MuleSoft Documentation

https://github.com/mulesoft/docs-general
Admin
MuleSoft Documentation provides comprehensive guides for building APIs, managing integrations, and...
Tokens:144,070
Snippets:1,280
Trust Score:9.8
License:Apache-2.0
Update:3 weeks ago
Show doc for...
Tokens:
Raw
### Chat Completions API Examples

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Examples of chat completion requests with tool calling and structured output validation.

```APIDOC
## [POST] /chat/completions

### Description
This endpoint handles chat completion requests with tool calling and semantic routing. It allows the model to call functions like `get_current_time` based on user queries.

### Method
POST

### Endpoint
`<public-endpoint>/<base-path>/chat/completions`

### Parameters
#### Headers
- **Content-Type** (string) - Required - Must be `application/json`.
- **client_id** (string) - Required - Client ID for authentication.
- **client_secret** (string) - Required - Client secret for authentication.

#### Request Body
- **tool_choice** (string) - Optional - Controls tool selection. Example: `"auto"`.
- **messages** (array) - Required - List of message objects with `role` and `content`.
- **tools** (array) - Optional - List of tool definitions, each with `type` and `function`.

### Request Example
```json
{
  "tool_choice": "auto",
  "messages": [
    { "role": "user", "content": "What is the time in San Francisco?" },
    {
      "role": "assistant",
      "content": null,
      "tool_calls": [
        {
          "id": "call_KDrTKkRTGfylhkAO4A8s0pAO",
          "type": "function",
          "function": {
            "name": "get_current_time",
            "arguments": "{\"timezone\":\"America/Los_Angeles\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "tool_call_id": "call_KDrTKkRTGfylhkAO4A8s0pAO",
      "content": "2026-02-20T05:02:05.873534-08:00"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_time",
        "parameters": {
          "type": "object",
          "properties": { "timezone": { "type": "string" } },
          "required": ["timezone"]
        }
      }
    }
  ]
}
```

### Response
#### Success Response (200)
No response schema is provided in the source.

#### Response Example
No response example is provided in the source.
```

```APIDOC
## [POST] /chat/completions

### Description
This endpoint handles chat completion requests with tool calling and model-based routing. It allows specifying a model and using tools for function calling.

### Method
POST

### Endpoint
`<public-endpoint>/<base-path>/chat/completions`

### Parameters
#### Headers
- **Content-Type** (string) - Required - Must be `application/json`.
- **client_id** (string) - Required - Client ID for authentication.
- **client_secret** (string) - Required - Client secret for authentication.

#### Request Body
- **model** (string) - Optional - Model identifier, e.g., `openai/gpt-5.2`.
- **tool_choice** (string) - Optional - Controls tool selection. Example: `"auto"`.
- **messages** (array) - Required - List of message objects with `role` and `content`.
- **tools** (array) - Optional - List of tool definitions, each with `type` and `function`.

### Request Example
```json
{
  "model": "openai/gpt-5.2",
  "tool_choice": "auto",
  "messages": [
    { "role": "user", "content": "What is the time in San Francisco?" },
    {
      "role": "assistant",
      "content": null,
      "tool_calls": [
        {
          "id": "call_KDrTKkRTGfylhkAO4A8s0pAO",
          "type": "function",
          "function": {
            "name": "get_current_time",
            "arguments": "{\"timezone\":\"America/Los_Angeles\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "tool_call_id": "call_KDrTKkRTGfylhkAO4A8s0pAO",
      "content": "2026-02-20T05:02:05.873534-08:00"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_time",
        "parameters": {
          "type": "object",
          "properties": { "timezone": { "type": "string" } },
          "required": ["timezone"]
        }
      }
    }
  ]
}
```

### Response
#### Success Response (200)
No response schema is provided in the source.

#### Response Example
No response example is provided in the source.
```

```APIDOC
## [POST] /chat/completions

### Description
This endpoint handles chat completion requests with structured output validation using a JSON Schema. It validates entity extraction into a defined schema, preventing integration errors.

### Method
POST

### Endpoint
`<public-endpoint>/<base-path>/chat/completions`

### Parameters
#### Headers
- **Content-Type** (string) - Required - Must be `application/json`.
- **client_id** (string) - Required - Client ID for authentication.
- **client_secret** (string) - Required - Client secret for authentication.

#### Request Body
- **messages** (array) - Required - List of message objects with `role` and `content`.
- **response_format** (object) - Optional - Specifies the response format, including `type` and `json_schema`.

### Request Example
```json
{
  "messages": [
    { "role": "system", "content": "Extract the event information." },
    { "role": "user", "content": "Madhu Dileep and Santosh A are going to a AI Summit on 19th Feb 2026." }
  ],
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "name": "CalendarEvent",
      "schema": {
        "type": "object",
        "properties": {
          "name": { "type": "string", "description": "Name of the event" },
          "date": { "type": "string", "description": "Date of the event, in MM-DD-YYYY format" },
          "participants": { "type": "array", "items": { "type": "string" } }
        },
        "required": ["name", "date", "participants"]
      }
    }
  }
}
```

### Response
#### Success Response (200)
No response schema is provided in the source.

#### Response Example
No response example is provided in the source.
```

```APIDOC
## [POST] /chat/completions

### Description
This endpoint handles chat completion requests with structured output validation using a JSON Schema and model-based routing. It validates entity extraction into a defined schema.

### Method
POST

### Endpoint
`<public-endpoint>/<base-path>/chat/completions`

### Parameters
#### Headers
- **Content-Type** (string) - Required - Must be `application/json`.
- **client_id** (string) - Required - Client ID for authentication.
- **client_secret** (string) - Required - Client secret for authentication.

#### Request Body
- **model** (string) - Optional - Model identifier, e.g., `gemini/gemini-3-flash-preview`.
- **messages** (array) - Required - List of message objects with `role` and `content`.
- **response_format** (object) - Optional - Specifies the response format, including `type` and `json_schema`.

### Request Example
```json
{
  "model": "gemini/gemini-3-flash-preview",
  "messages": [
    { "role": "system", "content": "Extract the event information." },
    { "role": "user", "content": "Madhu Dileep and Santosh A are going to a AI Summit on 19th Feb 2026." }
  ],
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "name": "CalendarEvent",
      "schema": {
        "type": "object",
        "properties": {
          "name": { "type": "string", "description": "Name of the event" },
          "date": { "type": "string", "description": "Date of the event, in MM-DD-YYYY format" },
          "participants": { "type": "array", "items": { "type": "string" } }
        },
        "required": ["name", "date", "participants"]
      }
    }
  }
}
```

### Response
#### Success Response (200)
No response schema is provided in the source.

#### Response Example
No response example is provided in the source.
```

--------------------------------

### Example LLM provider asset (llm-metadata.json)

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-publish-custom-llm-metadata.adoc

Complete JSON file for an LLM provider asset. Includes platform name, input format, authentication, models, default URL, and capabilities. Save this as llm-metadata.json.

```json
{
  "platform": "Geminiano",
  "name": "Geminiano",
  "inputFormat": "gemini",
  "kind": "llm-gw",
  "authentication": [
    {
      "kind": "apiKey",
      "defaultConfiguration": {
        "headerName": "X-goog-api-key",
        "headersToRemove": ["Authorization"]
      }
    }
  ],
  "models": ["gemini-2.5-flash"],
  "defaultUrl": [
    {
      "name": "default",
      "url": "https://generativelanguage.googleapis.com/v1beta/"
    }
  ],
  "capabilities": {
    "toolCalling": true,
    "structuredOutput": true,
    "imageInput": true,
    "pdfInput": true,
    "reasoning": {
      "supported": true
    }
  }
}
```

--------------------------------

### Model definition with capabilities and pricing

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-publish-custom-llm-metadata.adoc

JSON structure for defining a model with detailed metadata including capabilities, pricing, and lifecycle. The example shows a model with reasoning support and three effort levels.

```json
{
  "models": [
    "gemini-2.5-flash",
    {
      "id": "gemini-2.5-pro",
      "label": "Gemini 2.5 Pro",
      "description": "A multimodal model for complex reasoning tasks.",
      "limits": {
        "maxInputTokens": 1000000,
        "maxOutputTokens": 8192,
        "supportsPromptCaching": true,
        "maxCachedTokens": 500000
      },
      "capabilities": {
        "toolCalling": true,
        "structuredOutput": true,
        "imageInput": true,
        "reasoning": {
          "supported": true,
          "type": "adaptive",
          "effortLevels": ["low", "medium", "high"]
        }
      },
      "pricing": {
        "inputPerMillion": 1.25,
        "outputPerMillion": 5.0,
        "cachedInputPerMillion": 0.3125,
        "reasoningPerMillion": 5.0
      },
      "lifecycle": {
        "status": "active",
        "releasedAt": "2025-03-25T00:00:00Z",
        "sunsetAt": null
      }
    }
  ]
}
```

--------------------------------

### Test API URL

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/api-led-operate.adoc

Example URL to test the API from any device. Replace your-app-url with your actual application URL. Visiting this URL in a browser returns the greeting message.

```text
https://your-app-url.cloudhub.io/api/greeting?name=World
```

--------------------------------

### Streaming API Call Example (Anthropic)

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Streaming request to the Anthropic provider using the `--no-buffer` flag to enable real-time non-buffered token delivery.

```cli
curl --location '<public-endpoint>/<base-path>/v1/messages' \
  --header 'Content-Type: application/json' \
  --header 'anthropic-version: 2023-06-01' \
  --header 'client_id: <client-id>' \
  --header 'client_secret: <client-secret>' \
  --data '{
    "model": "claude-opus-4-1-20250805",
    "max_tokens": 2048,
    "stream": true,
    "messages": [
      { "role": "user", "content": "Explain step-by-step MuleSoft integration process" }
    ]
  }' \
  --no-buffer
```

--------------------------------

### Gemini Format Basic Chat Completion Example

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Basic chat completion example for the Gemini format. It ensures the gateway correctly routes traffic to the Gemini provider. Note that the Gemini format does not support multi-routing or fallback mechanisms.

```cli
curl --location '<public-endpoint>/<base-path>/models/gemini-2.5-flash:generateContent' \
  --header 'Content-Type: application/json' \
  --header 'client_id: <client-id>' \
  --header 'client_secret: <client-secret>' \
  --data '{
    "contents": [
      { "role": "user", "parts": [{ "text": "Hello, please introduce yourself" }] }
    ]
  }'
```

--------------------------------

### Model-Based Routing: Structured Output with gemini/gemini-3-flash-preview

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Same structured output example as the Semantic Routing variant but explicitly selects the model gemini/gemini-3-flash-preview. Use this when you want to force a specific model instead of relying on semantic routing.

```cli
curl --location '<public-endpoint>/<base-path>/chat/completions' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "model": "gemini/gemini-3-flash-preview",
  "messages": [
    { "role": "system", "content": "Extract the event information." },
    { "role": "user", "content": "Madhu Dileep and Santosh A are going to a AI Summit on 19th Feb 2026." }
  ],
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "name": "CalendarEvent",
      "schema": {
        "type": "object",
        "properties": {
          "name": { "type": "string", "description": "Name of the event" },
          "date": { "type": "string", "description": "Date of the event, in MM-DD-YYYY format" },
          "participants": { "type": "array", "items": { "type": "string" } }
        },
        "required": ["name", "date", "participants"]
      }
    }
  }
}'
```

--------------------------------

### APIkit Router Flow Example

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/_partials/mule-runtime-metrics.adoc

Example of an APIkit router flow that handles a GET request in the /reservation path. This flow is billable because it is used for routing APIkit requests.

```xml
<flow name="get:\reservation:cocheras-puerto-madero-api-config">
        <logger level="INFO" message="#[output json --- attributes.queryParams]" />
</flow>
```

--------------------------------

### Read and create tool surface pattern

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/af-use-case-mcp-bridge.adoc

Exposes GET and POST operations for agents that look up and create records but do not modify or delete.

```text
(exposed) GET    /resource/{id}
(exposed) POST   /resource
(not exposed) PUT    /resource/{id}
(not exposed) DELETE /resource/{id}
```

--------------------------------

### Streaming API Call Example (Gemini)

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Streaming request to the Gemini endpoint using the `streamGenerateContent` method with `alt=sse` and the `--no-buffer` flag to enable real-time token delivery.

```cli
curl --location '<public-endpoint>/<base-path>/models/gemini-2.5-flash:streamGenerateContent?alt=sse' \
  --header 'Content-Type: application/json' \
  --header 'client_id: <client-id>' \
  --header 'client_secret: <client-secret>' \
  --data '{
    "contents": [
      { "role": "user", "parts": [{ "text": "Explain step-by-step MuleSoft integration process" }] }
    ]
  }' \
  --no-buffer
```

--------------------------------

### Model-Based Routing: Tool Call with openai/gpt-5.2

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Same tool-call example as the Semantic Routing variant but explicitly selects the model openai/gpt-5.2. Use this when you want to force a specific model instead of relying on semantic routing.

```cli
curl --location '<public-endpoint>/<base-path>/chat/completions' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "model": "openai/gpt-5.2",
  "tool_choice": "auto",
  "messages": [
    { "role": "user", "content": "What is the time in San Francisco?" },
    {
      "role": "assistant",
      "content": null,
      "tool_calls": [
        {
          "id": "call_KDrTKkRTGfylhkAO4A8s0pAO",
          "type": "function",
          "function": {
            "name": "get_current_time",
            "arguments": "{\"timezone\":\"America/Los_Angeles\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "tool_call_id": "call_KDrTKkRTGfylhkAO4A8s0pAO",
      "content": "2026-02-20T05:02:05.873534-08:00"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_time",
        "parameters": {
          "type": "object",
          "properties": { "timezone": { "type": "string" } },
          "required": ["timezone"]
        }
      }
    }
  ]
}'
```

--------------------------------

### Reasoning capabilities object

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-publish-custom-llm-metadata.adoc

JSON snippet showing how to declare reasoning support within the capabilities object. The example sets supported to true, type to adaptive, and lists accepted effort levels.

```json
"capabilities": {
  "reasoning": {
    "supported": true,
    "type": "adaptive",
    "effortLevels": ["low", "medium", "high"]
  }
}
```

--------------------------------

### Basic Chat Completion Example (Anthropic)

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Basic chat completion request to the Anthropic provider using the native Anthropic API format. This format does not support multi-routing or fallback mechanisms.

```cli
curl --location '<public-endpoint>/<base-path>/v1/messages' \
  --header 'Content-Type: application/json' \
  --header 'anthropic-version: 2023-06-01' \
  --header 'client_id: <client-id>' \
  --header 'client_secret: <client-secret>' \
  --data '{
    "model": "claude-opus-4-1-20250805",
    "max_tokens": 1024,
    "system": "You are a helpful assistant",
    "messages": [
      { "role": "user", "content": "Hello, please introduce yourself" }
    ]
  }'
```

--------------------------------

### Runtime Manager Log Entry

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/api-led-operate.adoc

Example log entry shown in Runtime Manager after sending a request to the API. The log level is INFO and the message includes the application name, flow, and the greeting request.

```text
INFO  [hello-world-impl].get:\greeting  Received greeting request for name: World
```

--------------------------------

### Streaming Chat Completions Request with --no-buffer

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Streaming API call examples for real-time token delivery. Both use the '--no-buffer' flag to stream non-buffered tokens. The first uses semantic routing, the second uses model-based routing with 'gemini/gemini-3-flash-preview'. Suitable for chatbot UIs where text appears word-by-word.

```cli
curl --location '<public-endpoint>/<base-path>/chat/completions' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "messages": [
    { "role": "user", "content": "Explain step-by-step MuleSoft integration process" }
  ],
  "stream": true
}' \
--no-buffer
```

```cli
curl --location '<public-endpoint>/<base-path>/chat/completions' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "model": "gemini/gemini-3-flash-preview",
  "messages": [
    { "role": "user", "content": "Explain step-by-step MuleSoft integration process" }
  ],
  "stream": true
}' \
--no-buffer
```

--------------------------------

### Responses Endpoint with MCP Tools (Semantic and Model-Based Routing)

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Integrates the gateway with an external MCP server for automated action execution. The example asks an AI agent to search a specific internal Knowledge Base or update a Jira ticket using standardized tools defined on a remote MCP server. The Semantic Routing variant omits the model field, while the Model-Based Routing variant explicitly sets "model": "openai/gpt-5.2".

```cli
curl --location '<public-endpoint>/<base-path>/responses' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "input": [
    { "role": "system", "content": "You are helpful Service Agent" },
    { "role": "user", "content": "My Laptop screen is broken" }
  ],
  "tools": [
    {
      "type": "mcp",
      "server_label": "service_mcp",
      "require_approval": "never",
      "server_description": "Server enabled to do Service related actions",
      "server_url": "https://ask-service-mcp-dvaz3u.c87dy0.usa-e2.cloudhub.io/mcp"
    }
  ]
}'
```

```cli
curl --location '<public-endpoint>/<base-path>/responses' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "model": "openai/gpt-5.2",
  "input": [
    { "role": "system", "content": "You are helpful Service Agent" },
    { "role": "user", "content": "My Laptop screen is broken" }
  ],
  "tools": [
    {
      "type": "mcp",
      "server_label": "service_mcp",
      "require_approval": "never",
      "server_description": "Server enabled to do Service related actions",
      "server_url": "https://ask-service-mcp-dvaz3u.c87dy0.usa-e2.cloudhub.io/mcp"
    }
  ]
}'
```

--------------------------------

### Review API Spec with Callouts

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/api-led-design.adoc

Review the API spec with callout markers <1> through <4> identifying the endpoint path, required query parameter, HTTP responses, and the JSON response property. The endpoint is /greeting, and clients send GET requests to it.

```yaml
openapi: 3.0.0
info:
  title: hello-world-api
  version: 1.0.0
paths:
  /greeting: <1>
    get:
      parameters: <2>
        - name: name
          in: query
          required: true
          schema:
            type: string
          description: The name to greet
      responses: <3>
        '200':
          description: Success
          content:
            application/json:
              schema:
                type: object
                properties:
                  message: <4>
                    type: string
                    example: "Hello, World!"
```

--------------------------------

### Run MTF tests against Java 17

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/_partials/partner-and-customer-guide.adoc

Test your custom connector against Java 17. Set MUNIT_JVM to your Java 17 JVM installation and JAVA_HOME to Java 8. Requires Mule runtime 4.6.0 or later.

```bash
#!/bin/bash
RUNTIME_VERSION=4.6.0
MUNIT_JVM=/Library/Java/JavaVirtualMachines/temurin-17.jdk/Contents/Home/bin/java
mvn clean
mkdir target
mvn verify \
   -DruntimeProduct=MULE_EE \
   -DruntimeVersion=$RUNTIME_VERSION \
   -Dmunit.jvm=$MUNIT_JVM \
   -Dmule.module.tweaking.validation.skip=true \
   -Dmule.jvm.version.extension.enforcement=LOOSE > ./target/test.log
```

--------------------------------

### Check Provider Version Availability with curl

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-publish-custom-llm-metadata.adoc

Sends a GET request to the Exchange API to check if a specific asset version exists. Expect HTTP 404 for available, HTTP 200 for existing, and HTTP 401/403 for authorization issues.

```bash
curl --silent --show-error \
  --output /dev/null \
  --write-out 'HTTP %{http_code}\n' \
  --header "Authorization: Bearer $ANYPOINT_TOKEN" \
  "https://anypoint.mulesoft.com/exchange/api/v2/assets/$GROUP_ID/$ASSET_ID/$ASSET_VERSION"
```

--------------------------------

### Ask MuleSoft Agent: List instances on staging gateway

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/exp-ai-assistant-use.adoc

Use this natural language prompt to ask the MuleSoft Agent to list instances deployed to the staging gateway.

```text
What instances are deployed to the staging gateway?
```

--------------------------------

### GET request to local API

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/api-led-test.adoc

Send a GET request to the locally running Mule app with the name query parameter. The expected response is a JSON object with a message field.

```text
http://localhost:8081/api/greeting?name=World
```

--------------------------------

### deploy_ch2.json configuration

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/api-led-deploy.adoc

Deployment configuration file created by Anypoint Code Builder. Contains runtime version, application name, replicas, replica size, deployment model, autoStart, and ObjectStoreV2 settings.

```json
{
  "runtime": "4.x.x",
  "applicationName": "hello-world-impl-vh",
  "replicas": 1,
  "replicaSize": "0.1",
  "deploymentModel": "rolling",
  "autoStart": true,
  "ObjectStoreV2": true
}
```

--------------------------------

### Read-only tool surface pattern

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/af-use-case-mcp-bridge.adoc

Exposes all GET operations and excludes write operations for agents that only retrieve data.

```text
(exposed) GET    /resource/{id}
(exposed) GET    /resource
(not exposed) POST   /resource
(not exposed) PUT    /resource/{id}
(not exposed) DELETE /resource/{id}
```

--------------------------------

### Tool Calling Initial Request with get_current_time Function

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Initial tool calling requests that define a 'get_current_time' function and ask the model to invoke it. The first uses semantic routing, the second uses model-based routing with 'openai/gpt-5.2'. Both set 'tool_choice' to 'auto' so the model can decide to call the tool.

```cli
curl --location '<public-endpoint>/<base-path>/chat/completions' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "tool_choice": "auto",
  "messages": [
    { "role": "user", "content": "What is the time in San Francisco?" }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_time",
        "description": "When user asks for time tell me to invoke this Tool",
        "parameters": {
          "type": "object",
          "properties": {
            "timezone": { "type": "string", "description": "Timezone of the user asked location" }
          },
          "required": ["timezone"]
        }
      }
    }
  ]
}'
```

```cli
curl --location '<public-endpoint>/<base-path>/chat/completions' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "model": "openai/gpt-5.2",
  "tool_choice": "auto",
  "messages": [
    { "role": "user", "content": "What is the time in San Francisco?" }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_time",
        "description": "When user asks for time tell me to invoke this Tool",
        "parameters": {
          "type": "object",
          "properties": {
            "timezone": { "type": "string", "description": "Timezone of the user asked location" }
          },
          "required": ["timezone"]
        }
      }
    }
  ]
}'
```

--------------------------------

### Read and request-only tool surface pattern

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/af-use-case-mcp-bridge.adoc

Exposes GET and a specific POST request endpoint for agents that initiate workflows without modifying records.

```text
(exposed) GET    /resource/{id}
(exposed) POST   /resource/request
(not exposed) PUT    /resource/{id}
(not exposed) DELETE /resource/{id}
```

--------------------------------

### Ask MuleSoft Agent: Show active governance strategies

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/exp-ai-assistant-use.adoc

Use this natural language prompt to ask the MuleSoft Agent to show active governance strategies.

```text
What governance strategies are active?
```

--------------------------------

### Ask MuleSoft Agent: Create governance strategy

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/exp-ai-assistant-use.adoc

Use this natural language prompt to ask the MuleSoft Agent for guidance on creating a new governance strategy.

```text
How do I create a new governance strategy?
```

--------------------------------

### Ask MuleSoft Agent: Find MCP servers with payment tools

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/exp-ai-assistant-use.adoc

Use this natural language prompt to ask the MuleSoft Agent to find MCP servers that expose payment-related tools.

```text
Find MCP servers that expose payment tools
```

--------------------------------

### Non-Billable Flow with Logger Component

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/_partials/mule-runtime-metrics.adoc

Example of a Mule flow that does not have an event source and is not used for routing APIkit requests, so it does not count against the Anypoint Platform package allotment. This flow only contains a logger component.

```xml
2.a - Flow with only a logger component
<flow name="just-logging">
        <logger level="INFO" message="#[output json --- attributes.queryParams]" />
</flow>
```

--------------------------------

### Application URL Structure

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/api-led-operate.adoc

Structure of the application URL. Replace hello-world-impl-jsmith with your unique application name and <space-domain> with your Shared Space's domain. The URL is publicly accessible and includes HTTPS/TLS, load balancing, DDoS protection, and automatic scaling.

```text
https://hello-world-impl-jsmith.<space-domain>.cloudhub.io/api/greeting
```

--------------------------------

### Amazon Bedrock Model Name Format

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Amazon Bedrock Claude models must be specified in Amazon Resource Name (ARN) format. The first example shows a concrete ARN, and the second shows the general format.

```text
bedrockanthropic/us.anthropic.claude-sonnet-4-5-20250929-v1:0
```

```text
bedrockanthropic/<region>.anthropic.<model-rd>
```

--------------------------------

### Create hello-world-api.yaml API Spec

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/api-led-design.adoc

Replace the template content in hello-world-api.yaml with this OAS 3.0 API spec. It defines a GET /greeting endpoint with a required name query parameter and a 200 response containing a message property.

```yaml
openapi: 3.0.0
info:
  title: hello-world-api
  version: 1.0.0
paths:
  /greeting:
    get:
      parameters:
        - name: name
          in: query
          required: true
          schema:
            type: string
          description: The name to greet
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    example: "Hello, World!"
```

--------------------------------

### Run MTF tests with --illegal-access=deny

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/_partials/partner-and-customer-guide.adoc

Run MTF tests with the --illegal-access=deny parameter. Replace RUNTIME_VERSION with the latest Mule runtime version available. After running, check target/illegal-access.log for classes or dependencies that misbehave.

```bash
#!/bin/bash
RUNTIME_VERSION=4.6.0
MUNIT_JVM=/Library/Java/JavaVirtualMachines/adoptopenjdk-11.jdk/Contents/Home/bin/java
mvn clean
mkdir target 
mvn verify \
    -DruntimeProduct=MULE_EE \
    -DruntimeVersion=$RUNTIME_VERSION \
    -Dmunit.jvm=$MUNIT_JVM \
    -Dmtf.javaopts="--illegal-access=deny" > ./target/test.log
```

--------------------------------

### Creative Content Generation with Temperature Control

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/model-proxy-request.adoc

Two curl requests for creative content generation with temperature set to 1.5. The first uses semantic routing (no model specified), the second uses model-based routing with 'gemini/gemini-3-flash-preview'. Higher temperature values increase creativity.

```cli
curl --location '<public-endpoint>/<base-path>/chat/completions' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "messages": [
    { "role": "user", "content": "Write a creative story about AI" }
  ],
  "temperature": 1.5
}'
```

```cli
curl --location '<public-endpoint>/<base-path>/chat/completions' \
--header 'Content-Type: application/json' \
--header 'client_id: <client-id>' \
--header 'client_secret: <client-secret>' \
--data '{
  "model": "gemini/gemini-3-flash-preview",
  "messages": [
    { "role": "user", "content": "Write a creative story about AI" }
  ],
  "temperature": 1.5
}'
```

--------------------------------

### Define MySQL JDBC Driver as External Library

Source: https://github.com/mulesoft/docs-general/blob/latest/modules/ROOT/pages/_partials/partner-and-customer-guide.adoc

Use this @ExternalLib annotation to define the MySQL JDBC Driver as an external library for your custom connector, specifying the jar name regex, required class, and Maven coordinates. Update the coordinates to a version compatible with Java 17. The source shows a partial example (with a placeholder) that you must complete.

```java
@ExternalLib(name = "MySQL JDBC Driver",
  description = "A JDBC driver that supports connection to the MySQL Database",
  nameRegexpMatcher = "(.*)\\.jar",
  requiredClassName = "com.mysql.jdbc.Driver",
  coordinates = "mysql:mysql-connector-java:5.1.44")
public class MySqlConnectionProvider implements ConnectionProvider<Connection> {
  //
}
```
Tokens:
Raw