Skip to main content
Glama

thincms_create_tool

Create a new ThinCMS tool with custom HTML/JS, optional authentication, system prompt, and AI model configuration.

Instructions

Create a new Tool. html is the raw HTML/JS payload that renders inside a sandboxed iframe with a window.thinCMS runtime injected. Set authRequired to 'password' | 'google' | 'either' to gate access; 'none' makes the tool public. Set systemPrompt to prepend a persona to /ai/chat calls. For large HTML payloads (>10KB), use htmlFile with a local file path.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
htmlNoRaw HTML/JS payload
nameYesTool name (required)
slugNoURL slug (auto-generated from name if omitted)
siteIdNoOverride the active site for this single call. Pass to target a specific tenant without mutating shared active-site state — the right pattern when running concurrent agent sessions managing different tenants. Must match a siteId from your THINCMS_SITES config (use thincms_list_sites to inspect). When omitted, the call uses the active site set by thincms_switch_site.
statusNoPublish status (default: draft)
aiModelNoOverride site AI model for this tool (e.g. claude-sonnet-4-6)
enabledNoEnabled (default: true)
htmlFileNoLocal file path containing the HTML payload — use instead of html for large tools
rateLimitNoAI chat calls per end-user per hour (omit or null for unlimited)
allowSignupNoWhether the login screen offers self-signup (default: true)
descriptionNoShort description shown in admin UI
authRequiredNoAuth mode (default: none)
systemPromptNoDefault system prompt prepended to ai/chat calls
confirmProductionWriteNoAcknowledge that this call may write to a configured production site (THINCMS_PRODUCTION_SITE_IDS env var). Required for any POST/PUT/PATCH/DELETE against a production-listed site; ignored otherwise. The error message lists which site triggered the requirement and recommends thincms_snapshot before any production write.
Behavior3/5

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

No annotations provided, so the description carries the full burden. It discloses the sandboxed iframe behavior, auth gating, and systemPrompt usage. However, it omits side effects, permissions required, or whether the tool is immediately active. The description is adequate but not exhaustive.

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?

Four sentences with key information front-loaded. Every sentence adds value. Could be slightly more structured (e.g., bullet points) but remains clear and concise.

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

Completeness3/5

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

Covers the main behavioral aspects and key parameters, but missing return value description (no output schema) and does not mention sensitive parameters like `confirmProductionWrite`. For a 14-parameter tool, some details are omitted.

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 covers all parameters with descriptions. The description adds value by explaining the `html` parameter's rendering context, the meaning of `authRequired` values, and the purpose of `systemPrompt`. It also clarifies when to use `htmlFile`. This compensates for the high schema coverage.

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 starts with 'Create a new Tool' and explains the tool as an HTML/JS payload rendered in a sandboxed iframe. It clearly distinguishes the create operation from other tool actions by specifying the verb and resource.

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?

Provides explicit guidance on when to use `htmlFile` instead of `html` for large payloads and describes the auth options. Lacks explicit when-not-to-use or alternatives among siblings, but since it's the only create tool, the context is sufficient.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pmccarroll-fuel/thincms-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server