mcp-migration

mcp-migration is a skill for Claude Code from AlpayC/mcp-migration-check. It costs 162 tokens per session (2,685 once invoked), scanned A, original, MIT.

A migration guide and checker for MCP servers, which are programs that let AI applications use external tools and data. It explains the changes required by the 2026-07-28 MCP specification, including stateless transport and formal OAuth 2.1 support.

In plain words
What is it for?
Use it to migrate or review an MCP server, add the modern request and OAuth paths, handle deprecated logging, sampling, and roots capabilities, and move TypeScript code to the SDK v2 package names.
Why use it?
It helps developers understand a protocol revision that changes how servers handle requests, authentication, capabilities, and TypeScript packages. It also warns against removing legacy behaviour too early when older clients still need it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mcp-migration plugin — 1 skill shipped together

Good fit Use it to migrate or review an MCP server, add the modern request and OAuth paths, handle deprecated logging, sampling, and roots capabilities, and move TypeScript code to the SDK v2 package names.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alpayc/mcp-migration-check/mcp-migration
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add AlpayC/mcp-migration-check --skill mcp-migration
Clone the repo
git clone --depth 1 https://github.com/AlpayC/mcp-migration-check

Made for: Claude Code.

Or install mcp-migration, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-migration

README.md
[![agentmods](https://agentmods.dev/badge/skills/alpayc/mcp-migration-check/mcp-migration/github.svg)](https://agentmods.dev/skills/alpayc/mcp-migration-check/mcp-migration)
Your own site
<a href="https://agentmods.dev/skills/alpayc/mcp-migration-check/mcp-migration"><img src="https://agentmods.dev/badge/skills/alpayc/mcp-migration-check/mcp-migration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-migration

Your own site · 80×15
<a href="https://agentmods.dev/skills/alpayc/mcp-migration-check/mcp-migration"><img src="https://agentmods.dev/badge/skills/alpayc/mcp-migration-check/mcp-migration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,685 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00162 $0.02685
Opus 5 $0.00081 $0.01342
Sonnet 5 $0.00032 $0.00537
Haiku 4.5 $0.00016 $0.00268

Measured 3d ago against content hash 5e95efa95fc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-migration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/mcpcheck.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/mcp-migration/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP 2026-07-28 migration

The 2026-07-28 revision is a refactor, not a version bump. Six things this checker looks for break existing servers:

  1. The transport is stateless. The initialize/notifications/initialized handshake and the Mcp-Session-Id header are gone from this revision. Every request carries its own protocol version and client capabilities in _meta. This does not mean deleting the handshake. A server "wishing to support both legacy clients … and modern clients MAY implement both behaviors" and picks its semantics from how each request opens — so the goal is to add the modern path, and retire the legacy one on the schedule your own clients dictate. Removing it for compliance breaks every v1 client for no gain.
  2. OAuth 2.1 is formalized for remote servers: a protected MCP server acts as an OAuth 2.1 resource server and MUST implement RFC 9728 protected-resource metadata.
  3. logging, sampling, and roots are deprecated — still functional, with a twelve-month minimum window, but new implementations should not adopt them.
  4. The TypeScript SDK moved to v2 under new package names. @modelcontextprotocol/sdk is the v1 line and stops at 1.30.0. v2 ships as @modelcontextprotocol/server + @modelcontextprotocol/client (plus /core and an /express, /fastify or /hono adapter).
  5. The Python SDK moved to v2 under the same package name. The official PyPI package remains mcp, while mcp.server.fastmcp.FastMCP becomes mcp.server.MCPServer. A <2 constraint or the old import is a v1 signal.

The revision changed more than the checker covers: server/discover is now mandatory, all results carry a required resultType, the GET stream and resources/subscribe are replaced by subscriptions/listen, ping and logging/setLevel are gone, SSE resumability is removed, and Mcp-Method / Mcp-Name headers are required. A clean checker run is not a migration. Read the changelog before declaring a server done.

Do not tell anyone to upgrade @modelcontextprotocol/sdk to ^2. That package has never published a 2.x — the migration is to the new package names above. There is an official codemod, and it is a separate package:

npx @modelcontextprotocol/codemod@latest v1-to-v2 .

That codemod is TypeScript-only. Do not reach for it, or for a package rename, when the project is Go — which is the next thing on this list.

  1. The Go SDK moved by a minor, on the same module path. github.com/modelcontextprotocol/go-sdk speaks 2026-07-28 from v1.7.0; v1.6.1 is the last release on 2025-11-25. There is no go-sdk/v2 — the module proxy 404s it — so never advise an import-path change or a 2.x. github.com/mark3labs/mcp-go crossed at its own v1.0.0. And for the official SDK the upgrade is only half of it: the streamable HTTP transport serves the revision only with StreamableHTTPOptions.Stateless = true. Left unset, clients negotiate down to 2025-11-25. A stdio server needs no such flag.

C# moved differently again — a 2.x major of the ModelContextProtocol packages. Check the actual package before advising a version.

Work in this order: diagnose, triage, remediate, re-verify. The diagnosis step is scripted so it gives the same answer every time — resist the urge to skip it and eyeball the code, because the rule ids it emits are what the remediation guidance keys off.

Read the full file on GitHub · 207 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago Changed · +19 lines 5e95efa95fc2
  2. 9d ago First seen · 188 lines · 162 tokens per session scan A 95efa36bcb1c

Subscribe to this mod's changes

mcp-migration is a skill published in the GitHub repository AlpayC/mcp-migration-check (5 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 2,685 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

scanner-pmcc

Scan stocks for Poor Man's Covered Call (PMCC) suitability. Analyzes LEAPS and short call options for delta, liquidity, spread, IV, yield, trend direction, and earnings proximity. Use when user asks about PMCC candidates, diagonal spreads, or LEAPS strategies.

staskh/trading_skills · 63 tokens

ib-collar

Generate tactical collar strategy reports for protecting PMCC positions through earnings or high-risk events. Requires TWS or IB Gateway running locally.

staskh/trading_skills · 30 tokens

ib-portfolio-action-report

Generate a comprehensive portfolio action report with earnings dates and risk assessment. Use when user asks for portfolio review, action items, earnings risk, or position management across IB accounts. Requires TWS or IB Gateway running locally.

staskh/trading_skills · 49 tokens

ib-trades-history

Fetch trade executions from Interactive Brokers filtered by account, date range, or symbol. Supports live API (7 days history) and FlexReport (full history). Use when user asks about their trades, executions, or transaction history. Requires TWS or IB Gateway running locally.

staskh/trading_skills · 59 tokens

report-stock

Generate comprehensive stock analysis report (PDF or markdown) with trend, PMCC, and fundamental analysis.

staskh/trading_skills · 22 tokens

ib-report-delta-adjusted-notional-exposure

Report delta-adjusted notional exposure across all IBKR accounts. Calculates option deltas using Black-Scholes and reports long/short exposure by account and underlying. Use when user asks about delta exposure, portfolio risk, or directional exposure.

staskh/trading_skills · 58 tokens