Custom Actions:
Turn conversations into action
Securely connect to 1000s of tools and perform actions using your answer agents — create tickets, book meetings, update your CRM.
Trusted by teams at 10,000+ organizations
Why Custom Actions matter
Agents limited to answering questions can’t take real-world action, leaving teams stuck with manual steps, wasted time, and disconnected workflows.
-
Easily connect to MCP (Model Context Protocol), a universal adaptor that connects to thousands of tools and databases. With this, you can perform 1000s of context-aware custom actions — book calls, check orders, update records, or trigger workflows — securely and seamlessly, while staying grounded in your knowledge.
From Answers to action
-
Execute tasks confidently while staying grounded in accurate knowledge
-
Maintain data security and business accuracy with fast, frictionless action
-
Connect to 1000s of systems with no limits through seamless integrations
How to get started
Simply copy-paste the URL of any remote MCP server, and watch your agent transform from an information provider into a problem solver. No complex integrations. No months of development. Just real actions, real results, in minutes.
Business impact
Business impact of Custom Actions
-
Support
- Get fresh, real-time information beyond your knowledge base
- Pull live shipping updates from ERP and inform customers instantly
- Create support tickets in Jira or GitHub with instant ticket numbers
- Reduce manual troubleshooting steps and resolve issues faster
-
Sales & Marketing
- Book meetings directly into your calendar during conversations
- Update CRM records instantly — create contacts and track actions
- Trigger personalized email sequences in real time
- Eliminate bottlenecks in daily processes with automation
-
Engineering & Product
- Connect to over 7,000 apps through Zapier MCP integrations
- Integrate seamlessly with any system that has an MCP server
- Scale secure, agentic problem-solving across workflows
- Enable team collaboration to improve productivity and speed
Why organizations choose CustomGPT.ai
Enterprise-grade data security
Data Use & Responsibility
Trusted answers
Actions you trust
-
Accuracy
Actions triggered based on your accurate information.
-
Compliance-friendly
Clear controls for what agents can and can’t do.
Plans & pricing
Custom Actions are available on CustomGPT.ai plans
Frequently asked questions
What exactly is an MCP server, and why do I need one to use Custom Actions?
An MCP (Model Context Protocol) server is a standardized bridge that connects AI agents to external tools and data sources. Instead of building custom integrations for each AI platform, MCP provides a universal protocol that works across different AI applications, including CustomGPT.ai.
The key benefit is modularity and reusability – one MCP server can provide tools for database queries, API interactions, file access, or specialized computations, and any MCP-compatible AI can use it. When connected, the AI sees these tools, understands how to use them, and can call them as needed during conversations. This keeps the AI focused on reasoning while delegating specific actions to purpose-built tools, making it easy to extend AI capabilities without modifying the AI application itself.
How is a “Custom Action” different from a regular knowledge‑base query or document lookup?
A knowledge‑base query retrieves or synthesizes information that already exists inside CustomGPT.ai.A Custom Action is user‑defined code that executes outside CustomGPT.ai – creating, updating, or retrieving live data in your own systems. In short, KB = read‑only insight; Action = read‑write execution.
Real‑world examples of what agents can now do
- Book a discovery call directly into your Calendly‑like scheduling system.
- Open a support ticket in Jira, Zendesk, or ServiceNow and return the ticket number.
- Check an order’s shipping status in your ERP and notify the customer in real time.
- Trigger a personalized email sequence via your marketing automation platform.
- Approve an expense in a finance app once the user confirms the amount.
How does this compare to competitors’ MCP actions and connectors?
Most platforms (ChatGPT, Claude, Zapier Actions, N8N, LangChain Tools) let you connect MCP server to their agent and use it within your organizations. CustomGPT.ai Custom Actions go one step further: you can package the agent itself – complete with its actions – and let your customers or website visitors use it. For example, embed an agent on your site so prospects can both chat and book a call with you in a single conversation, all powered by your MCP server.
Where in the dashboard do I create, edit, or delete Custom Actions?
Navigate to Agent › Actions. The page lists existing actions and an Add Action button for new ones.
What information or credentials do I need to connect my MCP server?
At launch we support:
- Public endpoints (no auth)
- API‑key / token header
- OAuth 2.0 (client‑ID / secret + scopes)
Is there a sandbox or staging environment to test actions before they go live?
Yes. After registering an action you can chat with the agent in the app using test prompts before exposing it to end‑users.
Can a single agent connect to multiple MCP servers, and is there a limit?
Initially, one agent → one MCP server. Multi‑server support is on our roadmap.
Does the agent automatically decide when to invoke a Custom Action?
The agent selects the appropriate action, but it pauses and asks the user for approval (summary of intent + inputs). You can optionally disable this confirmation for a fully autonomous flow.
Do Custom Actions inherit my existing SOC 2 / GDPR compliance posture within CustomGPT.ai?
All data that passes through CustomGPT.ai remains covered by our SOC 2 Type II controls and GDPR tooling. Anything processed only on your MCP server is your responsibility to secure and audit.
What happens if the MCP server is compromised – are there rate limits, timeouts, or other safeguards?
If the agent detects a failed or suspicious response it will gracefully decline: “Sorry, I can’t complete that action right now.” We also enforce reasonable timeouts and retry caps.
Is there logging or an audit trail of every action invocation?
Yes. Each call is written to the Action Logs tab with timestamp, user, parameters, response, and status.
Does invoking a Custom Action consume the same token quota as a standard chat completion?
No. Each action call counts as two standard queries – one to decide and one to process the result.