catalystbyzoho/agent-skills

catalyst-zoho-mcp

Catalyst Zoho MCP — manage Catalyst infrastructure (tables, buckets, cache) via CatalystbyZoho MCP tools using natural language.

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/catalystbyzoho/agent-skills --skill catalyst-zoho-mcp

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

How It Works

  1. Check if MCP is connected — Look for CatalystbyZoho_* tools in your tool list.
  1. MCP NOT connected — HARD STOP.

Do NOT write any code, create any files, or call any SDK. Ask the user which setup path they prefer, then load references/zoho-mcp.md and follow only that path. Do not proceed to step 3 until the user confirms CatalystbyZoho_* tools are visible in their client.

To work with Catalyst via MCP, choose your setup path: Option A — Global MCP Server (recommended) Add your DC-specific URL to your AI client config, authorize once via browser, done. No console needed. US: https://catalyst.zohomcp.com/mcp/message, EU: https://catalyst.zohomcp.eu/mcp/message, IN: https://catalyst.zohomcp.in/mcp/message, AU: https://catalyst.zohomcp.com.au/mcp/message, CA: https://catalyst.zohomcp.ca/mcp/message, SA: https://catalyst.zohomcp.sa/mcp/message, JP: https://catalyst.zohomcp.jp/mcp/message, UAE: https://catalyst.zohomcp.ae/mcp/message. Option B — Personal MCP Server (custom/team setup) Create your own server at mcp.zoho.com, select tools, get a personal URL with a token embedded. Which would you prefer?
  1. Pre-flight sequence — In order:
  • Confirm DC first. Wrong DC = empty org list. Use /catalyst-by-zoho:switch-dc to switch data centers if CatalystbyZoho_List_All_Organizations returns empty or the wrong org.
  • Run CatalystbyZoho_List_All_Organizations → CatalystbyZoho_List_All_Projects to set project context before any other MCP tool call.
  1. Load `references/zoho-mcp.md` — for the full tool catalog, execution flow, and common error fixes.
  2. If the query involves DataStore (create table, add columns, query data) — also load references/mcp-datastore.md.
  3. Answer — Call the appropriate CatalystbyZoho_* tool directly. Show the user what tool was called and what it returned.

Triggers

Use this skill for: "Zoho MCP", "MCP tools", "catalyst MCP", "create table with AI", "MCP DataStore", "MCP Cache", "MCP Stratus", zoho-mcp-server, "MCP setup", "MCP config", "global MCP server", "infrastructure as conversation", "Claude MCP Catalyst", "MCP tool error", "MCP not connecting", "use AI to create database table", or CatalystbyZoho_ tool.

References

ReferenceLoad when the query is about…
references/zoho-mcp.mdGlobal MCP server setup (all 3 clients), all available CatalystbyZoho_* tools, execution flow, org→project pre-flight sequence, common MCP errors
references/mcp-datastore.mdCreating tables/columns via MCP, DataStore column types, batch column creation, data type constraints

Related by task

from this repository

More skills

All skills
catalystbyzoho
Community

catalyst-by-zoho

Expert coding assistant for Catalyst by Zoho — Zoho's full-stack serverless cloud platform. Use for any question about Catalyst services, CLI, SDKs, architecture, pricing, or Zoho MCP tool-based infrastructure management.

installs
1
GitHub stars
69
Updated
Oct 8
catalystbyzoho
Community

catalyst-cache

Catalyst Cache — in-memory key-value store with TTL for ephemeral session and temporary data. Trigger on 'Cache', 'cache segment', 'cache key', 'TTL', 'segment.put', 'segment.get', or 'temporary data Catalyst'.

installs
1
GitHub stars
69
Updated
Oct 8
catalystbyzoho
Community

catalyst-quickml

Catalyst QuickML — no/low-code ML, Generative AI, and ready-to-use AI platform. Covers (1) Prediction: ML pipelines, classification/regression, text analytics, recommendation, forecasting, clustering, anomaly detection, AutoML, prediction endpoints; (2) Generative AI: LLM Serving (chat, VLM), RAG, Knowledge Base, GenAI endpoints; (3) Zia Model Library: pre-built no-training models; (4) QuickML pricing — subscription plans and pay-as-you-go rates. Trigger on 'QuickML', 'AutoML', 'ML pipeline', 't

installs
1
GitHub stars
69
Updated
Oct 8
catalystbyzoho
Community

catalyst-zia

Catalyst Zia Services — OCR, Face Analytics, Text Analytics, Object Detection, Barcode Reader, and Content Moderation via pre-trained AI APIs. Trigger on 'Zia', 'OCR', 'face detection', 'text analytics', 'object detection', 'barcode', 'content moderation', or 'image recognition'. DC restrictions: Identity Scanner Document Processing is IN DC only (API included); Facial Comparison works via API from any DC (console testing is IN DC only). For QuickML (AutoML, ML pipelines, LLM Serving, RAG) load

installs
1
GitHub stars
69
Updated
Oct 8