Deploy Claude-generated websites to EliteSpec hosting in one tool call. An MCP (Model Context Protocol) server for Claude Code and Claude Desktop.
npm install -g @elitespec/claude-host
elitespec-host install # prints Claude config JSON to paste
elitespec-host login # one-time authRelated MCP server: Nippy
Once installed in Claude, the model can call:
deploy_site(name, files, industry?) — ship a static site to <slug>.elitespec.co.nz
update_site(siteId, files) — push changes to an already-deployed site
list_sites() — list the user's hosted sites
Example conversation:
User: Make me a landing page for my Auckland bakery.
Claude: (writes HTML, CSS, JS in the conversation)
User: Publish it.
Claude: (calls
deploy_sitewith the files)
Free tier: <slug>.elitespec.co.nz subdomain, up to 3 sites.
$9/mo: custom domain, unlimited sites, no EliteSpec branding.
$29/mo: everything above plus Forge AI upgrades (rewrite copy, add pages, stock photos matched to your industry).
Full docs at https://forge.elitespec.co.nz/docs/claude-host
Your Claude Code session never sees your password. Login is handled by the CLI and stores a token at ~/.elitespec/host.json.
MIT
Deploy a static website to EliteSpec hosting. Returns a live URL on *.elitespec.co.nz. Use this when the user has a website (HTML + CSS + JS + images) ready to go live. Works best for landing pages, small business sites, and portfolios. First deploy requires a one-time EliteSpec account (free tier available).
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| files | Yes | ||
| industry | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions that the tool returns a live URL and requires an account for first deploy, but it does not clarify if the tool overwrites an existing deployment with the same name, what happens on failure, or any rate limits. The behavioral traits are partially revealed but leave gaps.
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 three sentences long, front-loads the core purpose in the first sentence, and then provides contextual usage and account info. Every sentence adds value without redundancy or unnecessary detail.
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?
Given the complexity (3 params, no output schema, no annotations), the description does not fully equip the agent. It omits parameter semantics, does not describe the return format beyond 'live URL', and does not mention error handling or idempotency. The tool's purpose is clear, but the surrounding context for execution is lacking.
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?
The schema has 3 parameters (name, files, industry) with 0% description coverage. The description does not elaborate on what any of these parameters mean—e.g., what the 'name' field represents, how the 'files' object is structured (path-to-content mapping), or the purpose of 'industry'. Without this, the agent cannot confidently populate the parameters.
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 clearly states the verb 'deploy', the resource 'static website to EliteSpec hosting', and the outcome 'returns a live URL on *.elitespec.co.nz'. It distinctly sets the tool apart from its siblings list_sites and update_site, which are for listing and updating existing sites respectively.
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?
The description explicitly says when to use the tool: when the user has a website (HTML+CSS+JS+images) ready to go live. It also mentions ideal use cases (landing pages, small business sites, portfolios) and a prerequisite (one-time EliteSpec account). However, it does not explicitly state when not to use it or name alternatives, which would be helpful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the authenticated user's hosted sites on EliteSpec.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It implies authentication is needed ('authenticated user') but does not disclose rate limits, data freshness, or error scenarios. Adequate for a simple read operation.
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?
Single sentence that is front-loaded and concise. No unnecessary words. Perfectly sized for the tool's simplicity.
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?
Given no output schema and simple nature, description is mostly complete. It could optionally mention what each site entry contains, but not required.
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?
No parameters exist in the schema (0 params, 100% coverage), so baseline 4 applies. Description adds no parameter info, which is acceptable.
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 clearly specifies the action 'list', the resource 'sites', and the scope 'authenticated user's hosted sites on EliteSpec'. It distinguishes from siblings 'deploy_site' and 'update_site' by using a read-only verb.
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?
No guidance on when to use this tool versus alternatives (deploy_site, update_site). No explicit when-not or context for usage beyond the basic action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Push updated files to an existing EliteSpec-hosted site. Only files in the payload are overwritten; other files remain.
| Name | Required | Description | Default |
|---|---|---|---|
| siteId | Yes | ||
| files | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behavior (only payload files overwritten), but no annotations exist. Lacks details on auth, error handling, or idempotency.
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?
Two concise sentences, front-loaded with purpose, no wasted words.
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?
Covers basic functionality for a simple update tool, but missing output schema and error case info; adequate given low complexity.
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?
With 0% schema coverage, description does not explain parameters beyond schema; 'files' object format and 'siteId' are not elaborated.
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?
Description clearly states verb 'Push updated files' and resource 'EliteSpec-hosted site', and distinguishes behavior from siblings (e.g., deploy_site likely for initial deploy).
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?
Implies use for updating existing site files, but no explicit when-to-use/alternatives guidance. Sibling names provide context but not directly in description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0deploy_sitelist_sitesupdate_siteEach tool targets a distinct operation: deploying a new site, listing existing sites, and updating a site. There is no ambiguity or overlap between them.
All tool names follow a consistent verb_noun pattern in snake_case: deploy_site, list_sites, update_site. The naming is uniform and predictable.
With 3 tools, the server covers the core lifecycle for static site hosting (deploy, list, update), which is appropriate for the domain. A delete operation is missing but does not severely impact the count.
The tool surface covers deploy, list, and update, but lacks a delete operation for removing hosted sites. This is a notable gap for a hosting service, as agents may need to clean up old sites.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Turn Claude or ChatGPT into a website builder that ships a real site to a live URL you own.
Build, clone & publish websites by chatting with Claude. Live in seconds, custom domains + SSL.
Talk to Claude and get a live web app deployed to a real URL, with Postgres, storage and cron.
Deploy static sites from AI agents: deploy_site publishes files and returns a live URL in seconds.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Elitespec/claude-host'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
