Flowershow
Server Details
Publish Markdown and HTML from your AI session as a live website. No account needed.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- flowershow/flowershow
- GitHub Stars
- 1,108
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of confusing it with another. Its purpose (publishing files as a live site) is stated unambiguously.
A single, clear action verb 'publish' that directly matches the domain. No mixed conventions exist because there is only one name.
One tool is thin in absolute terms, but it is a rich, well-scoped operation that absorbs create, update, and delete-adjacent behaviors via parameters. It fits a narrowly focused publishing service rather than feeling like an extreme mismatch.
Lifecycle coverage is strong: create, incremental update, deletion of files, and whole-site replacement are all handled, plus error/confirmation flows. Minor gaps remain—no read/list/status tool to inspect current site contents or expiry without republishing.
Available Tools
1 toolpublishPublish to FlowershowADestructiveInspect
Publish files as a live website on Flowershow and get a shareable URL. Use when the user says "publish this", "put this online", "make this a website", "share this as a page" or "host this".
Accepts Markdown (.md, rendered as a styled page with navigation), HTML (.html, served as-is) and supporting files such as CSS, JS, JSON and images: one page or a small site, up to 50 files and 3 MB per call. Name the home page index.md or index.html.
Without an account this creates a new site that expires in 7 days and returns a claim link: always show the user the live URL and the claim link exactly as returned, so they can keep the site. To update that site later in the conversation, call publish again with its siteId and claimToken and only the files you changed or added: files you don't send are kept as they are. To remove pages or files, list their paths in delete (files can then be empty). Only when the user explicitly asks to start the site over, set replaceWholeSite to true: the files you send become the whole site and every other file is removed. If that would remove existing files, the call is refused and tells you how many and which; ask the user, then call again with confirmDeleteCount set to that number. For bigger sites, suggest the Flowershow CLI (fl).
| Name | Required | Description | Default |
|---|---|---|---|
| files | Yes | Files to add or update. When updating a site, send only the files that changed; other files are kept. Can be empty when only deleting. | |
| delete | No | Paths of existing files to remove from the site (with siteId), e.g. ["old-page.md"] | |
| siteId | No | Update this existing site instead of creating a new one | |
| claimToken | No | The claimToken returned when the anonymous site was created (needed with siteId when not signed in) | |
| replaceWholeSite | No | Set true only when the user asks to start the site over: the files sent become the whole site and all other files are permanently removed. Never use it to update a few pages. Default false. | |
| confirmDeleteCount | No | With replaceWholeSite: the number of existing files the replace will remove, as reported by the refused first call. Set it only after the user has confirmed. |
Output Schema
| Name | Required | Description |
|---|---|---|
| siteId | Yes | |
| liveUrl | Yes | |
| message | Yes | |
| claimUrl | No | |
| expiresAt | No | |
| claimToken | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds substantial behavior beyond the annotations: anonymous sites expire in 7 days, a claim link must be shown, files not resent are kept, delete paths remove files, replaceWholeSite is destructive, and a refusal/confirmDeleteCount confirmation flow guards against accidental mass deletion. These details are consistent with destructiveHint=true and openWorldHint=true, and they materially improve safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but front-loaded: the first sentence states the action and the second gives trigger examples. The remaining paragraphs are dense with operational rules that earn their place, with no filler or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex, destructive, open-world publishing tool, the description covers the full lifecycle: creating, sharing, claiming, updating, deleting, replacing, and escalating to the CLI. An output schema exists, so it does not need to explain return values, and nothing important appears absent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents each parameter. The description still adds meaningful workflow semantics: how siteId and claimToken work together, that only changed files should be sent on update, that files can be empty when deleting, and how replaceWholeSite and confirmDeleteCount interact. That goes beyond the schema, though the schema already carries the basic per-parameter definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: publish files as a live website on Flowershow and get a shareable URL. It distinguishes creation from updating by siteId and explains the output expectation, so an agent can tell exactly what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit trigger phrases ('publish this', 'put this online', 'host this') and clear conditions for updating an existing site, deleting files, replacing a whole site, and suggesting the CLI for larger sites. The when-to-use and when-not-to-use boundaries are unusually well specified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Changed
publish4 fields changed- added
Input schema / properties / confirmDeleteCountAdded value: +{ + "description": "With replaceWholeSite: the number of existing files the replace will remove, as reported by the refused first call. Set it only after the user has confirmed.", + "maximum": 9007199254740991, + "minimum": 0, + "type": "integer" +} - added
Input schema / properties / deleteAdded value: +{ + "description": "Paths of existing files to remove from the site (with siteId), e.g. [\"old-page.md\"]", + "items": { + "type": "string" + }, + "maxItems": 1000, + "type": "array" +} - changed
Input schema / properties / files / descriptionPrevious value: -"The complete set of site files"New value: +"Files to add or update. When updating a site, send only the files that changed; other files are kept. Can be empty when only deleting." - added
Input schema / properties / replaceWholeSiteAdded value: +{ + "description": "Set true only when the user asks to start the site over: the files sent become the whole site and all other files are permanently removed. Never use it to update a few pages. Default false.", + "type": "boolean" +}
1 tool update
- First observed
publish
Related MCP Connectors
Publish websites from your AI chat: pages, multi-file sites, ZIPs or templates, live in seconds.
Publish AI-generated HTML to a private, unguessable link, straight from Claude or ChatGPT.
- SwolvyOAuthcom.swolvy
Publish HTML from Claude, ChatGPT, Gemini or any MCP client and get a shareable link. No account.
- dropOAuthio.neuronik
Publish web pages straight from your AI assistant and share them with a link.
Related MCP Servers
AlicenseAqualityDmaintenanceEnables AI tools to publish HTML pages and get shareable URLs instantly, with optional account features for persistence, in-place updates, and visibility control.1MIT- AlicenseNot gradedqualityDmaintenancePublishes AI-generated HTML and Markdown to a hosted, shareable URL with versioning, theming, and access control.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to publish HTML or Markdown to a public URL with a single HTTP POST, automatically converting Markdown to a styled webpage, with no account or setup required.1 npm1MIT
- AlicenseNot gradedqualityDmaintenancePublish the website you built with AI to a live public URL — straight from chat, no setup. Enables deploying static sites and updating them with edit tokens.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.