Tools and Integrations
By default, your agent answers questions from your knowledge base. Tools let it do things too - look up an order, check a shipment, create a ticket, or call your own systems. You choose exactly which tools your agent can use on the Tools tab of the agent configuration page.
How Tools Work
When your agent is in a conversation, it decides - based on the visitor's question - whether a tool would help. If you have enabled a "look up order" tool, the agent can call it, read the result, and use it in its answer. You stay in control of which tools exist and what they are allowed to do.
The agent Tools tab showing the built-in tool catalog, the buttons to add custom API tools and presets, and the MCP servers section
Built-in Tools
DeskClone ships a catalog of safe, ready-to-use tools you can switch on with a single toggle. Common ones include:
- Search knowledge base - find relevant content to answer a question
- Read a file - open a specific knowledge base file
- Save a memory - remember a detail for later in the conversation
- Get the current time - useful for deadlines and "how long ago" questions
- List uploaded files - see the files and images a visitor attached in the chat
- Confirm resolution - mark a question as resolved
- Escalate to a human - hand off when the agent cannot resolve the request
- Execute resolution - perform a real resolution action (refund, replacement, credit) through one of your connected integrations, and confirm it to the visitor only from the integration's verified receipt
Each tool shows its risk as a badge - Read-only tools change nothing; Action tools take an action. You enable a tool with its toggle.
Execute resolution (verified actions)
Execute resolution is how a customer-facing agent takes real actions safely and honestly. Instead of exposing your raw integration tools (a refund endpoint, an order-creation endpoint) to the agent in visitor chats, you map friendly action names - like refund or replacement - to those tools. In the conversation the agent calls the action; DeskClone runs the real integration server-side with all your guardrails (amount limits, confidence thresholds, per-conversation caps) enforced, and hands the agent back a verified receipt of what actually happened.
Two honesty guarantees come with it:
- The agent confirms an action to the visitor only from the verified receipt - amounts and reference numbers come from your integration's actual response.
- If an action fails or is blocked, the agent must say plainly that it was not completed and bring in your team. DeskClone also checks every reply server-side: a reply claiming a completed action with no verified receipt behind it is corrected in place and the conversation is escalated to your team - a visitor is never left believing something happened when it didn't.
Configuration of the action mappings is operator-level today - reach out via Help and we'll set your actions up with you while the visual editor is being finished.
New agents start with a sensible default set, so they can answer from your knowledge base immediately.
Custom API Tools
Custom API tools connect your agent to your own systems. Point the agent at any HTTP endpoint and it can call it during a conversation.
Open the API Connections sub-tab
Go to Agents, click your agent card, open the Tools tab, and select the API Connections sub-tab.
Add a new API tool
In API Connections, add a new API tool. Give it a clear name and description - the description tells the agent when to use it.
Configure the request
Set the method (GET, POST, PUT, PATCH, or DELETE), the URL, and any path, query, or body parameters the agent should fill in.
Add authentication
Choose how the tool authenticates: bearer token, header key, basic username and password, or OAuth. Credentials are stored encrypted.
Test it
Use the Test button to send a sample request and confirm the connection works before going live.
Creating a custom API tool: give it an ID, name, endpoint, and method, and it's added to your agent.
Write the tool's description for the agent, not for yourself. "Look up the status of an order by its order number" tells the agent exactly when to reach for it. A vague description leads to the tool being used at the wrong time, or not at all.
Connection Presets
If you use a popular service, you do not have to wire it up by hand. Connection presets set up the right tools for you in a couple of clicks. Presets are available for:
- Zendesk - create and update tickets
- HubSpot - look up contacts, create and read tickets
- Salesforce - run lookups, create and update cases
- Shopify - look up orders and customers
- Stripe - check payments and issue refunds
- PayPal - check transactions
- Slack - post messages
- Jira - search, create, and comment on issues
- Linear - search, create, and comment on issues
- GitHub - read and create issues
- PagerDuty - page the on-call, create and read incidents
- Notion - read pages
- Calendly - check availability and bookings
Connecting a preset: Browse Presets, pick a service (Calendly here), paste the credential, and its tools are added to your agent.
Open API Connections
On the Tools tab, open the API Connections sub-tab.
Pick a service
Choose a connection preset for the service you want (for example, Shopify). Use the search box or the category filters (Support, CRM, Development, and so on) to find a service quickly.
Connect your account
Enter the credentials the service asks for (an API key, token, or OAuth login). Each field says where to find its value, and the form links to the credentials guide below. The relevant tools are added to your agent automatically.
Review the result
After connecting, DeskClone checks your credentials against the service and shows the outcome. The same screen tells you the new tools start out employee-only (your public widget will not use them yet) and offers one click to allow customer chats to use the read-only tools. Action tools stay employee-only - route those through Execute resolution.
Where to get each service's credentials
- Zendesk - API token: Admin Center → Apps and integrations → APIs. Connect with your Zendesk subdomain and agent email.
- HubSpot - private app access token: Settings → Integrations → Private Apps. Grant the contacts read and tickets read/write scopes.
- Salesforce - consumer key and secret: Setup → App Manager → New Connected App. Enable OAuth and the Client Credentials flow, and set a run-as user (that user's permissions decide what the agent can reach). Connect with your My Domain name.
- Shopify - Admin API access token: Apps → Develop apps → your app → API credentials.
- Stripe - restricted secret key: Dashboard → Developers → API keys. Restrict it to charges, customers, and refunds.
- PayPal - client ID and secret: developer.paypal.com → Apps & Credentials. Pick sandbox or production to match the environment you select in the form.
- Slack - bot token (xoxb-...): api.slack.com/apps → your app → OAuth & Permissions, then install the app to your workspace.
- Jira - API token: id.atlassian.com → Security → API tokens. Connect with your Atlassian site name and account email.
- Linear - personal API key: Settings → Security & access → Personal API keys.
- GitHub - fine-grained personal access token: Settings → Developer settings → Personal access tokens. Scope it to the repositories and permissions the agent needs.
- PagerDuty - REST API key: Integrations → API Access Keys. Also enter the email of a PagerDuty user; incidents the agent creates are attributed to them.
- Notion - integration token: notion.so/my-integrations. Share the pages or databases with the integration to grant access.
- Calendly - personal access token: Integrations → API & Webhooks.
MCP Servers
If you run a Model Context Protocol (MCP) server, you can connect it to expose its tools to your agent. From the Tools tab, open the MCP Servers sub-tab, add your server's URL and credentials, and DeskClone will list the tools it provides so you can enable the ones you want.
The Mock APIs sub-tab (visible under Tools) is coming soon. It will let you give a tool canned responses for testing, so you can try a tool's behavior before the real API is ready.
Risk Levels and Visibility
Every tool has a risk level, and DeskClone uses it to keep your public widget safe:
- Read-only - looks something up, changes nothing. Example: check an order status.
- Mutating - changes data. Example: update a ticket.
- Destructive - removes or irreversibly changes data. Example: issue a refund.
Customer-facing widget conversations are locked down by default. Public chats see read-only tools, the safe built-ins (like escalate to a human), and Execute resolution - the guarded action path described above. Your raw mutating and destructive tools are not offered to the agent in public chats unless you explicitly set a tool's visibility to include customers; the recommended pattern is to keep them employee-only and route customer actions through Execute resolution, so every action passes your guardrails and returns a verified receipt. Employee-assisted ticket work sees all risk levels, with the approval workflow adding another check on top.
On the Tools tab, any tool your public widget will not use carries a Not in customer chats badge, so you can see at a glance which tools are employee-only. Change a tool's availability from its settings (the gear icon on its row).
Guardrails
For any tool that moves money or changes customer data, set guardrails. A guardrail (for example, a maximum refund amount, or a required field) is enforced before the request is sent - so a cleverly worded message cannot talk your agent into exceeding it. When a guardrail blocks an action, the agent is told why and can escalate to a human instead of retrying.
Always set guardrails on financial and data-changing tools. Risk gating keeps these tools out of public chats, and guardrails cap what they can do even in employee-assisted work. Together they are your safety net.
Checking Tool Health
Once you have connected custom tools and presets, click Check credentials on the Tools tab to confirm each one's credentials still work. The check tells you which tools are healthy and which need attention (for example, an expired API key), so a broken integration does not surface as a failed answer to a customer.
You do not have to keep checking manually. If a connection's credentials are rejected during a real conversation (for example, an API key expires), DeskClone alerts you automatically:
- The account admin gets an email right away saying which tool failed, what the service returned, what it means for your agent, and the exact next step.
- The tool shows a red Needs reconnect badge on the Tools tab, with a summary banner at the top, until it works again.
- Affected conversations are handed to your team in the meantime - the agent never pretends an action worked while its connection is broken.
Update the credential and the alert clears automatically on the next successful call - there is nothing to dismiss.
What's Next
Your agent now has the knowledge and the actions it needs. Time to put it in front of visitors - head to Embed Widget to generate and install the chat widget.
Was this page helpful?