_stack_audit, complete_stack_audit, generate_data_layer_blueprint and 7 more), but cannot delete data. 12 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 16, 2026, version 1.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
23 tools
Changes things 11Claude Code: ask
complete_stack_auditTurn user answers and connected-system evidence into explainable KEEP, SWAP, and BUILD recommendations with confidence, alternatives, and next prompts.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Turn user answers and connected-system evidence into explainable KEEP, SWAP, and BUILD recommendations with confidence, alternatives, and next prompts.
detect_stack_from_textInfer 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.).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
generate_build_promptGenerate a copy-ready one-shot build or migration prompt from a StackSwap KEEP, SWAP, or BUILD recommendation.No findings
Why it is in this group
- The name "generate_build_prompt" says "generate": a word for a change.
Description, as the server wrote it Generate a copy-ready one-shot build or migration prompt from a StackSwap KEEP, SWAP, or BUILD recommendation.
generate_data_layer_blueprintGenerate a case-specific GTM data-layer blueprint when systems mirror state, drift, or lack explicit ownership.No findings
Why it is in this group
- The name "generate_data_layer_blueprint" says "generate": a word for a change.
Description, as the server wrote it Generate a case-specific GTM data-layer blueprint when systems mirror state, drift, or lack explicit ownership.
recommend_partnerGiven a need (e.g.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Given a need (e.g. 'outbound', 'CRM', 'automation'), return StackSwap's recommended affiliate partner(s) with sign-up URL and positioning.
recommend_stackStackSwap's reference starter stack for a given industry vertical.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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).
request_system_connectionReturn a safe, read-only connection or export request for a named system when an audit lacks evidence.No findings
Why it is in this group
- The name "request_system_connection" says "request": a word for a change.
Description, as the server wrote it Return a safe, read-only connection or export request for a named system when an audit lacks evidence.
scan_stackRun 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 conn…No findings
Why it is in this group
- The description's first verb is "run": a word for a change.
Description, as the server wrote it 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.
start_stack_auditStart an adaptive GTM architecture audit and return the smallest discovery questionnaire needed before KEEP, SWAP, or BUILD recommendations.No findings
Why it is in this group
- The name "start_stack_audit" says "start": a word for a change.
Description, as the server wrote it Start an adaptive GTM architecture audit and return the smallest discovery questionnaire needed before KEEP, SWAP, or BUILD recommendations.
submit_correctionSubmit a correction to the StackSwap catalog (pricing, feature list, gotcha, AI-readiness score, category, or other).No findings
Why it is in this group
- The name "submit_correction" says "submit": a word for a change.
Description, as the server wrote it 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.
suggest_swapsFor each tool supplied, return StackSwap's AI-native replacement recommendation (when one exists) with annual savings and reasoning.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.).
Only reads 12Show 12 read-only tools
compare_toolsHead-to-head comparison of two GTM tools.No findings
Why it is in this group
- The name "compare_tools" says "compare": a word for reading.
Description, as the server wrote it 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').
compare_tools_n_waySide-by-side comparison of 2–6 GTM tools in one shot.No findings
Why it is in this group
- The name "compare_tools_n_way" says "compare": a word for reading.
Description, as the server wrote it 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.
find_overlapsGiven 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…No findings
Why it is in this group
- The name "find_overlaps" says "find": a word for reading.
Description, as the server wrote it 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.
get_buyer_questionsReturn 10-20 questions a B2B GTM buyer should ask a vendor before signing — with 'why it matters' and 'watch for' red-flag answers.No findings
Why it is in this group
- The name "get_buyer_questions" says "get": a word for reading.
Description, as the server wrote it 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.
get_category_landscapeFull map of one GTM category — leaders, runner-ups, and skip/replace candidates.No findings
Why it is in this group
- The name "get_category_landscape" says "get": a word for reading.
Description, as the server wrote it 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.
get_kb_articleFetch the full body of a StackSwap knowledge base article as markdown.No findings
Why it is in this group
- The name "get_kb_article" says "get": a word for reading.
Description, as the server wrote it 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.
get_renewal_strategyReturn 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 wal…No findings
Why it is in this group
- The name "get_renewal_strategy" says "get": a word for reading.
Description, as the server wrote it 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.
get_tool_detailsFull 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…No findings
Why it is in this group
- The name "get_tool_details" says "get": a word for reading.
Description, as the server wrote it 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).
get_vendor_fact_sheetReturn the full vendor fact sheet (per GTM Decision Schema v1.0.0) for a tool, when one exists.No findings
Why it is in this group
- The name "get_vendor_fact_sheet" says "get": a word for reading.
Description, as the server wrote it 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.
inspect_available_connectionsIdentify available connected systems and the read-only evidence StackSwap needs.No findings
Why it is in this group
- The name "inspect_available_connections" says "inspect": a word for reading.
Description, as the server wrote it Identify available connected systems and the read-only evidence StackSwap needs. The server cannot introspect neighboring MCPs automatically.
search_contentFull-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 frame…No findings
Why it is in this group
- The name "search_content" says "search": a word for reading.
Description, as the server wrote it 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.
search_toolsSearch StackSwap's catalog of ~400 GTM tools by name.No findings
Why it is in this group
- The name "search_tools" says "search": a word for reading.
Description, as the server wrote it 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.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:00 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 11
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 11 tools that change things (11 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://stackswap.ai/api/mcp: tools/list returned 23 tools to an anonymous client, including request_system_connection (write), start_stack_audit (write), complete_stack_audit (write), generate_data_layer_blueprint (write), generate_build_prompt (write) and 6 more
Posture changes
- Oct 29, 2026
- HTTP status of an anonymous initialize: 530 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 11
- Protocol version: none to 2025-06-18
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 530 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 11 (and 1 more).View diff
- HTTP status of an anonymous initialize: 530 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 11
- Protocol version: none to 2025-06-18
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http stackswap https://stackswap.ai/api/mcpclaude mcp add --transport http stackswap https://stackswap.ai/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__stackswap__inspect_available_connections",
"mcp__stackswap__search_tools",
"mcp__stackswap__get_tool_details",
"mcp__stackswap__get_vendor_fact_sheet",
"mcp__stackswap__find_overlaps",
"mcp__stackswap__compare_tools",
"mcp__stackswap__compare_tools_n_way",
"mcp__stackswap__search_content",
"mcp__stackswap__get_kb_article",
"mcp__stackswap__get_category_landscape",
"mcp__stackswap__get_buyer_questions",
"mcp__stackswap__get_renewal_strategy"
],
"ask": [
"mcp__stackswap__request_system_connection",
"mcp__stackswap__start_stack_audit",
"mcp__stackswap__complete_stack_audit",
"mcp__stackswap__generate_data_layer_blueprint",
"mcp__stackswap__generate_build_prompt",
"mcp__stackswap__suggest_swaps",
"mcp__stackswap__scan_stack",
"mcp__stackswap__recommend_partner",
"mcp__stackswap__recommend_stack",
"mcp__stackswap__detect_stack_from_text",
"mcp__stackswap__submit_correction"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as stackswap. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.StonesofCreation/stackswap/verify?hash=c99e3c36cb6464279a090c1f3884800e1c4514479c28e40ac8314b02feed7615" | jq -e '.changed == false'Pinned hash c99e3c36cb64, from Nov 16, 2026, 06:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.StonesofCreation/stackswap/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.StonesofCreation/stackswap)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:21 UTC.
StackSwap MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the StackSwap MCP server safe?
- No scan can promise that. What its definitions show: 23 tools, 11 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the StackSwap MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the StackSwap MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the StackSwap MCP server have?
- 23 tools: 11 write, 12 read. request_system_connection, start_stack_audit, complete_stack_audit, generate_data_layer_blueprint, generate_build_prompt, suggest_swaps, scan_stack, recommend_partner and 15 more.
Does the StackSwap MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the StackSwap MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the StackSwap MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.