neuron

Publish Site

neuron_sites_publish

Publish a static site (HTML/CSS/JS/images/fonts/PDF/video) and get its link. Creates a new site when siteId is omitted, otherwise redeploys to the same URL — the link and access settings survive and the previous version stays available for rollback. Pass exactly one source: dir (local folder, e.g. the output of a build), zipPath (local .zip), html (a single page), or files ([{path, base64}]). New sites start Restricted (only you). Use neuron_sites_set_access to share. Only changed files are uploaded on redeploy. A new site is reviewed by Neuron once; until approved (reviewStatus), visitors can't open it. Its address (label) is fixed for life.

Input Schema

TableJSON Schema

Name	Required	Description
`dir`	No	Local folder to publish (local MCP only). index.html at its root opens first.
`html`	No	A single HTML page; becomes index.html.
`mode`	No	'replace' (default): the source IS the whole site. 'patch' (needs siteId): start from the live version; the source's files add/replace those paths, `delete` removes paths, everything else carries over. Use patch for a one-file change.
`name`	No	Name for a new site (required when siteId is omitted).
`note`	No	Version note, e.g. 'Added pack 41'.
`files`	No	Files as base64 with relative paths.
`label`	No	Business plans: the address for a new site (<label>.<sites domain>). Lowercase letters, numbers, hyphens. Can't be changed later. Omit to get one generated.
`delete`	No	mode=patch only: site paths to remove, e.g. ['brand/old-logo.png'].
`siteId`	No	Existing site to redeploy. Omit to create a new site.
`zipPath`	No	Local .zip to publish (local MCP only). A single top-level folder is unwrapped.
`entryPath`	No	Page that opens at / when there's no index.html.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 7, 2026

addedInput schema / properties / delete

Added value: +{
+  "description": "mode=patch only: site paths to remove, e.g. ['brand/old-logo.png'].",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / mode

Added value: +{
+  "description": "'replace' (default): the source IS the whole site. 'patch' (needs siteId): start from the live version; the source's files add/replace those paths, `delete` removes paths, everything else carries over. Use patch for a one-file change.",
+  "enum": [
+    "replace",
+    "patch"
+  ],
+  "type": "string"
+}

AddedOct 7, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations are minimal (non-readOnly, open-world, non-idempotent, non-destructive), and the description adds substantial behavior an agent could not infer: new sites start Restricted, a one-time review gates visitor access via reviewStatus, the label is immutable, previous versions remain rollback-able, and only changed files upload on redeploy.

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?

Every sentence carries information (modes, source options, access default, review gate, incremental upload, immutability) and the core action is front-loaded in sentence one. It is dense and long for a single paragraph, but there is no filler to cut.

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 an 11-parameter mutation tool with no output schema, the description covers the important behavioral surface: creation vs redeploy, source constraints, default access, review gating, and the returned link. Minor gaps remain (failure modes, size limits, how to poll reviewStatus), but nothing essential for correct invocation is missing.

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?

Schema coverage is 100% so the baseline is 3, but the description adds the mutual-exclusion rule 'pass exactly one source: dir, zipPath, html, or files' and the patch/replace semantics, which the schema does not express as a constraint (no oneOf/anyOf). That is genuine value beyond the parameter descriptions.

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?

The description names a specific verb+resource ('Publish a static site') and immediately distinguishes the two modes of operation (new site vs redeploy to the same URL), which separates it from siblings like neuron_sites_update, neuron_sites_duplicate, and neuron_sites_rollback. An agent can tell exactly what this tool produces — a hosted site with a link.

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

Usage Guidelines4/5

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

It clearly states when to omit siteId (create) vs supply it (redeploy), and routes sharing to neuron_sites_set_access. It does not explicitly contrast against neuron_sites_update or neuron_sites_duplicate, so it stops short of full when-not guidance, but the context is concrete.

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

All neuron tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?