> For the complete documentation index, see [llms.txt](https://docs.digibee.com/documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.digibee.com/documentation/release-notes/july-2026/july-7.md).
# July 7
## :sparkles: **Agents**
### **New OAuth 2.0 audience validation on MCP Server Trigger**
You can now validate the `aud` (audience) claim in incoming OAuth 2.0 JWT tokens using the new **Validate OAuth2 Audience** parameter.
When enabled, only tokens issued for the MCP Server Trigger URL are accepted, helping prevent tokens created for other services from being used. This parameter is available only when OAuth2 JWT authentication is enabled. If disabled, audience validation is skipped while other JWT validations remain in effect.
Explore the MCP Server Trigger settings
## :plug: **Connectors & Triggers**
### **Dynamic Accounts across more connectors**
Dynamic Accounts is now available on more connectors, including:
* [Email V2](/documentation/connectors-and-triggers/connectors/web-protocols/email-v2.md)
* [AWS Simple Email Service (SES)](/documentation/connectors-and-triggers/connectors/aws/ses.md)
* [Dynamics 365](/documentation/connectors-and-triggers/connectors/enterprise-applications/dynamics-365.md)
* [PGP](/documentation/connectors-and-triggers/connectors/security/pgp.md)
* [PBE Cryptography](/documentation/connectors-and-triggers/connectors/security/pbe-cryptography.md)
* [RSA Cryptography](/documentation/connectors-and-triggers/connectors/security/rsa-cryptography.md)
* [S3 Storage](/documentation/connectors-and-triggers/connectors/aws/s3-storage.md)
Instead of hardcoding a single account per connector, you can now resolve which account to use at runtime with an expression, based on data in the message itself. This makes it easier to build pipelines that adapt to different accounts, credentials, or destinations depending on the context of each message.
Learn how to configure Dynamic Accounts
### **Byte-for-byte HL7 message pass-through**
You can now preserve the original HL7 message exactly as received when converting to JSON with the HL7 Message Transformer. Enabling the new pass-through parameter skips the normalizing parse step, so no characters, escape sequences, or trailing empty fields are altered, ensuring the message reaches its destination unchanged.
This is especially useful when the receiving system performs its own parsing and requires an identical copy of the original message.
See how it works
## :bugs: **Bug Fixes**
* **Canvas:** Improved error handling so certain errors now display a standard error state instead of a blank screen.
* **Password reset:** Fixed an issue where the password creation and reset screen did not display a success confirmation after submission, even though the password was created correctly.
* **Agent Component:** Fixed an issue where MCP server connection errors, such as authentication failures, were not shown in the Execution Logs.
* **For Each:** Fixed a configuration error that required manually setting Max Number Length even when Advanced was unmarked; the field now correctly falls back to its default value (1000).
* **LDAP:** Fixed an error that caused all LDAP connector test executions to fail with a pipeline configuration error, regardless of the account or search operation configured.
* **REST V2:** Fixed an issue where the Write Timeout and Call Timeout fields defaulted to an invalid value and showed a validation error. Both fields now default to 30000 ms, consistent with Connect Timeout and Read Timeout.
* **Azure Event Hubs:** Fixed an error affecting the Transport Type field configuration.
{% hint style="warning" %}
**Action required:** If you configured this field before this fix, you must reopen and save the connector to apply the correction. Pipelines saved with the previous value will keep failing until then.
{% endhint %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## 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, and the optional `goal` query parameter:
```
GET https://docs.digibee.com/documentation/release-notes/july-2026/july-7.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.