# Architecture

There would 2 instances of Protocol Server that is running. One is `Client` facing and the other is `Network` facing.\
\
**In the case of BAP**\
\
`Client` facing Protocol Server manages building the context, validating the request body as per the Standard Beckn Open API schema, listens to the Message Queue, Aggregates the results in the case of Synchronous mode and forwards the results to the client side application as a webhook callback.

`Network` facing Protocol Server manages forwarding the request to the respective Participant or Beckn Gateway (BG). Also it validates the incoming requests from Participants & BG as per the Standard Beckn Open API schema and then validates the signature sent from the clients to ensure the data integrity.

<figure><img src="/files/2brhcrWH6nUPG7taA1Ev" alt=""><figcaption></figcaption></figure>

**In the case of BPP**\
\
`Client` facing Protocol Server listens to the Message Queue and forwards the request to client side application, exposes an endpoint where the client side application can send the results to the network which is again validated against the Standard Beckn Open API schema and pushed to the network facing Protocol Server.

`Network` facing Protocol Server also listens to the Message Queue and forwards the request to the respective Participant or BG. Also it validates the incoming requests from Participants & BG as per the Standard Beckn Open API schema and then validates the signature sent from the clients to ensure the data integrity.

<figure><img src="/files/l7EGVRidPjiYUTWNavFU" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://starterpack.onest.network/learn/integration-of-adaptors/beckn-protocol-server/architecture.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.