> For the complete documentation index, see [llms.txt](https://docs.taskade.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.taskade.com/changelog/changelog-2026/march-2026/march-22-2026.md).

# March 22, 2026

{% hint style="info" %}
**Developer highlights.** This section tracks API, MCP, SDK, automation, and Taskade Genesis platform changes for developers. For the full product changelog see [taskade.com/changelog](https://www.taskade.com/changelog); for release newsletters see [taskade.com/blog/updates](https://www.taskade.com/blog/updates).
{% endhint %}

## What's New:

### MCP SDK Upgraded to ^1.27.1 / mcp-proxy ^6.4.4

The `@modelcontextprotocol/sdk` dependency across the Taskade MCP server and related server packages was bumped to `^1.27.1`. The `mcp-proxy` package used by the hosted MCP server was bumped to `^6.4.4`. This pull in a patched `koa` version (host-header injection fix, alert #371) and updated `ajv`. MCP clients that connect to the hosted or workspace MCP server benefit from these security and compatibility fixes without any client-side configuration change.

Reference: [Workspace MCP](/developers/workspace-mcp.md)

***

### Agent Memory Available Across All LLM Models

The Genesis app builder agent (TAA) now persists memory for all configured LLM models, not only Anthropic models. The agent reads and writes memory entries autonomously across conversations. This is relevant for Genesis apps that rely on long-running or multi-session agent interactions, regardless of the model selected in the app configuration.

Reference: [Getting Started with Genesis](/taskade-genesis/genesis/getting-started.md)

***

### Context Window Credit Multiplier Introduced

AI credit consumption for large-context requests now uses a `ceil(totalTokens / 150k)` multiplier. Requests whose total token count exceeds one 150k-token window consume proportionally more credits. The effective threshold was initially shipped at 200k and adjusted to 150k shortly after. API integrators and Genesis apps making high-context agent calls (long document analysis, large knowledge bases) should account for this multiplier in credit budget planning.

Reference: [API Guide](/developers/comprehensive-api-guide.md)


---

# 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.taskade.com/changelog/changelog-2026/march-2026/march-22-2026.md?ask=<question>&goal=<endgoal>
```

`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.