Why MCP Was Always a Bad Idea
The author argues that the Model Context Protocol (MCP) is an outdated solution designed for less capable LLMs and has been superseded by more advanced AI capabilities. Modern large language models can now directly execute code and call APIs, rendering the complex infrastructure built around MCP servers unnecessary for many tasks. The article suggests that developers should replace most MCP servers with direct terminal access and standardized HTTP API interactions to improve efficiency and reduce context bloat.
- ▪MCP was originally released by Anthropic in November 2024 to help agents connect to external services when LLMs were less reliable.
- ▪The rapid adoption of MCP led to context bloat issues, prompting the development of various harnesses and monitoring systems to manage tool schemas.
- ▪Recent advancements in LLMs allow them to autonomously write scripts, use CLI help commands, and call APIs directly, reducing the need for MCP servers.
- ▪The author recommends deleting most MCP servers in favor of agents with terminal access and standardized HTTP API usage, such as using Accept: text/markdown headers.
Hacker News (Front Page) files mainly under programming. We currently carry 1,914 of its stories. Top-voted stories on Hacker News.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Maharshi Patel |
| Canonical URL | https://maharship.com/blog/why-mcp-was-always-a-bad-idea/ |
| Publication time | Sun, 20 Sep 2026 19:44:40 +0000 |
| Retrieval time | 2026-09-20T20:03:47.381Z |
| Last seen | 2026-09-20T20:03:47.381Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 5aHEy6Z3RNyK · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Back to blogWhy MCP Was Always a Bad IdeaSeptember 14, 2026MCPAIWhy MCP Was Always a Bad Idea Recently I went to an all-day event centered around the latest and greatest in the MCP world. While all of the presenters were awesome and seemed to be passionate about the work they were doing, I’m honestly tired of MCP. It’s a horrible protocol built for a time when LLMs weren’t that smart, and we’ve outgrown it. A Brief History MCP was released in November 2024 by the Anthropic team as a protocol designed to help agents connect to external services and data sources.1 The models of the time were still relatively primitive, at least compared to what we have right now. We didn’t even have Claude Code back then, and general-purpose agentic workflows were far less reliable.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Maharshi Patel.
Discussion
0 commentsMore from Maharshi Patel
