Memungkinkan AI agent untuk mengecek apakah model ID LLM sudah deprecated atau retired dan menemukan rekomendasi penggantinya dari berbagai provider utama.
Juga dikenal sebagai hivemindunit/llmintel-mcp, model-lifecycle, @llmintel/mcp
- Stars
- 1
- Tools
- 5
- Unduhan, 30 hari
- 695
- Versi terbaru
- 0.2.0
- Commit terakhir
- 20 Okt 2026
- Lisensi
- MIT
Apa itu LLMIntel Model Lifecycle MCP?
LLMIntel Model Lifecycle adalah MCP server. Memungkinkan AI agent untuk mengecek apakah model ID LLM sudah deprecated atau retired dan menemukan rekomendasi penggantinya dari berbagai provider utama. Server ini menyediakan 5 tool, seperti check_model, list_retiring_models, suggest_replacement.
Ringkasan dibuat dari README proyek
Tentang LLMIntel Model Lifecycle MCP server
LLMIntel Model Lifecycle membantu developer dan AI agent memverifikasi apakah model ID LLM tertentu masih aktif atau sudah retired. Tool ini menyediakan lookup secara live untuk mencegah kode menggunakan model yang sudah deprecated yang tidak lagi merespons API calls. Server ini mengagregasi data dari provider utama termasuk OpenAI, Anthropic, Azure AI Foundry, AWS Bedrock, Google, dan Cohere dengan memparsing halaman deprecation resmi mereka.
User dapat menjalankan server ini secara lokal via npx atau terhubung ke hosted HTTP endpoint. Anda tidak memerlukan pendaftaran atau API keys untuk penggunaan standar, meskipun penggunaan key opsional dapat meningkatkan rate limits. Sistem ini menyertakan tools seperti check_model untuk memverifikasi satu ID, list_retiring_models untuk melihat jadwal ekspirasi mendatang, dan suggest_replacement untuk menemukan pengganti yang direkomendasikan. Tool ini dirancang untuk digunakan di dalam MCP hosts seperti Cursor, Claude Desktop, atau Claude Code.
Apa yang bisa Anda lakukan dengannya
- 1Verifikasi keamanan model dalam kodeSeorang agent dapat memindai codebase untuk memastikan semua identifier model saat ini masih didukung dan belum retired.
- 2Identifikasi ekspirasi model mendatangDeveloper dapat meminta daftar model yang dijadwalkan berhenti berfungsi dalam jangka waktu tertentu.
- 3Menemukan pengganti model yang sesuaiKetika sebuah model dinyatakan deprecated, agent dapat menemukan successor resmi yang direkomendasikan oleh provider.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal LLMIntel Model Lifecycle MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal LLMIntel Model Lifecycle MCP di Claude Code
$ claude mcp add --env 'LLMINTEL_API_KEY=<YOUR_LLMINTEL_API_KEY>' model-lifecycle -- npx -y @llmintel/mcpInstal LLMIntel Model Lifecycle MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"model-lifecycle": {
"command": "npx",
"args": [
"-y",
"@llmintel/mcp"
],
"env": {
"LLMINTEL_API_KEY": "<YOUR_LLMINTEL_API_KEY>"
}
}
}
}Instal LLMIntel Model Lifecycle MCP di VS Code
.vscode/mcp.json
{
"servers": {
"model-lifecycle": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@llmintel/mcp"
],
"env": {
"LLMINTEL_API_KEY": "<YOUR_LLMINTEL_API_KEY>"
}
}
}
}Instal LLMIntel Model Lifecycle MCP di VS Code CLI
$ code --add-mcp '{"name":"model-lifecycle","type":"stdio","command":"npx","args":["-y","@llmintel/mcp"],"env":{"LLMINTEL_API_KEY":"<YOUR_LLMINTEL_API_KEY>"}}'Instal LLMIntel Model Lifecycle MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"model-lifecycle": {
"command": "npx",
"args": [
"-y",
"@llmintel/mcp"
],
"env": {
"LLMINTEL_API_KEY": "<YOUR_LLMINTEL_API_KEY>"
}
}
}
}Instal LLMIntel Model Lifecycle MCP di Codex
$ codex mcp add model-lifecycle --env 'LLMINTEL_API_KEY=<YOUR_LLMINTEL_API_KEY>' -- npx -y @llmintel/mcpInstal LLMIntel Model Lifecycle MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.model-lifecycle] command = "npx" args = ["-y", "@llmintel/mcp"] [mcp_servers.model-lifecycle.env] LLMINTEL_API_KEY = "<YOUR_LLMINTEL_API_KEY>"
Instal LLMIntel Model Lifecycle MCP di Gemini CLI
$ gemini mcp add -s user -e 'LLMINTEL_API_KEY=<YOUR_LLMINTEL_API_KEY>' model-lifecycle npx -- -y @llmintel/mcpInstal LLMIntel Model Lifecycle MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"model-lifecycle": {
"command": "npx",
"args": [
"-y",
"@llmintel/mcp"
],
"env": {
"LLMINTEL_API_KEY": "<YOUR_LLMINTEL_API_KEY>"
}
}
}
}Tool LLMIntel Model Lifecycle MCP 5
Terdeteksi dari READMEcheck_modellist_retiring_modelssuggest_replacementsearch_modelsrecent_lifecycle_changes
| check_model | — | |
| list_retiring_models | — | |
| suggest_replacement | — | |
| search_models | — | |
| recent_lifecycle_changes | — |
Konfigurasi
LLMINTEL_API_KEYRahasiaOptional. The catalog is public and needs no key; supplying one only raises the rate-limit budget.
LLMINTEL_BASE_URLOptional. Override the catalog origin (defaults to https://llmintel.ai). Useful for self-hosted or staging deployments.
| Nama | Deskripsi | Tipe |
|---|---|---|
| LLMINTEL_API_KEY | Optional. The catalog is public and needs no key; supplying one only raises the rate-limit budget. | Rahasia |
| LLMINTEL_BASE_URL | Optional. Override the catalog origin (defaults to https://llmintel.ai). Useful for self-hosted or staging deployments. |
Pengecekan otomatis
Berjalan 12 Nov 2026Laporan lengkap →Lolos checks otomatis kami. Ini bukan audit keamanan: baca kodenya dan berikan server akses paling terbatas yang dibutuhkannya. Cara kerja checks
- Source repository terhubung dan dapat dijangkauLolos
- Lisensi open source (OSI)Lolos
- Ada commit atau release dalam satu tahun terakhirLolos
- Nama package tidak mirip dengan package populerLolos
- Remote endpoint menggunakan HTTPSLolos
- Tools yang bersifat destruktif telah diberi labelLolos
- Tidak ada instruksi tersembunyi untuk modelLolos
- Tidak ada advisory kritis pada paket atau dependensinyaLolos
README
Lihat di GitHub@llmintel/mcp
An MCP server that tells your coding agent whether a model id is safe to use.
LLMs are trained on a snapshot of the world and will confidently write gpt-4-32k into your code
long after it stops answering. This server gives the agent a live lookup for whether a model is
deprecated and when it stops working. It returns the replacement too. Answers are normalized across
OpenAI, Anthropic, Azure AI Foundry, AWS Bedrock, Google, and Cohere, and parsed from each
provider's own deprecation pages.
No API key, no signup. The catalog is public.
Install
Add it to any MCP host. The package runs straight from npm via npx.
Cursor
In .cursor/mcp.json:
{
"mcpServers": {
"llmintel": {
"command": "npx",
"args": ["-y", "@llmintel/mcp"]
}
}
}
Claude Code
claude mcp add llmintel -- npx -y @llmintel/mcp
Claude Desktop
Same shape as the Cursor block above, in claude_desktop_config.json.
Hosted endpoint (no install)
The same five tools are served over Streamable HTTP at https://llmintel.ai/v1/mcp. Hosts that take
a URL need no Node and no package:
{
"mcpServers": {
"llmintel": {
"url": "https://llmintel.ai/v1/mcp"
}
}
}
The endpoint is stateless and read-only. It answers from the same catalog the npm package queries.
Tools
| Tool | Returns |
|---|---|
check_model |
Whether one model id is safe to use: lifecycle state, the retirement deadline in days, the replacement, and the source link. |
list_retiring_models |
What breaks in the next 180 days (default; configurable up to 1095). Past-due models are listed first, then upcoming ones soonest-first. |
suggest_replacement |
The provider's own recommendation for what to move to. Falls back to same-provider active models when none was published. |
search_models |
Catalog search filtered by provider and lifecycle state. |
recent_lifecycle_changes |
The change feed across all providers, for questions like "what was deprecated this month". |
Example
You: Before we ship this, check the model ids in
src/agents/.
The agent calls check_model for each one and gets back:
DO NOT USE — this model is retired; API calls to it fail.
"claude-sonnet-4-20250514" resolves to the tracked model anthropic/claude-sonnet-4-20250514.
Model: claude-sonnet-4-20250514 (anthropic/claude-sonnet-4-20250514)
Provider: anthropic
Lifecycle state: retired — retired; calls fail
Deprecated: 2026-04-14 (105 days ago)
Retirement: 2026-06-15 (43 days ago)
The provider has not named a replacement. Use suggest_replacement for options.
Pricing/limits: $3/1M in · $15/1M out
Source: https://docs.anthropic.com/en/docs/about-claude/model-deprecations
Provider's own term: "Retired"
Deadlines are always given in days, because a model cannot reliably judge whether 2026-07-30 is
soon.
Design notes
A failed lookup is never a safety verdict. If the catalog is unreachable, the tool returns an MCP error and says so. An agent that read a network failure as "no deprecation found" would happily ship a retired model id. A model that simply isn't tracked gets the same treatment: it returns "not in the catalog, verify with the provider", never "OK".
Pass whatever string is literally in the code (gpt-4o, anthropic/claude-opus-4-1, azure/gpt-4o)
and it resolves to the canonical tracked model.
When the provider's own deprecation notice names a successor, that is what you get. Otherwise the fallback list of same-provider active models is labelled as candidates to evaluate, so an agent can tell the two apart.
Anything past its retirement date is broken now, so it gets its own heading instead of sitting in "retiring soon".
Configuration
Both variables are optional.
| Variable | Default | Purpose |
|---|---|---|
LLMINTEL_API_KEY |
none | Raises the rate-limit budget. The catalog itself is public, so you do not need this. |
LLMINTEL_BASE_URL |
https://llmintel.ai |
Point at a self-hosted or staging catalog. |
Anonymous callers get 30 requests/minute per IP, enough for interactive agent use.
Data provenance
Every record links to the provider page it was parsed from and preserves the provider's verbatim
lifecycle term (sourceTerm), so a normalization decision is always auditable. Changes go through a
human verification queue before publication. Collector freshness is public at
/v1/status.
The same data is available as a plain REST API, also without a key. See llmintel.ai/docs.
Where to find it
| Directory | Entry |
|---|---|
| Official MCP Registry | ai.llmintel/model-lifecycle |
| Glama | @hivemindunit/llmintel-mcp |
| Smithery | llmintel/model-lifecycle |
| npm | @llmintel/mcp |
Development
pnpm --filter @llmintel/mcp build
pnpm exec vitest run packages/mcp # protocol-level tests against a fake catalog
# Drive the built binary against a live catalog
pnpm --filter @llmintel/mcp smoke
LLMINTEL_BASE_URL=http://localhost:3000 pnpm --filter @llmintel/mcp smoke
License
MIT © LLMIntel
Pertanyaan tentang LLMIntel Model Lifecycle MCP
Bagaimana cara menambahkan LLMIntel Model Lifecycle MCP ke Claude Code?
Jalankan claude mcp add --env 'LLMINTEL_API_KEY=<YOUR_LLMINTEL_API_KEY>' model-lifecycle -- npx -y @llmintel/mcp di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan LLMIntel Model Lifecycle MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Tool apa yang disediakan LLMIntel Model Lifecycle MCP?
Server ini menyediakan 5 tool, termasuk check_model, list_retiring_models, suggest_replacement, search_models, recent_lifecycle_changes.
Apakah saya memerlukan API key untuk menggunakan server ini?
Tidak, katalog ini bersifat publik dan Anda dapat menggunakannya tanpa API key atau pendaftaran.
Apa yang terjadi jika sebuah model tidak ada dalam katalog?
Server akan mengembalikan pesan yang menyatakan bahwa model tersebut tidak ada dalam katalog dan menyarankan Anda untuk memverifikasinya ke provider terkait, alih-alih berasumsi bahwa model tersebut aman digunakan.
Bisakah saya menggunakan ini tanpa menginstall npm package?
Ya, Anda bisa menggunakan hosted HTTP endpoint jika MCP host Anda mendukung URL.
Apakah ada rate limit untuk pengguna anonim?
Ya, pemanggil anonim dibatasi sebanyak 30 request per menit per IP.