/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
Browse
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
Concept Search
Semantic similarity search
High Impact Stories
Top coverage by position
Sentiment Analysis
Positive/negative coverage
Anomaly Detection
Unusual coverage patterns
Analysis
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR

Chronicles

The story behind the story

days · browse · Enter similar · o open

MCP has promise beyond AI, and could serve as a “universal plugin system” that connects disparate data sources and tools together to enable new capabilities

Or: The Day My Toaster Started Taking Phone Calls  —  There's this thing about USB-C that nobody really talks about.

Works on My Machine Scott Werner

Context & Ripple Effects

MCP began as an open-source way to connect AI assistants with data sources, following Anthropic’s initial standard release. Subsequent coverage focused on its role in agent and search workflows, including Microsoft’s discussion of MCP alongside AI agents.

This article extends that arc: MCP could become a general interoperability layer rather than merely an LLM connector. Its USB-C comparison also emphasizes that a nominally universal interface can still fragment through implementation complexity and uneven compatibility.

First-order effects

  • Builders can evaluate MCP as a common interface for linking tools and data sources beyond a single AI assistant, broadening the kinds of integrations it might support.
  • High token use remains an immediate constraint for AI-facing implementations, making the protocol’s convenience trade off against context efficiency.

Second-order effects

  • Tool vendors and middleware providers may face pressure to expose MCP-compatible interfaces if customers want integrations to travel more easily across assistants and applications.
  • The USB-C analogy highlights a likely integration burden: incompatible extensions or partial implementations could shift complexity from point-to-point connectors into testing, compatibility, and support work.

Third-order effects

  • If adoption broadens while implementations remain interoperable, MCP could help move integration competition from proprietary connectors toward shared context and tool-access layers.
  • If token overhead and compatibility divergence persist, the protocol may instead reproduce the fragmented-plugin problem it aims to solve, with interoperability depending on middleware rather than the standard alone.

The trend: MCP is part of the push to make context and tool access portable across AI agents and, potentially, wider software ecosystems.

Discussion

  • @searls Justin Searls on bluesky
    MCP is doing the heavy lifting here.  I've written two “agentic” apps.  I immediately realized I could improve both by replacing the LLM part with normal fucking code.  The revolution here is MCP shoehorning API access into many more programs and services than we previously had..…
  • @scottwernerd Scott Werner on x
    MCP: An (Accidentally) Universal Plugin System. Everyone keeps saying AI will bring the “personalization era” of software, but handwaving whenever it comes to “how”. If MCP is a USB-C port like they say, you don't even need AI in the loop, you just have a universal plugin system …