--- schema_version: "1" id: bdd180e98783ef576bd5b4d9a5f9ebcdfdb2926a6bce51ceaa273275618eeff5 title: A2A Connector 1.1 - Examples collection: mulesoft version: current locale: en-us portal_url: https://docs.salesforce.com/mulesoft/current/en-us/a2a-connector/1.1/a2a-connector-examples.md canonical_url: https://docs.mulesoft.com/a2a-connector/1.1/a2a-connector-examples source_site: docs.mulesoft.com content_type: documentation content_hash: e0a9825fc02776dd8cbbcd2afce9417fbcd8f714973a62617909f119999ef4ee description: MuleSoft Documentation Site release: "1.1" latest: false --- --- product: A2A Connector version: 1.1 --- # A2A Connector 1.1 - Examples > For the full documentation index, see: https://docs.mulesoft.com/llms.txt This A2A server configuration uses an agent card JSON file that contains metadata about the agent. Client A2A agents use this information to determine: - When to use the agent (based on description and skills) - Where to contact the agent (based on the url property) ## Configure an A2A Server This is an example A2A server configuration using an absolute path: ```xml ``` When deploying your application to CloudHub, absolute or relative local paths may not resolve correctly. To ensure the connector can locate your agent card in a deployed environment, use the `${app.home}` variable: ```xml ```
1a2a:server-config defines the A2A server configuration.
2a2a:connection specifies the path to use to listen for requests.
3a2a:agent-card specifies the agent card. Use the file attribute to point to the absolute path of the JSON file on disk. For CloudHub use cases, if the file is located in the home directory of the CloudHub instance, you can reference it using ${app.home}/agent-card.json.
## A2A Request Format When sending requests to the **A2A Server - Task Listener** source from external clients (such as Postman or other A2A agents), you must use the correct JSON-RPC format. Incorrectly formatted requests result in unmarshalling errors such as: ```text Error unmarshalling string json payload into type io.a2a.spec.SendMessageRequest. Cause: Invalid params ``` The minimum required JSON-RPC request format for the `message/send` method is: ```json { "jsonrpc": "2.0", "method": "message/send", "id": "test-001", "params": { "message": { "kind": "message", "messageId": "550e8400-e29b-41d4-a716-446655440000", "role": "user", "parts": [ { "kind": "text", "text": "Hello, this is my message" } ] } } } ``` You can use metadata types in Anypoint Studio to ensure your payloads conform to the A2A schema. The connector includes JSON schema definitions for `MessageSendParams` and other A2A objects. For additional schema references, see the [A2A Java SDK](https://github.com/a2aproject/a2a-java). ## Write a Listener That Receives the A2A Request This example shows how a listener is created. The user prompt that’s sent from the client agent is extracted to a variable `user_prompt`: ```xml ``` ### Example Response The response is formatted as an A2A task, which is then returned to the client: ```xml ``` ## Mule App Example This example shows how a financial A2A agent Mule app that can answer queries related to US companies and their financial standings listens to A2A requests and passes the user prompt to an LLM using MuleSoft Inference Connector. You can paste this code into the Studio XML editor to quickly load the flow for this example into your Mule app: ```xml #(1) #(2) #(3) #(4) #(5) #(6) #(7) #(8) #(9) ```
1The a2a:task-listener component acts as the entry point, waiting to receive a task from an A2A server. This task contains a user’s query about stock market data.
2The logger component outputs an informational message Triggering MCP Tools to the MuleSoft logs.
3The set-variable component extracts the ID from the incoming payload (the task received in step 1) and stores it in a flow variable named task_id.
4Another set-variable component extracts the sessionId from the payload. If sessionId isn’t present, it defaults to an empty string. This value is stored in a flow variable named session_id.
5This set-variable extracts the actual user query from the payload. Specifically, it takes the text from the first part of the message within the payload and stores it in a flow variable named user_prompt.
6The ms-inference:mcp-tools-native-template configures an LLM to act as a specialized financial analysis assistant.
7This set-variable component takes the response generated by the ms-inference:mcp-tools-native-template (from step 6) and stores it in a flow variable named mcp_tooling_results.
8The ms-inference:agent-define-prompt-template component processes the results from the previous AI interaction to generate a user-friendly response.
9The ee:transform (DataWeave transformation) component takes the payload.response from the previous AI interaction and transforms it into a structured JSON output.
## Configure the A2A Client to Call Other A2A Agents This minimal flow listens for an A2A task and forwards the same payload to a remote agent using your A2A client configuration. ```xml ``` ## Configure On Task Stream Listener (SSE) End to End Use this pattern when your A2A server must return incremental task updates through SSE (`message/stream`) instead of a single response (`message/send`). ### Server Configuration for Streaming Use the same HTTP listener and A2A server pattern as non-streaming setups, with an agent card path appropriate for your deployment (for example `${app.home}/agent-card.json` on CloudHub). ```xml ``` ### Streaming Flow Example The streaming process first emits a Task event, then emits intermediate status and artifact events, and finally closes the stream with a final status event. ```xml ``` ### Expected SSE Event Format The stream is delivered as standard server-sent events. Each event contains a JSON payload in `data:`. ```text event: task data: {"id":"task-123","contextId":"context-task-123","kind":"task","status":{"state":"working"},"final":false} event: artifact-update data: {"id":"task-123","contextId":"context-task-123","kind":"artifact-update","artifact":{"artifactId":"artifact-task-123","name":"partial-answer","parts":[{"kind":"text","text":"Here is an incremental result chunk."}]}} event: status-update data: {"id":"task-123","contextId":"context-task-123","kind":"status-update","status":{"state":"completed"},"final":true} ``` > [!NOTE] To close the SSE stream gracefully, set `final: true` on the last status update. If > `final` isn’t emitted, clients can remain subscribed waiting for additional events. ### Error Handling Pattern for Streaming Flows Wrap stream-processing logic in error handling and always send a terminal status update on failures: ```xml ``` ## JSON-RPC 2.0 Request and Response Patterns The snippets below illustrate JSON-RPC for `message/send` and `message/stream`, a sample completed-task result, and how fields map to Mule task payloads. ### Non-Streaming Request Clients send this when invoking `message/send` and expecting one task result (not an SSE stream). ```json { "jsonrpc": "2.0", "id": "req-1001", "method": "message/send", "params": { "message": { "kind": "message", "messageId": "550e8400-e29b-41d4-a716-446655440000", "role": "user", "parts": [ { "kind": "text", "text": "Summarize the latest task status." } ] } } } ``` ### Non-Streaming Response (Task Shape) The JSON-RPC `result` object follows the A2A task structure, including `status`, `artifacts`, and optional `history`. ```json { "jsonrpc": "2.0", "id": "req-1001", "result": { "id": "task-1001", "contextId": "context-task-1001", "kind": "task", "status": { "state": "completed" }, "artifacts": [ { "artifactId": "artifact-task-1001", "name": "answer", "parts": [ { "kind": "text", "text": "Task completed successfully." } ] } ], "history": [] } } ``` ### Streaming Request (`message/stream`) Clients use this method and parameters when they open an SSE stream and consume multiple task, artifact, and status events. ```json { "jsonrpc": "2.0", "id": "req-stream-2001", "method": "message/stream", "params": { "message": { "kind": "message", "messageId": "6f4e31f8-5a4d-4a54-9fa3-31c9c0d10a1b", "role": "user", "parts": [ { "kind": "text", "text": "Generate a step-by-step answer." } ] } } } ``` ### Mapping JSON-RPC Payload to `io.a2a.spec.Task` In server flows, Mule payload fields map directly to task structures: - `payload.id` maps to task ID. - `payload.contextId` maps to context ID. - `payload.message` carries the incoming user message. - `payload.message.parts` contains content segments for extraction (for example, `payload.message.parts[0].text`). - `payload.status` and `payload.artifacts` are used to build task updates in responses. ## Sample `agent-card.json` for Streaming and Push Notifications Use this sample as a starting point for cards that advertise both SSE streaming and push notification support: ```json { "name": "Finance Streaming Agent", "description": "Handles financial analysis tasks with streaming progress updates and push notifications.", "url": "https://example.org/a2a", "provider": { "organization": "Example Org" }, "version": "1.0.0", "capabilities": { "streaming": true, "pushNotifications": true }, "skills": [ { "id": "financial-analysis", "name": "Financial Analysis", "description": "Analyzes public company financial performance." } ], "defaultInputModes": ["text"], "defaultOutputModes": ["text"] } ``` ## Complete Mule App Example for Non-Streaming Tasks and Push Notifications Use this full example when you want request-response processing with `message/send` and optional push notification callbacks, without SSE streaming. > [!NOTE] This pattern complements, but does not replace, the > [Configure On Task Stream Listener (SSE) End to End](#configure-on-task-stream-listener-sse-end-to-end) > section. Use this section for non-streaming flows, and the SSE section for incremental stream > updates. ```xml ``` ## See Also - [A2A Connector Troubleshooting](https://docs.mulesoft.com/a2a-connector/1.1/a2a-connector-troubleshooting) - [A2A Connector Reference](https://docs.mulesoft.com/a2a-connector/1.1/a2a-connector-reference) - [MuleSoft Inference Connector](https://github.com/MuleSoft-AI-Chain-Project/mule-inference-connector) - [Introduction to Anypoint Connectors](https://docs.mulesoft.com/connectors/introduction/introduction-to-anypoint-connectors) - [Salesforce Help](https://help.salesforce.com)