Build with

Overview

Voiceflow integrates with MuleSoft so your AI agent can call an approved Mule API and answer order questions with the result returned by your business service. MuleSoft runs the external workflow; Voiceflow calls its approved endpoint and uses the response in the conversation.

Examples of when to use MuleSoft

Studio

Use an editable test project in Agent studio. Your integration developer or administrator prepares the service below, supplies its endpoint and credentials, and gives you a verified test request plus its expected result. Keep provider-side deployment with that owner.

Code

Use a Voiceflow personal or service key with project access, a current Voiceflow CLI and the selected test Environment. You prepare the provider service and create, execute and attach the Voiceflow request separately. The examples use a test project; they can read or change connected systems.

Connecting MuleSoft

Prepare a deployed endpoint and the credentials for its approved operation.

Prepare the provider service

Studio

Ask your MuleSoft administrator or integration developer to complete the service setup linked below. Obtain all four handoff items before creating the Voiceflow tool:

  • The deployed HTTPS endpoint and its exact authentication headers.
  • The credential value for the Voiceflow Secret and the approved client ID.
  • A request schema, response schema and verified test customer/resource.
  • A successful test response and a rejected unauthorized request, confirmed in the provider’s execution history.

The sample request fields on this page are a recipe contract for your existing workflow. Have the owner map them to that workflow; a provider account alone does not create this endpoint.

Code

1

Expose the approved business flow

Your Mule integration developer starts with an existing order lookup flow. Add an HTTP Listener for POST /orders/status, accept JSON strings customer_id and order_id, and invoke that existing flow. HTTP Listener places the request body in payload; the business flow must validate the authenticated caller’s access to that order. The path is this recipe’s deployed application contract, not an Anypoint management endpoint.

2

Return the business result

Map the completed lookup to JSON containing order_id, status and estimated_delivery. Configure error responses for invalid or unauthorized requests. HTTP Listener ordinarily returns the final payload when the flow finishes; if the flow queues background work instead, define a pending receipt and a separate status/notification route before connecting it to the agent.

3

Protect and deploy the API

Deploy the application behind HTTPS using your organization’s Mule runtime and gateway. In API Manager, apply Client ID Enforcement to the managed API. Configure its credential expressions to read the client_id and client_secret headers. Register a client application, request access to this API and approve its contract. A client ID alone is insufficient when the policy also requires the secret. Do not use an Anypoint account password or management bearer token here.

4

Deliver a verified endpoint

The developer supplies the public HTTPS URL, approved client ID/secret, request/response schema and a verified test customer/order pair. Confirm the deployed API rejects missing credentials and an unauthorized order, then returns the intended order under the approved contract. Keep upstream system connections, policy deployment and runtime operations with that developer.

Provider setup: HTTP Listener setup and responses and Mule Gateway Client ID Enforcement.

Create the Voiceflow request

Studio

1

Store the service credential

Open your test project in Agent studio, then More → Secrets. Create mulesoft_client_secret with the credential supplied by the service owner. Creating its default also writes Main’s Published value, so keep initial setup in a test project. If the selected Environment has a different Draft credential, set its Draft override too.

2

Create a request variable

Open More → Variables, create mulesoft_request with an empty default and ask your application developer to populate it with the prepared request. For a Studio Run test, temporarily set its default to the developer’s prepared test string in this isolated test project; backend runtime variables do not automatically populate Studio Run. Clear the default after that test.

3

Configure the API request

Open Agent → Global tools → + → API and name the tool Check an order through MuleSoft. Choose POST, set the owner-supplied endpoint and add the headers below. Set the raw JSON body to {payload}.

Configure the deployed MuleSoft endpoint and its request fields. Photo:
4

Bind inputs before running

Open the attached tool’s inputs. Open authorization and set its Default value to the Secret mulesoft_client_secret, and set payload’s Default value to mulesoft_request. Bind client_id to the fixed approved application ID supplied by your administrator. Keep Async execution off so the agent receives this call’s response. The provider workflow may still return a pending receipt.

Code

Set VF_TOKEN, PROJECT_ID and ENVIRONMENT for the test project. Set PROVIDER_CREDENTIAL to the API client secret. The service owner supplies PROVIDER_URL and MULE_CLIENT_ID plus the verified test request.

Save this definition as mulesoft-tool.json, replacing the illustrative URL with PROVIDER_URL. Braced names declare inputs on this API tool; they are bound to Secrets/variables on its attachment later.

Save apiTool.id as API_TOOL_ID, then discover input IDs:

Creating the Secret default also writes Main’s Published value. If your selected Environment uses a different credential, set its Draft override before testing. Match each variables[].name to its id for the attachment; resolve unresolvedReferences before continuing.

Check an order through MuleSoft

Provide a verified request and use the result from the current call.

Invoke Check an order through MuleSoft when the customer asks where their order is. The authenticated application supplies the verified identity and prepared request variable before the call; keep those inputs bound to trusted defaults. Use the returned order ID, delivery status and estimated delivery only after confirming they belong to the requested order. For a pending result, explain that work is waiting. For a current failure or missing required fields, say the result could not be confirmed; never reuse an earlier result or automatically repeat an uncertain write.

Prepare the request

Code

The application developer builds the request from an authenticated customer/resource and the confirmed task. Save this illustrative body as mulesoft-request.json, replacing test identities with values the application has verified:

Serialize it with the literal-safe request encoder: node encode-request.mjs mulesoft-request.json > mulesoft-payload.txt. It preserves quotes, newlines and literal text such as {customer_name} without treating that text as a Voiceflow variable or Secret. Do not concatenate customer text into quoted JSON placeholders.

Studio

Have your developer deliver the encoded string and populate mulesoft_request in the authenticated client’s next action before this tool runs. They send variables on the runtime action; creating the variable or session alone does not fill it. For Studio Run, use the temporary test default described above, then clear it. The provider service must enforce customer access and validate the request; tool descriptions do not enforce either.

Code

Read the confirmed body, encode it, and build standalone inputs. This tests the saved request against the selected Environment’s Draft; it does not attach the tool or publish the agent.

Require success: true, inspect output.status and output.body, and check the business fields against the service owner’s response schema. truncated: true means the returned body is incomplete. On timeout or error, inspect provider execution before retrying a write.

Let the agent use the request

Studio

1

Describe the trigger and result use

Open the attached Check an order through MuleSoft tool and set Trigger to the condition below. Its input defaults must already point to the Secret and prepared request variable; the model must not collect credentials or choose another customer’s identifier.

2

Test the conversation

In Run, use the verified test request. Ask “Where is my order?” and confirm the intended tool runs with the fixed identity and prepared payload. Inspect the current tool result in Run and compare it with the order in the business system. Also test the rejected-resource case: the agent must not claim success or expose another customer’s data.

Code

Save this as mulesoft-attachment.json. Replace YOUR_API_TOOL_ID and each input ID with the values discovered above. Replace YOUR_APPROVED_CLIENT_ID with the approved fixed ID. The payload and credential are defaults, not model-collected inputs.

Your authenticated backend supplies the encoded payload as variables.mulesoft_request on the next runtime action. Use a test client bound to this project’s Draft, ask for the order status and inspect the emitted tool call, current response and agent answer. Verify both the successful and rejected-resource cases. The backend/provider enforces access; the description is model guidance, not an authorization gate.

The attached API tool returns the provider body to the agent. For a Workflow’s Capture response, paths start at that body: for example status rather than standalone output.body.status. A missing capture can leave an earlier variable value unchanged; clear result variables before a Workflow call and branch on the current HTTP/business outcome. These Global tool examples use the current result directly.

Maintaining the connection

Inspect provider execution, update credentials and test the intended deployment.

Replace a credential

1

Inspect the original provider execution

Use the request ID and execution time to find the provider run and its downstream record. A timeout can follow a completed side effect; reconcile that state before repeating a write.

2

Update the intended credential version

Studio

Open the same project and More → Secrets, select the provider Secret and update the target Environment’s Draft value for testing. After validation, explicitly set the Published value for the intended Environment; this changes the credential serving live traffic.

Code

Retain secret.id from creation as SECRET_ID, set PROVIDER_CREDENTIAL to the replacement and use the value operation below. After validation, explicitly set the Published value for the intended Environment; this changes the credential serving live traffic.

Code

Save the Draft update body as credential-value.json:

For the selected Environment’s Published credential, change versionVariant to published after the Draft test. To replace the project default, omit environmentAlias and versionVariant; this also writes Main’s Published value. Test the intended connection before changing a live default.

Before launch, select the target Environment and supply the provider Secret’s Default value for its published agent; a Draft override alone does not supply Published. Publish the tested configuration, then repeat the conversation test against that Environment’s published client and verify the provider account/resource it reaches.

Rotate the credential with the provider owner, update the relevant Secret default/Environment overrides, and retest the existing tool. Removing a tool from Voiceflow does not remove the provider deployment or revoke its credential. Disable/revoke access in MuleSoft when retiring the integration, then remove the unused attachment and API resource.

Use the up and down arrow keys to select a result, Enter to open it, and Escape to close the search.