This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
For AI agents — MCPBundles Directory API
Recommended: Directory API v1 over HTTP for detail and anonymous invoke when eligible (not MCP JSON-RPC on the publisher URL; no user MCPBundles credentials on v1).
GET https://www.mcpbundles.com/api/directory/v1/servers/weinerandballs-mcp-dc5d3227f2
GET https://www.mcpbundles.com/api/directory/v1/servers/weinerandballs-mcp-dc5d3227f2?live=1 (optional live refresh)
GET https://www.mcpbundles.com/api/directory/v1/servers/weinerandballs-mcp-dc5d3227f2/tools/<tool> (one tool: schema + invoke.url)
POST https://www.mcpbundles.com/api/directory/v1/servers/weinerandballs-mcp-dc5d3227f2/tools/{tool}
POST body: flat JSON of tool argument names and values; not an arguments wrapper. Replace {tool} with a tool name from GET detail.
Restricted agent shell (ChatGPT Codex desktop, some IDE sandboxes):
Default command sandboxes often block outbound network. curl exit 6 or "Could not resolve host" for www.mcpbundles.com is usually sandbox DNS — not evidence this site is down.
Retry the same Directory API GET with sandbox_permissions "require_escalated" and a one-sentence justification on the shell tool (Codex on-request approval). Do not tell the user the site is unreachable from sandbox curl alone.
Example justification: Run the public MCPBundles Directory API search outside the command sandbox to complete the user's MCP server lookup.
If the agent has browser access (e.g. Codex @Browser): open https://www.mcpbundles.com/?q=<query> or stay on this page — no shell network needed. Use WebMCP search_mcp_servers then get_mcp_server (document.modelContext / page tools; refresh with fetchTools or getTools if a tool id is missing from the snapshot). Read-only directory search; same index as Directory API v1 GETs. Neither WebMCP nor Directory API v1 uses user MCPBundles credentials.
Without a browser: after escalated curl fails, use GET https://www.mcpbundles.com/?q=<query> with Accept: text/markdown for ranked results.
Hub MCP (connected session): discover_mcp_servers — same filter semantics as search_mcp_servers.
Contract: https://www.mcpbundles.com/agents.md
OpenAPI: https://www.mcpbundles.com/api/directory/v1/openapi.json
Guide: https://www.mcpbundles.com/guides/mcpbundles-directory-api
For MCP client apps (human connect):
MCP connect URL: https://weinerandballs.com/api/mcp
Skill page: https://www.mcpbundles.com/skills/weinerandballs-mcp-dc5d3227f2
Explore capabilities (41)
read 8
write 17
Showing 25 of 41
Showing 25 of 41 tools from the public preview. Connect the server to inspect the full live tool list.
List5
Create3
Add2
Publish2
Set2
Other capabilities11
Create a site from a brief
write
create_site_from_brief
BUILD FIRST, ASK LATER. Creates a complete, live draft website in one call - free, instant, no account and no sign-in. Call this as soon as someone asks for a website, using whatever you already know and sensible defaults for the rest, then show them the returned preview_url and refine it with edit_section and set_theme. Do not interview the user first. Composition is deterministic and no language model is involved, so anything you leave blank renders as a visible placeholder rather than invente
Description may be truncated on the public preview.
Create a site from a brief — BUILD FIRST, ASK LATER. Creates a complete, live draft website in one call - free, instant, no account and no sign-in. Call this as soon as someone asks for a website, using whatever you already know and sensible defaults for the rest, then show them the returned preview_url and refine it with edit_section and set_theme. Do not interview the user first. Composition is deterministic and no language model is involved, so anything you leave blank renders as a visible placeholder rather than invente
Create a site from raw HTML — BUILD FIRST. Creates a live draft site from HTML you already have - free, instant, no account and no sign-in, fully deterministic with no language model involved. Call it immediately when the user brings you markup, then show them the returned preview_url. Choose create_site_from_brief instead when you are authoring the site yourself and want every section to stay editable in the Pagetool editor: this route keeps the markup verbatim and the flattening is ONE-WAY. Both routes end in the same host
Edit or remove a site section — Changes one node of a site - text, title, styling, link, image, heading level - or removes it and its descendants when remove is true. Address a section with section_id (from list_sections) or index, then aim at the node inside it with field (e.g. "heading", "body", "items[1].title"); list_sections shows every section's fields. Text goes on text nodes only: content aimed at a container is refused with the right field names. Free, and no account is needed for a draft you created.
Add a section — Adds ONE section of any kind (menu, map, faq, hours, ...) to an existing site, styled like the rest of it, without rebuilding the site. Pass content_json with that section's keys (or html with your own markup instead of kind), and position to choose where it goes (default: end, before the footer). Saves an undo version first; stage:true previews it before it goes live. Free.
Add a page to a site — Adds a new page (e.g. "/about", "/contact") to an existing site, built from html (same importer as create_site_from_html) or composed from sections/content_json in the site's own palette and fonts. Link between pages with href="/about". Respects the plan's page limit; stage:true previews it before it goes live. Free.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Weinerandballs is an MCP server at weinerandballs.com. MCPBundles discovered 41 tools on the live endpoint.
How do I connect Weinerandballs to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does Weinerandballs provide?
Operate this server?
Request removal if you do not want Weinerandballs listed here, or claim the listing if you want to manage it on MCPBundles.
Operate Weinerandballs?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
List a site's sections — Lists a site's top-level sections in order - each one's CURRENT index, its stable section_id, its kind, its heading, and its fields (every editable node inside it: heading, body, items[n].title, ... with each node's index and current text) - so you can aim edit_section at exactly the right node with section_id + field. Indices shift whenever an earlier section is removed, so list the sections again after any removal instead of reusing an index you recorded earlier. Free, and no account is needed
List your sites — Lists every site you own, newest first - site_key, name, preview_url and when that preview link expires, whether it is published and on which domain, and when it was created and last changed. Signed in (OAuth) it lists your account; with a draft_token it lists that draft. Read-only and free.
Archive an unpublished site — Removes one of your own UNPUBLISHED sites from your account so it no longer appears in list_sites (for example test sites). Nothing is deleted: it is the same recoverable archive the dashboard uses. Live sites, and sites with an active client pay link, are refused. Signed-in accounts only. Free.
List the pages of a site — Lists every page of a site (home first) with its path, name, draft preview URL and live URL. Use the path as the page parameter of edit_section, add_section, list_sections and the version tools. Free.
Remove a page from a site — Removes one page (not the home page) from your site, using the dashboard's recoverable delete: a version is saved first and the page can be restored. Signed-in accounts only. Free.
Replace a page with new HTML — Re-imports ONE page (the home page too) from new HTML, in place: same address, same share link, same place in the page order, and a version is saved first so it can be undone. Use it to refresh a page built earlier. stage:true previews it before it goes live. Free.
Buy the domain for a live build (code prowess) — Operator token only, during a "code prowess" build the owner authorized with a spending cap. Buys ONE domain for the business through our registrar (owner-paid; no customer charge), points it at the server and starts HTTPS. Use dry_run first to compare endings. Exact business name within the cap beats a cheaper near-miss. Auto-renew stays off. Then publish_site and poll publish_status.
Check whether a domain is live — For a domain your site uses: does DNS point at our server, is the HTTPS certificate in place, and does the page answer? live:true means a visitor can open https://<domain> now. A fresh domain usually takes 5-15 minutes; poll every 20-30 seconds.
Record a review of one exact site version — Reviewer token only. Records pass or revise for one exact version of a site (from list_reviews). The operator token can publish only a version whose latest review is a pass; any edit makes a new version.
List reviews and the current reviewable versions — For one site: whether publishing with the operator token needs a review (enforced), the current draft and staged versions (what record_review must name), and the reviews recorded so far, newest first.
Check a published site the way a visitor and a crawler see it — For a published domain of your site: https root 200, http and www reach https://<domain>/ in one hop, title/description/og tags name the site, og:image is a 1200x630 PNG/JPEG, the favicon is the site's own, no editor leftovers, outbound links answer, exactly one h1, no draft badge. Returns PASS/WARN/FAIL per check. stored:true returns the automatic report made about two minutes after publish_site.
List a site's undo history — Lists a site's saved versions, newest first - version_id, why it was saved, its label, whether an AI edit made it (ai: true), and when. Every edit_section and set_theme call saves the page first, so any AI edit can be undone with restore_version. Free, and no account is needed for a draft you created.
Restore a saved version (undo) — Puts a site back to a version from list_versions - the undo button for AI edits. The current page is saved as a version first, so a restore can itself be undone. Free, and no account is needed for a draft you created.
Import an image (hosted copy) — Copies a photo from a public URL (e.g. the business's own website) into Pagetool's image store and returns its hosted url. Use that url in content_json (hero/about/card/gallery image), in edit_section src, or in <img src> for create_site_from_html - external image URLs are otherwise dropped. JPEG, PNG, WebP, GIF or AVIF up to 10 MB; resized to 1600px WebP and safety-checked. No public URL (e.g. photos the owner took)? Send data_base64 instead - downscale large photos first. Counts against the si
Save the client record for a site — Saves who a site is for and where things stand: business name, contact name/email/phone, the source pages its facts came from, status (prospect, pitched, managed, declined, transferred_out) and notes. Only the fields you pass change; null clears one. list_sites shows each site's record.
Create a one-time site transfer link — Creates a one-time link that hands a managed site to a departing client: they sign in or sign up and accept, and the site (and, by default, its domain) moves to their account. The link works once and expires at expires_at; creating a new one cancels the previous one. Signed-in accounts only.
Make staged changes live — Makes a site's staged changes (edit_section/set_theme with stage: true) live. The live page is saved as a version first, so this can be undone with restore_version. Free.
Drop staged changes — Drops a site's staged changes without touching the live site. Free.
Repaint a site's theme — Repaints the palette and fonts of an existing site across every section without touching its content or structure - the tool for make it warmer, darker, more corporate. At least one of palette_primary, palette_neutral, font_heading, font_body is required. Free, and no account is needed for a draft you created.
Get a site's preview URL — Returns the shareable preview URL for a site, plus its expiry. The create tools already return this URL, so call this only when you need it again later. Free, and no account is needed for a draft you created. Drafts are kept for 7 days from creation.
Showing the first 25 tools — full list and schemas: Directory API.
MCPBundles probed 41 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does Weinerandballs require?
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.