PulseAugur
EN
LIVE 18:53:51

mcp SDK 2.0.0 update breaks multiple AI tools, requiring dependency pins

A recent update to the mcp Python SDK to version 2.0.0 has caused widespread issues for various AI tools, including AutoGen, LlamaIndex, and Copilot CLI. The new version introduced breaking changes in its API, such as altered return types for functions, renamed variables, and updated JSON schema requirements. Many tools that did not properly pin their mcp dependency were affected when they automatically updated to the new version, leading to their servers becoming unresponsive. The primary solution involves pinning the mcp dependency to a version prior to 2.0.0 or applying specific patches for affected tools. AI

IMPACT Breaks in core SDKs like MCP can disrupt AI development workflows, highlighting the need for robust dependency management in the rapidly evolving AI tooling ecosystem.

RANK_REASON The item describes a breaking change in a software development kit (SDK) that impacts multiple downstream tools, requiring users to update their dependencies or apply workarounds.

Read on dev.to — MCP tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

mcp SDK 2.0.0 update breaks multiple AI tools, requiring dependency pins

COVERAGE [1]

  1. dev.to — MCP tag TIER_1 English(EN) · MilkyWay008 ·

    Your MCP tools stopped working after an update? Blame the mcp 2.0 SDK migration

    <p>If you run any AI tooling that uses MCP, the last couple of weeks might have been rough. The pattern kept showing up in GitHub issues: somebody does a routine update, and suddenly their MCP servers "just stop working." No error, or a cryptic one. The gateway reports healthy, t…