Cabgo Builder

cabgo_create_trial

Public (no auth): create a Cabgo tenant in TRIAL state — no payment required up-front. Returns companyId + activationUrl + welcome email confirmation. NEW: pass presetId (taxi_classic | delivery_food | delivery_gas) to bootstrap branding + services + zones + tariffs + module toggles in the SAME call — no need to call apply_preset separately. Pass triggerBuild:'android' to also queue an APK in the same call. Cash-only is the default: the tenant lands with cashEnabled=true, so if the operator only wants to operate in cash they don't need to call cabgo_configure_payment_provider at all. Trial duration: 14 days. Required: ownerEmail (use whatever the operator already gave you in chat — don't re-ask), companyName.

Input Schema

TableJSON Schema

Name	Required	Description
`plan`	No	BASIC \| PROFESSIONAL \| ENTERPRISE — hint for activation Stripe Checkout.
`phone`	No	WhatsApp / phone in international +E.164 format.
`source`	No	Free-form attribution label, e.g. 'chatgpt-app'.
`appName`	No	Brand for the mobile app — falls back to companyName.
`appPlan`	No	STARTER \| PRO \| FULL — hint for activation Stripe Checkout.
`country`	No	ISO-3166-1 alpha-2 lowercased, e.g. 'mx', 'ar'. Optional — defaults are picked based on the operator's chat context.
`logoUrl`	No	Publicly-accessible image URL for the logo.
`presetId`	No	If set, the preset is applied server-side right after tenant creation (branding + services + zones + tariffs + toggles).
`ownerName`	No	Operator's name (optional but recommended).
`ownerEmail`	Yes	Operator's email. Re-use what they already told you in chat — don't ask twice. Becomes COMPANY_ADMIN of the new tenant.
`companyName`	Yes	Display name of the company (rider-facing). e.g. 'Taxi Express Tucumán'.
`primaryColor`	No	Brand primary color in hex.
`productLines`	No
`triggerBuild`	No	Pass true or 'android' to queue an Android build in the same call. The APK link arrives via the trial reminder email or cabgo_get_build.
`presetContext`	No	Overrides for the preset: { centerLat, centerLng, radiusKm, primaryColor, appName }. centerLat/Lng default 0,0 (no map geometry) unless provided.
`secondaryColor`	No	Brand secondary color in hex.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes

TDQS

A4.3/5.0

Behavior4/5

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

Discloses key behaviors: public no-auth, trial state, returns companyId+activationUrl+email, 14-day duration, cash-only default. Annotations already indicate readOnlyHint=false and openWorldHint=true; description adds specific side effects like welcome email and APK queuing. No contradictions.

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?

Front-loaded with key purpose and auth status. Uses bold for emphasis and bullet-style phrasing. Some redundancy (e.g., repeated 'Re-use from chat') but still efficient for the complexity. Could be slightly shorter but well-organized.

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?

Given 16 parameters, nested objects, and output schema, description covers essential aspects: no auth, trial state, return values, new features, defaults. Output schema exists for return details. Lacks info on error conditions but otherwise complete.

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?

With 94% schema coverage, baseline is 3. Description adds value by explaining ownerEmail reuse, presetId enum values and their effect, triggerBuild usage, and cash-only default. This helps the agent understand parameter purpose beyond schema.

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?

Clearly states it creates a Cabgo tenant in TRIAL state with no payment upfront. Distinguishes from sibling tools like cabgo_create_my_app (likely for production) and cabgo_pricing by focusing on trial creation and mentions new features (presetId, triggerBuild).

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 when-to-use context (creating a trial tenant) and guidelines like not needing to call apply_preset separately if presetId is provided, and cash-only default avoids payment provider setup. Lacks explicit when-not-to-use but sibling set makes it clear.

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

All Cabgo Builder tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each tool has a distinct purpose: about, create app, create trial, publish requirements, install instructions, pricing, and signup. Even though cabgo_create_my_app and cabgo_create_trial both create tenants, their descriptions clearly differentiate them by context (free workspace vs trial) and intended use (immediate app creation vs trial configuration).

Naming Consistency4/5

All tools use the 'cabgo_' prefix consistently and mostly follow a verb_noun pattern (e.g., create_my_app, create_trial, get_publish_requirements). Two tools (cabgo_about, cabgo_pricing) are nouns rather than verbs, but this is a minor deviation that does not hinder comprehension.

Tool Count5/5

With 7 tools, the server is well-scoped. The count is sufficient to cover the core onboarding workflow without being overwhelming or insufficient for the stated purpose of helping users launch and publish their app.

Completeness3/5

The tool set covers the initial lifecycle (info, creation in two modes, publishing requirements, installation, pricing, and legacy signup). However, there are no tools for post-creation management (e.g., updating app settings, managing drivers, viewing analytics), which leaves notable gaps for ongoing operations.

Resources

Need Help?