Skip to main content
Glama

Press5 launch pad

Deploy a static site

deploy_site

Publish a static website (HTML, CSS, JS, images) to the Press5 launch pad and get its live URL. Works with no account: without a token the site gets a random name, goes live at once, and the reply has a claim_url for the person to keep it (unclaimed sites are deleted after 3 days) and a site_key to redeploy the same site. With a token, "site" picks the name (3-42 lowercase letters, digits, hyphens; created the first time if free). Send every file of the built site; this replaces the whole site. Text files as plain content, binary files as base64 with encoding "base64". Best for small sites: for big builds use the HTTP API with a .tar.gz (see https://my.press5.xyz/llms.txt). To start from one of the free starter templates (list_templates), send "template" and optional "fields" instead of files.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "deploy_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
spaNoSingle-page app: serve index.html for unknown paths (client-side routing)
siteNoSite name, becomes <site>.on.press5.xyz. Needs a token; leave it out for a random name.
filesNo
tokenNoA press5 token (p5_...). Only needed when the MCP connection has no Authorization header, e.g. right after login_check.
fieldsNoWith template: the text to fill in, by field key, e.g. {"name": "Rosie's Café", "email": "hi@rosies.example"}.
site_keyNoThe site_key from an earlier deploy without an account, to update that same site.
templateNoInstead of files: the id of a starter template from list_templates, published as it is or with "fields" filled in.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / fields
      Added value: +{
      +  "additionalProperties": {
      +    "type": "string"
      +  },
      +  "description": "With template: the text to fill in, by field key, e.g. {\"name\": \"Rosie's Café\", \"email\": \"hi@rosies.example\"}.",
      +  "type": "object"
      +}
    • addedInput schema / properties / template
      Added value: +{
      +  "description": "Instead of files: the id of a starter template from list_templates, published as it is or with \"fields\" filled in.",
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "files"
      -]
  2. Changed3 schema fields changed
    • changedInput schema / properties / site / description
      Previous value: -"Site name, becomes <site>.on.press5.xyz"New value: +"Site name, becomes <site>.on.press5.xyz. Needs a token; leave it out for a random name."
    • addedInput schema / properties / site_key
      Added value: +{
      +  "description": "The site_key from an earlier deploy without an account, to update that same site.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "site",
      -  "files"
      -]New value: +[
      +  "files"
      +]
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds substantial behavior beyond the annotations: anonymous deploys get a random name, come with a claim_url, and unclaimed sites are deleted after 3 days; site_key enables redeploys; deployments replace the whole site. The "replaces the whole site" overwrite sits in mild tension with destructiveHint=false and idempotentHint=false, but it is disclosed rather than hidden, and the remaining disclosures are genuinely useful.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and outcome are front-loaded, then the token/no-token branches, then file-encoding rules, then the size caveat and template alternative. Every sentence carries information, though the block is dense and the HTTP-API pointer could be trimmed without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter, nested-object tool with no output schema, the description covers return values (live URL, claim_url, site_key), the anonymous vs. authenticated split, encoding rules, and replacement semantics. Minor gaps remain on the spa flag and on what happens when a token is present but the name is taken.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Coverage is already 86%, yet the description still adds meaning the schema lacks: "site" requires a token and follows naming constraints (3-42 chars, lowercase/digits/hyphens, created first time if free), site_key only applies to anonymous deploys, and template/fields are an alternative to files. It does not further explain spa or token lifecycle, so it stops short of the top score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Publish a static website (HTML, CSS, JS, images) to the Press5 launch pad and get its live URL" states a specific verb, resource, accepted artifact types, and the outcome. It is clearly distinguishable from siblings such as list_sites, delete_site, and rollback_site.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit routing rules: use this for small sites, but use the HTTP API with a .tar.gz for big builds; use "template" + "fields" (via list_templates) instead of files when starting from a starter; use site_key to redeploy an unclaimed site. It also states the token vs. no-token conditions that determine behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources