Stacktree

Registre officiel IA et agents

Publish HTML to private, unguessable, replace-in-place URLs from any MCP-compatible AI agent.

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

Remote (streamable-http)
Claude Code
claude mcp add --transport http stacktree 'https://api.stacktr.ee/mcp'
Configuration JSON (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "stacktree": {
            "type": "http",
            "url": "https://api.stacktr.ee/mcp"
        }
    }
}
NPM package stacktree-mcp
Claude Code
claude mcp add stacktree -- npx -y stacktree-mcp@0.8.3
Configuration JSON (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "stacktree": {
            "command": "npx",
            "args": [
                "-y",
                "stacktree-mcp@0.8.3"
            ]
        }
    }
}

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. stacktree-mcp
  2. Set up with an agent
  3. Install
  4. You may not need this package
  5. Tools
  6. Linking a wallet
  7. Reading feedback
  8. Privacy Policy
  9. Privacy defaults
  10. What the free plan gives you

stacktree-mcp

MCP server for stacktr.ee. Publish HTML artifacts from any MCP client (Claude Desktop, Claude Code, Cursor, Continue, etc).

Set up with an agent

If you have a coding agent open, hand it this line and it does the rest — installs, verifies the connection, and learns the tool surface:

Fetch and follow the setup instructions at https://stacktr.ee/prompt.md

Works in any agent that can fetch a URL. The instructions are plain Markdown; read them first if you like.

Install

Add to your MCP client config:

{
  "mcpServers": {
    "stacktree": {
      "command": "npx",
      "args": ["-y", "stacktree-mcp"],
      "env": { "STACKTREE_API_KEY": "stk_live_..." }
    }
  }
}

Generate an API key at https://app.stacktr.ee.

You may not need this package

This is the stdio bridge, for clients that cannot speak streamable HTTP. If yours can, connect straight to the hosted server at https://api.stacktr.ee/mcp, which exposes the same 42 tools and takes the same key:

curl -sS -X POST https://api.stacktr.ee/mcp \
  -H "Authorization: Bearer $STACKTREE_API_KEY" \
  -H 'accept: application/json, text/event-stream' \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

No browser and no OAuth flow is required to do that: an stk_live_ key is a valid credential on the MCP endpoint, exactly as it is on the REST API. OAuth 2.1 with Dynamic Client Registration is also accepted, for connectors acting on behalf of a signed-in human; session cookies are refused. Send one credential.

No key, and no human to ask? POST https://api.stacktr.ee/provision buys one over x402. A human nearby but no browser? POST https://api.stacktr.ee/api-keys/device-code, print the returned verification_url_complete for them, and poll /api-keys/device-code/poll until it returns the key (RFC 8628).

Tools

ToolWhat it does
publish_htmlPublish HTML; returns { url, id, expires_at, ... }. Pass client to file it under a client space.
update_siteReplace the HTML of an existing site in place; URL is preserved.
get_siteRead a site's current HTML source — edit it, then update_site.
set_passwordAdd or clear a passcode gate. Works on every plan.
set_expirySet hours-from-now expiry, or null for never. Clamped to the plan ceiling.
set_email_gateRestrict viewers to an email domain (one-time magic-link verify). Paid plans only.
set_client_feedbackLet the people you send a page to comment on it (words, images, video) and react, with no account.
set_agentationOlder developer mark-up toolbar. Prefer set_client_feedback.
list_sitesList sites owned by this API key. Paged (has_more + cursor); filter with client.
delete_siteTake a page down. The link dies at once; the content is kept 30 days, then destroyed.
restore_sitePut a deleted or expired page back at the same URL, inside those 30 days.
claim_siteAdopt a page published without an account, using its claim_token. Same URL; a claim counts as a publish.
get_contentRead a page back as html (exact stored source, editable) or text (stripped, cheap to read).
get_meThis key's account, plan, counts and enforced limits. Read limits from here, never from a description.
link_walletLink your wallet so pages you publish are owned by your account.
list_feedbackRead client comments, unresolved first, each with what it is on and whether it is still on the page.
create_share_linkMint a link addressed to one person — every open through it is attributed to that name.
list_share_linksThe links on a page, with attributed opens and when each was last opened.
revoke_share_linkKill one link; the page and every other link keep working.
resolve_feedbackMark a feedback item addressed, with an optional note.
set_clientFile a page under a client space by name or slug (auto-created), or null to detach.
list_client_spacesThe client spaces on the account: page counts, bound hostname, portal state.
create_client_spaceCreate a space up front. Rarely needed — publishing with client creates one.
update_client_spaceRename, archive, or set the space-wide viewer gate every page under it inherits.
delete_client_spaceRemove a space. Its pages detach and keep their URLs.
get_design_guideThe house design guide — read it before generating or restyling a page.
get_passcodeShow the passcode on a page you own, to send it to the client again (passcodes set since 13 September 2026).
list_versionsEarlier versions of a page, newest first: one snapshot per update.
restore_versionPut an earlier version back at the same URL after a bad update.
whos_it_forRecord who a page is for and get their own link. Sends nothing.
unopened_pagesPages, and named people, that have not opened what was sent an hour on.
get_revision_briefEverything that came back on a page, as the brief for its next version.
publish_revisionReplace a page in place and resolve the comments it answers, in one step.
resolve_commentsResolve several comments at once, each with a note the reviewer sees.
request_approvalAsk named people to approve a page; one private link each.
get_approval_statusWho has approved the version that is live now, section by section.
list_responsesWhat readers sent through the forms marked on a page.
resolve_addressed_notesClose the reviewers' notes an update answered, with one line each.
open_html_fileOpens an .html file in ChatGPT desktop's file viewer. Here it only echoes the file back.
stacktree_pagesYour 25 newest pages: ChatGPT's pages panel. Same data as list_sites.
publish_card_statusRefreshes the publish card in ChatGPT and Claude. Here it returns the page's detail.
publish_card_openThe publish card's Open button: a 15-minute owner preview link to a page.

Linking a wallet

If your agent pays for publishes from its own wallet (x402 / MPP), link that wallet to your Stacktree account so every page it publishes — past and future — is owned there:

  1. Your human generates a link code at https://app.stacktr.ee/wallets.
  2. link_wallet({ code }) → returns the exact message to sign.
  3. Sign it with your wallet (personal_sign).
  4. link_wallet({ code, wallet, signature }) → links the wallet and adopts the pages it already published.

Reading feedback

Turn comments on with set_client_feedback and whoever you sent the link to can select words, or click an image, video or section, and leave a comment only the owner sees. list_feedback returns them, unresolved first, each with a one-line target and on_page (still in the page, or gone since an edit). Fix the page in place with update_site (same URL): its response lists which open comments no longer match the new version. Then resolve_feedback each answered one with a short note, which the client sees next to their comment.

Privacy Policy

Full policy: https://stacktr.ee/privacy. In short:

  • What is collected. This server sends what you ask it to publish (the HTML and files) and your tool calls to https://api.stacktr.ee, authenticated with your Stacktree API key. It collects nothing from your machine beyond that and keeps no local data.
  • How it is used and stored. Published files are stored in Cloudflare R2 and page metadata (URL, visibility, expiry, password hash, view counts) in Cloudflare D1, to serve your pages. Optional features you switch on per page, such as the design pass, Ask this page and page video, send that page's text to the AI services named in the policy, under terms that exclude training on it.
  • Sharing. Stacktree does not sell personal data. It shares data only with the sub-processors needed to run the service, listed in the policy (for example Cloudflare, Clerk for sign-in, Stripe for billing).
  • Retention. A page lives until it expires or you delete it; after that the content is kept 30 days so it can be restored, then destroyed. Serving logs are kept 30 days with IP addresses hashed.
  • Contact. privacy@stacktr.ee

Privacy defaults

Every site gets an unguessable https://stacktr.ee/p/{token}/ URL. Pass public_slug to opt into https://{slug}.stacktr.ee/.

pii_check defaults to block — uploads matching common secrets and PII shapes (emails, SSNs, credit cards, OpenAI/GitHub/Stripe API-key prefixes) are refused. Pass warn to publish anyway (matches are flagged in the response), or off to skip the scan.

What the free plan gives you

A key on the free plan publishes 3 pages in total, and each one expires 7 days after it is published. The count is lifetime, not concurrent: deleting a page or letting it expire does not give the slot back.

expires_in_hours: "never" is refused on a plan that caps page lifetime, not quietly shortened: 409 expiry_clamped, nothing published, and the body carries the date the page would have got. Pass accept_clamp: true to take the ceiling, or tell the user the plan cannot make the link permanent. A number longer than the ceiling is shortened rather than refused, with expiry_clamped: true in the response. Either way, read expires_at_iso off the response and quote that, never the value you asked for.

Passcodes (set_password) work on every plan, free included. Email gates (set_email_gate) and viewer numbers are on paid plans. Hitting a ceiling returns HTTP 402 with a stable plan_* code in error:

CodeMeans
plan_lifetime_limit_exceededAll 3 free pages used. Deleting one does not help.
plan_site_limit_exceededActive-page cap reached.
plan_password_not_availablePasscodes are not on this plan (they are on Free; a plan can still be without them).
plan_viewer_gate_not_availableEmail gates are not on this plan.
plan_domain_not_availableCustom domains are not on this plan.

GET /me — or the get_me tool — returns the calling key's own limits object. Read caps from there rather than hard-coding them. Current plans and prices: https://stacktr.ee/pricing.md.

Questions fréquentes

Qu'est-ce que Stacktree ?

Publish HTML to private, unguessable, replace-in-place URLs from any MCP-compatible AI agent.

Comment installer Stacktree ?

Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http stacktree 'https://api.stacktr.ee/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour Stacktree ?

Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.

Stacktree est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient Stacktree ?

Il est publié par stevysmith. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.