Is MCP dead because of CLIs?

No. The thread's most-cited post comes from a team that rejected MCP and then added it to core. CLIs win locally; MCP wins for hosted auth, policy and non-terminal clients.

Do skills replace MCP servers?

They replace the instructions around a server, not the connection. A skill cannot authenticate to a SaaS API on its own. The MCP spec even lists "Skills over MCP" as an extension, so the two are converging.

Where should an MCP server config live?

Local scope (default) is private to you in ~/.claude.json. Project scope writes .mcp.json at the repo root for your team, and Claude Code asks each person to approve it once. User scope follows you across projects.

How do I stop a skill running a dangerous command?

allowed-tools only pre-approves commands for that turn. It does not restrict which tools exist. Enforcement comes from your permission rules and, better, from the system itself, such as a read-only database role.

Which is best for CI?

A plain CLI, with the binary pinned in your image. If you need MCP in CI, set MCP_CLIENT_SECRET for pre-registered OAuth clients and commit the server definition in .mcp.json.

MCP vs CLI vs Skills: Which Tool Layer Your Agent Needs

TL;DR

MCP vs CLI vs skills: a 40-tool server can cost 12,000 tokens of definitions, a skill about 40. Decision table, three recipes, when to pick each.

A 40-tool MCP server can put roughly 12,000 tokens of tool definitions in front of your agent before it does anything, while a one-line skill costs about 40 tokens until Claude decides to use it. That gap is the whole argument behind the "just use the CLI" camp, and a 686-point Hacker News thread shows it is only half the story.^[1] My short answer: use a CLI plus a skill for anything that already has a good command line, use MCP when you need hosted auth, policy or non-terminal clients, and use a skill alone when the job is a procedure, not a capability. The sections below give a decision table, the same Postgres task done three ways, the token math, and a pick-this-when list.

What the 686-point thread actually argued

The thread is about an Earendil post titled "You said no MCP". The team behind the Pi agent harness had rejected MCP and now supports it in core. Their reasoning: MCP changed, and the changes Pi needed (deferred tools, tools exposed only to a code sandbox) were useful beyond MCP.^[2] Their own line on CLIs is the one people quote: CLIs work because "the agent and model just wire stuff together with efficient bashisms."

So the headline "agents prefer CLIs" is a simplification. The comments split by use case, not by ideology:

Local developers with a terminal-capable agent mostly say a CLI or REST API plus a doc file is enough, and that many MCP servers could have been CLIs.
Several commenters argue the opposite on security: an MCP server holds the API key so the agent never sees it, and enterprises get per-tool policy and fast revocation.
Anyone shipping to chat apps like claude.ai or chatgpt.com points out a CLI does nothing there. MCP is the only door.
The context-bloat complaint is real but harness-dependent. Some harnesses load every tool definition up front; others defer them.

The catch: the "MCP is dead" take and the "MCP wins" take are both wrong for the same reason. They describe different deployments.

The three layers, defined by what they actually are

MCP is a JSON-RPC protocol where a server exposes tools, resources and prompts to a host. The current spec is dated 2026-07-28 and describes stateless, self-contained requests with per-request capability negotiation.^[3] In Claude Code you add servers over HTTP (recommended for remote), stdio (local process), or SSE (deprecated).^[4]

A CLI is any command the agent can run through its shell tool. No protocol, no registration. The agent reads --help, or you tell it the flags.

A skill is a folder with a SKILL.md. Per the Claude Code docs, "skill descriptions are loaded into context so Claude knows what's available, but full skill content only loads when invoked."^[5] Skills live at ~/.claude/skills/<name>/SKILL.md for personal use or .claude/skills/<name>/SKILL.md for a repo, and a skill can pre-approve commands with allowed-tools.

These are not rivals at the same level. A skill is instructions. A CLI is a capability. MCP is a capability with a contract. The popular pairing, a skill that teaches the agent to drive a CLI, is just the first two stacked.

Criterion	MCP server	CLI	Skill
Auth	OAuth flow built in (`claude mcp login`), or headers and env vars. Server can hold the secret so the agent never sees it	Whatever the tool uses: env var, config file, SSO. The agent's shell can usually read it	None of its own. Inherits whatever the commands it calls use
Context cost	One definition per tool (name, description, JSON schema). Claude Code defers these through tool search by default	Zero until used, then the help text and output	Description only (capped at 1,536 characters in the listing), body loads on invoke
Discoverability	Best. `tools/list` is machine-readable	Weak unless `--help` is good	Good. Description is the trigger
Sandboxing	Server process boundary. Hosted servers keep credentials off your box	Runs with the shell's permissions	None. Permission rules still govern the commands it triggers
Works in CI	Yes, with care: `MCP_CLIENT_SECRET` for OAuth clients, project `.mcp.json` needs approval	Best. It is already a command	Yes, if the repo ships `.claude/skills`
Versioning	Protocol versioned by date; server versions are the vendor's. `npx -y pkg@latest` drifts	Pin the binary in your lockfile or image	Versioned by git with your repo
Maintainer	Vendor or community. You inherit their bugs	The tool's authors	You

Setup	Resting context	Per 100 sessions
40-tool MCP server, all definitions loaded	40 x 300 = ~12,000 tokens	~1.2M input tokens
Same server with Claude Code tool search (names discovered on demand)	Only tools Claude actually searches for	Varies; far lower
One skill with a 160-character description	~40 tokens	~4,000 tokens
Three skills, same size	~120 tokens	~12,000 tokens

MCP vs CLI vs Skills: Which Tool Layer Your Agent Needs

What the 686-point thread actually argued

The three layers, defined by what they actually are

Tools that go with this post

JSON Formatter & Validator

cURL to Code Converter

Regex Playground

Base64 Encoder / Decoder

UUID Generator

More from developer-productivity

Is Claude Nerfed? Build a 20-Task Eval Canary in an Afternoon

Opus 5.5 in Claude Code: Effort, Settings, CLAUDE.md Rules

Decision table

Recipe 1: query Postgres through an MCP server

Recipe 2: psql plus a skill

Recipe 3: a skill that wraps a script

Token cost math for tool definitions

Pick this when

Quick answers

Is MCP dead because of CLIs?

Do skills replace MCP servers?

Where should an MCP server config live?

How do I stop a skill running a dangerous command?

Which is best for CI?

Where to go next

Sources

One insight, every Monday. 7am IST.

Need production-ready templates?

Comments · 0

Claude Code Spend Limit: Hard Caps That Stop a Runaway Bill

Codex CLI Daemon: What It Does and How to Turn It Off

Claude Max API Credits: What $100 to $500 a Month Buys

Codex Cloud Pricing 2026: 5-Hour Window Math, Plus to Pro 500