Erkle MCP server
Commit 13 Nov 2026Menyediakan memori tim yang dibagikan dan telah ditinjau untuk AI coding agent guna menjaga konsistensi di berbagai repository dan tool.
Juga dikenal sebagai erkle-ai/cli
- Stars
- 1
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- —
- Commit terakhir
- 13 Nov 2026
- Lisensi
- MIT
Apa itu Erkle MCP?
Menyediakan memori tim yang dibagikan dan telah ditinjau untuk AI coding agent guna menjaga konsistensi di berbagai repository dan tool.
Ringkasan dibuat dari README proyek
Tentang Erkle MCP server
CLI ini memungkinkan tim engineering untuk menjaga standar coding yang konsisten di berbagai repository dan AI tools yang berbeda. Dengan menghubungkan agent seperti Claude Code, Cursor, dan Codex ke hosted MCP server, tim dapat membangun memori bersama yang tetap ada meskipun berpindah antar orang maupun proyek. Hal ini mencegah agent individu membuat keputusan yang bertentangan, seperti melakukan retry pada pemanggilan API tertentu secara salah, padahal tim sebelumnya sudah memutuskan untuk menanganinya dengan cara berbeda.
Developer dapat menggunakan perintah npx @erkle/cli init untuk menghubungkan agent lokal mereka ke layanan Erkle. Proses setup akan secara otomatis mengonfigurasi file spesifik proyek seperti .mcp.json atau .cursor/mcp.json dan menambahkan instruksi yang diperlukan ke file AGENTS.md atau CLAUDE.md. Ini memastikan bahwa setiap agent akan mencari batasan tim yang sudah ada sebelum memulai tugas, serta mengusulkan konvensi baru untuk ditinjau oleh maintainer setelah pekerjaan selesai. Sistem ini menggunakan sign-in OAuth berbasis browser untuk setiap agent alih-alih mengharuskan penggunaan API key secara manual.
Apa yang bisa Anda lakukan dengannya
- 1Mencegah keputusan coding yang bertentanganAI agent dapat mencari memori bersama untuk menemukan batasan spesifik, seperti menghindari retry pada endpoint tertentu guna mencegah double-charging.
- 2Berbagi konvensi antar repositoryTim dapat memastikan bahwa pengetahuan yang didapat di satu repository tersedia bagi agent yang bekerja di proyek yang sepenuhnya berbeda.
- 3Formalisasi pengetahuan tim yang baruSaat agent menemukan pola baru, ia dapat mengusulkan konvensi formal yang memerlukan persetujuan maintainer manusia sebelum menjadi bagian dari memori tim.
- 4Otomatisasi konfigurasi agentDeveloper dapat dengan cepat menyiapkan berbagai AI coding tools sekaligus di dalam sebuah git repository menggunakan satu perintah inisialisasi.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Konfigurasi
ERKLE_URL
| Nama | Deskripsi | Tipe |
|---|---|---|
| ERKLE_URL | — |
Pengecekan otomatis
Berjalan 15 Nov 2026Laporan lengkap →Belum diverifikasi. Sebuah server memerlukan skor 80, tidak ada temuan serius, dan data yang cukup untuk kami periksa. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkauerkle-ai/cli is public and reachablegithub.com/erkle-ai/cli ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyaTidak diperiksa
- Provenance build (atestasi Sigstore)Tidak diperiksa
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-13github.com/erkle-ai/cli ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerTidak diperiksa
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubnpx @erkle/cli init
Your agents forget what your team decided. One teammate's Claude Code learns
that the billing service must never retry a charge; tomorrow another
teammate's Cursor retries it. CLAUDE.md helps inside one repo, but it doesn't
travel across repos, tools, or people, and nobody reviews what goes in it.
Erkle gives every agent on the team the same reviewed memory.
What it looks like
After init, a session goes like this (illustrative):
You: Add retries to the charge endpoint.
Agent: [memory_search "charge endpoint retries" repo=acme/billing]
Found 1 constraint (team scope, approved by Dana):
"Never retry POST /charges. Stripe idempotency keys expire after 24h,
and a retry after that double-charges. Retry only the webhook."
I'll add retries to the webhook handler instead and leave /charges alone.
...
Agent: I learned the webhook handler must be idempotent on event.id.
Propose it as a convention for acme/billing? [y/n]
You: y
Agent: [memory_create] Proposed. A maintainer reviews it before it goes live.
What is Erkle?
Erkle is shared, reviewed team memory for AI coding
agents. It's a hosted MCP server (https://erkle.ai/mcp) where your team's
decisions, conventions, constraints and lessons live, scoped to the team, a
project, or a repository. Agents search it before a task and propose what
they learned after; maintainers review proposals before they go live. One
memory works across Claude Code, Cursor, Codex and claude.ai, so every
teammate's agent knows what the team knows.
@erkle/cli is the setup step: erkle init wires your agents to that server
and tells them how to use it.
Run it in a git repository (installed globally, the command is erkle init).
It:
- Adds the
erkleMCP server to each agent you pick (Claude Code, Cursor, Codex). - Adds a short instructions block to
AGENTS.md/CLAUDE.md, so agents search Erkle before a task and propose what they learned after. - Prints the sign-in step for each agent and a first-run prompt that imports what the repo already knows.
init never signs in and never talks to Erkle. Each agent runs its own
browser sign-in the first time it connects.
What it writes
| Agent | Project (default) | --global |
|---|---|---|
| Claude Code | .mcp.json |
claude mcp add --scope user (~/.claude.json) |
| Cursor | .cursor/mcp.json |
~/.cursor/mcp.json |
| Codex | .codex/config.toml (loaded once you trust the project) |
~/.codex/config.toml |
Project files live in the repo root, so commit them and every teammate gets the same setup.
Instructions go between <!-- erkle:start --> and <!-- erkle:end --> in
AGENTS.md and CLAUDE.md, whichever exist. A CLAUDE.md that is a
symlink to AGENTS.md, or that imports it with an @AGENTS.md line, is left
alone so the block appears once. If neither file exists, init creates
AGENTS.md, which Claude Code, Cursor and Codex all read. Re-running replaces
only the text between the markers.
Existing files keep everything else: other MCP servers, other keys, JSON
indentation, and TOML comments. If a file can't be parsed (JSON with
comments, for example) init stops and writes nothing. If an erkle entry
already points somewhere else, init reports it as a conflict and leaves it
alone unless you pass --force; everything else in the plan is still
applied.
init treats the repo as untrusted, since it may be a fresh clone. If a
project file is a symlink that resolves outside the repo, init stops and
writes nothing. An existing erkle entry with keys that can run code
(command, env, headersHelper, ...) is a conflict too. If a file changes
between the plan and the write, init stops instead of overwriting it.
Running init again when everything is set up changes nothing.
Options
--agents <list> claude,cursor,codex (default: ask, or the detected ones)
--global write user-level config instead of the repo's
--url <url> MCP server URL (default https://erkle.ai/mcp, or $ERKLE_URL)
-y, --yes apply without asking
--dry-run print the plan and write nothing
--force replace an existing erkle entry that has a different URL
--no-instructions don't touch AGENTS.md / CLAUDE.md
-h, --help show help
-v, --version show the version
Exit codes: 0 success, nothing to do, or cancelled at the prompt; 1 error
(nothing written); 2 bad usage. When stdin or stdout isn't a terminal,
init won't ask, so pass --yes to apply (or --dry-run to preview);
without either it exits 2.
For local development against a dev server:
ERKLE_URL=http://localhost:8080/mcp npx @erkle/cli init
FAQ
Does init need an Erkle account or API key? No. It only writes config
files. Each agent opens a browser OAuth sign-in the first time it connects.
There are no API keys.
Which agents are supported? Claude Code, Cursor and Codex. claude.ai connects to the same server as a custom connector; see erkle.ai.
How is this different from CLAUDE.md or AGENTS.md? Instruction files
live in one repo and change by commit. Erkle is shared across repos and tools,
scoped by team, project and repo, permissioned, and reviewed. init keeps a
short block in your instruction files that points agents at Erkle; see
Erkle vs. AGENTS.md.
What does it cost? $5 per user per month, or $50 per user per year, after a 7-day trial with no card needed. See pricing.
Who maintains this
Erkle is built and operated by
Justin Albrecht.
Development happens in a private repository. This public repository is the
release mirror: each release lands here as one commit made by the release
automation, which is why commits show github-actions[bot], and its tag is
what gets published to npm. How Erkle itself handles your data is on the
security page.
Bugs
Open an issue at github.com/erkle-ai/cli. This repository receives one commit per release and doesn't take pull requests; see CONTRIBUTING. Report vulnerabilities privately, as described in SECURITY.
Pertanyaan tentang Erkle MCP
Apakah init memerlukan akun Erkle atau API key?
Tidak, perintah init hanya menulis file konfigurasi. Agent akan menggunakan sign-in OAuth berbasis browser saat pertama kali terhubung.
AI agent mana saja yang didukung?
CLI ini mendukung Claude Code, Cursor, dan Codex.
Apa perbedaan Erkle dengan CLAUDE.md atau AGENTS.md?
Jika file instruksi terbatas pada satu repository saja, Erkle menyediakan memori bersama di berbagai repository, tool, dan tim dengan proses review.
Berapa biaya penggunaan Erkle?
Erkle berbiaya $5 per user per bulan atau $50 per user per tahun, setelah masa free trial selama 7 hari.