MCP was always a bad idea?
- ID
- 26784
- Status
- summarized
- Published
- 21 Sep 2026, 3:44 AM
- Fetched
- 23 Sep 2026, 2:56 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://maharship.com/blog/why-mcp-was-always-a-bad-idea/
- Source URL
- https://hnrss.org/best
Summary
- Score
- 6.5
- Created
- 23 Sep 2026, 2:58 AM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
The author argues MCP (Model Context Protocol), released by Anthropic in November 2024 and later donated to the Linux Foundation's Agentic AI Foundation in 2025, is becoming obsolete because modern LLMs can now call APIs directly, write scripts, and compose services autonomously without a dedicated tool-calling protocol. They describe an 'MCP industrial complex' of monitoring tools and context-bloat workarounds (Composio, MintMCP, Pipedream) that exist to patch over limitations that better models are outgrowing.
Why it matters
If you're building or investing in MCP servers or MCP-based agent infrastructure, this argues you may be building on a layer that shrinking model capability gaps will make redundant. Consider whether direct API-calling agents (via code execution environments) reduce the need for MCP-style tool schemas in your stack before committing further.
Discussion angle
Is MCP actually dying, or does it still solve credential management and discoverability problems that raw API-calling agents don't handle? Test the author's claim against what you're actually shipping today.