Olbrain Alchemist MCP server
2026년 11월 11일 커밋Claude Code, Cursor, GitHub Copilot과 같은 코딩 환경에서 자연어 설명을 사용하여 AI agent를 빌드, 테스트 및 게시합니다.
다른 이름 Olbrain/alchemist-plugin, alchemist-plugin
- 스타
- 1
- Tools
- 16
- 다운로드, 30일
- —
- 최신 버전
- 0.9.14
- 마지막 커밋
- 2026년 11월 11일
- 라이선스
- MIT
Olbrain Alchemist MCP란?
Olbrain Alchemist은(는) MCP server입니다. Claude Code, Cursor, GitHub Copilot과 같은 코딩 환경에서 자연어 설명을 사용하여 AI agent를 빌드, 테스트 및 게시합니다. 16개 도구를 제공합니다. 예: whoami, create_org, select_org.
프로젝트 README에서 생성된 요약
Olbrain Alchemist MCP server 정보
Alchemist는 개발자가 자연어 설명을 사용하여 AI agent를 생성, 테스트 및 게시할 수 있도록 지원하는 agent builder입니다. Claude Code, Cursor, GitHub Copilot, Antigravity, Codex를 포함한 인기 코딩 환경에 직접 통합됩니다. Olbrain 계정에 연결하면 브리핑, 계획, 빌드, 테스트, 게시를 포함하는 구조화된 다단계 프로세스를 통해 AI를 가이드할 수 있습니다.
이 시스템은 코딩 어시스턴트가 agent를 설계하는 동안 Alchemist가 단계별 가이드와 검증을 제공하는 방식으로 작동합니다. 도구 및 지식 연결부터 초안 버전에 대한 실환경 테스트 실행까지 전체 라이프사이클을 관리합니다. agent가 빌드되면 Olbrain 플랫폼에서 실행되며, 팀 리뷰 및 수정을 위해 Noesis 콘솔에 표시됩니다.
보안은 서버가 중요한 변경을 수행하거나 게시하기 전에 승인을 요청하는 승인 시스템을 통해 유지됩니다. 사용자는 이러한 승인 카드에 대해 AI가 어느 정도의 자율성을 가질지 구성할 수 있습니다. 또한 서버는 빌드 단계와 조직 설정을 관리하기 위해 alchemist_do 및 alchemist_answer와 같은 특정 도구를 제공합니다.
활용 사례
- 1특화된 고객 서비스 agent 생성개발자가 가격 문의를 처리하고 환불을 진행하는 agent를 빌드하도록 AI에게 지시할 수 있습니다.
- 2웹 플랫폼에 agent 배포AI에게 기존 프로젝트에 채팅 스니펫이나 server route를 추가하도록 명령하여 agent를 라이브 상태로 만들 수 있습니다.
- 3agent 아키텍처 시각화개발자는 agent의 로직과 연결 구조를 이해하기 위해 시각적 다이어그램을 요청할 수 있습니다.
- 4진행 중인 agent 빌드 관리채팅에서 agent 이름을 참조하여 특정 agent 개발 프로세스를 재개할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
Olbrain Alchemist MCP 설치 방법
형식 확인: 2026년 11월 10일Cursor에 추가Goose에 추가Claude Code에 Olbrain Alchemist MCP 설치
$ claude mcp add --transport http alchemist-plugin https://alchemist.olbrain.com/mcp/Cursor에 Olbrain Alchemist MCP 설치
~/.cursor/mcp.json
{
"mcpServers": {
"alchemist-plugin": {
"url": "https://alchemist.olbrain.com/mcp/"
}
}
}VS Code에 Olbrain Alchemist MCP 설치
.vscode/mcp.json
{
"servers": {
"alchemist-plugin": {
"type": "http",
"url": "https://alchemist.olbrain.com/mcp/"
}
}
}VS Code CLI에 Olbrain Alchemist MCP 설치
$ code --add-mcp '{"name":"alchemist-plugin","type":"http","url":"https://alchemist.olbrain.com/mcp/"}'Codex에 Olbrain Alchemist MCP 설치
$ codex mcp add alchemist-plugin --url https://alchemist.olbrain.com/mcp/Codex config.toml에 Olbrain Alchemist MCP 설치
~/.codex/config.toml
[mcp_servers.alchemist-plugin] url = "https://alchemist.olbrain.com/mcp/"
Gemini CLI에 Olbrain Alchemist MCP 설치
$ gemini mcp add -s user --transport http alchemist-plugin https://alchemist.olbrain.com/mcp/Gemini settings.json에 Olbrain Alchemist MCP 설치
~/.gemini/settings.json
{
"mcpServers": {
"alchemist-plugin": {
"url": "https://alchemist.olbrain.com/mcp/",
"type": "http"
}
}
}Olbrain Alchemist MCP 도구 16
README에서 감지됨whoamicreate_orgselect_orglist_membersalchemistalchemist_statealchemist_doalchemist_answeralchemist_buildsalchemist_buildalchemist_edit_buildalchemist_rate_build
| whoami | — | |
| create_org | — | |
| select_org | — | |
| list_members | — | |
| alchemist | — | |
| alchemist_state | — | |
| alchemist_do | — | |
| alchemist_answer | — | |
| alchemist_builds | — | |
| alchemist_build | — | |
| alchemist_edit_build | — | |
| alchemist_rate_build | — |
도구 16개 모두 보기도구 수 줄이기
alchemist_stopalchemist_connectalchemist_capabilitiesalchemist_show_agent
| alchemist_stop | — | |
| alchemist_connect | — | |
| alchemist_capabilities | — | |
| alchemist_show_agent | — |
자동 검사
2026년 11월 14일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능olbrain/alchemist-plugin is public and reachablegithub.com/olbrain/alchemist-plugin ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-11github.com/olbrain/alchemist-plugin ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
- 모델에 대한 숨겨진 지침 없음16 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨No tool named like delete, drop or exec통과
- 원격 엔드포인트가 MCP 핸드셰이크에 응답HTTPS endpoint answered 401 (sign-in required)통과
README
GitHub에서 보기What it is
Alchemist is Olbrain's agent builder, available as an MCP server and a Claude Code plugin. You tell Claude what the agent should do, in plain words. Claude (or Codex, Antigravity or Cursor) plans and designs the agent from your words and your project, with Alchemist's step-by-step guidance. Alchemist builds it in your Olbrain organisation, tests it on real inputs, checks each step in order, refusing one that is skipped, and publishes it.
Every agent it builds runs on Olbrain and stays visible in Noesis, Olbrain's console, where your team can open, review and change it.
Install
Claude Code
/plugin marketplace add Olbrain/alchemist-plugin
/plugin install alchemist@alchemist
Then run /mcp, pick alchemist and sign in with your Olbrain account. New to Olbrain?
Choose Create account on the sign-in page.
Claude Code asks before every tool call. To stop it asking each time Claude checks on a
build, allow these five tools once under /permissions (they read; alchemist_state also
marks the build's news as seen, and Claude shows it to you):
mcp__plugin_alchemist_alchemist__whoami, mcp__plugin_alchemist_alchemist__alchemist_builds,
mcp__plugin_alchemist_alchemist__alchemist_build,
mcp__plugin_alchemist_alchemist__alchemist_capabilities and
mcp__plugin_alchemist_alchemist__alchemist_state. Leave the rest asking, including
alchemist_do and alchemist_answer: they take build steps, answer cards or change your
organisation.
To see an agent drawn in a pane beside the chat, also install the canvas:
/plugin install alchemist-canvas@alchemist
It draws the agent whenever Claude shows it, and redraws it when a publish or make-live
card arrives, with new, changed and removed parts marked. /agent-canvas opens the pane
when the terminal is too narrow for it to open by itself. It needs a Claude Code build
with plugin panes; older builds and Codex skip it.
Codex
Install Olbrain Alchemist from the OpenAI plugin directory, which serves Codex and ChatGPT: chatgpt.com/plugins/plugin_asdk_app_6ae0b1249a888191ac551144ac1819fb. It brings the Alchemist skills and connects the MCP server. Sign in with your Olbrain account when asked. The directory can be a release behind this repository while OpenAI reviews one.
Or connect the server by hand:
codex mcp add alchemist --url https://alchemist.olbrain.com/mcp/
codex mcp login alchemist
With the server added by hand, you can copy the plugins/alchemist/skills/alchemist folder to
~/.agents/skills/alchemist so Codex follows the same workflow as Claude, including when to
continue a build and when to start a new one. Without it, the server's own instructions carry
the same rule. A copied skill does not update itself: copy it again after each release.
Antigravity
agy plugin install https://github.com/Olbrain/alchemist-plugin/tree/main/plugins/alchemist
Or in the Antigravity app: Customizations → Plugins → Install from URL with the same URL.
This installs the Alchemist skills and connects the MCP server. Sign in with your Olbrain
account when Antigravity asks; if it doesn't, open /plugin, expand alchemist under
Installed and choose Sign in.
The canvas is Claude Code only.
Cursor
Install Olbrain Alchemist from the Cursor plugin directory:
cursor.directory/plugins/alchemist. Sign in with
your Olbrain account when Cursor asks, or from the alchemist row in Customize.
A team admin can also add this repository in Dashboard → Plugins & MCPs → Import from Repo
(https://github.com/Olbrain/alchemist-plugin).
The canvas is Claude Code only.
GitHub Copilot
copilot plugin marketplace add Olbrain/alchemist-plugin
copilot plugin install alchemist@alchemist
This installs the Alchemist skills and connects the MCP server in Copilot CLI. Ask Copilot to use Alchemist and sign in with your Olbrain account when the browser opens. The canvas is Claude Code only.
claude.ai and Claude Code on the web
Add a custom connector with the URL https://alchemist.olbrain.com/mcp/
(Customize → Connectors → Add custom connector; on Team and Enterprise plans an owner adds it
under Organization settings → Connectors). Then click Connect and sign in.
How a build works
| Stage | What happens | Your call |
|---|---|---|
01 Brief |
Your coding agent drafts what you asked for (who the agent serves, what it does, what it must not do) from your words and your project; Alchemist checks it. | Approve or change it |
02 Plan |
Your coding agent drafts the agents, steps, channels and tools; Alchemist checks it. | Approve or change it |
03 Build |
Alchemist builds the agent, connects its tools and knowledge, and reviews the setup for gaps and contradictions. | Sign in to tools or add keys when a card asks |
04 Test |
Your coding agent writes the tests; Alchemist checks them, runs them on the draft and grades them. A job gets a live run on a real input first. | Run the live test, or not yet |
05 Publish |
The tested version is published, with a 30-day free trial for a new agent. | Publish, or not yet |
06 Go live |
Embed code, API and SDK steps, or the channel it answers on. | You run the commands |
Alchemist gives one stage at a time and refuses a step taken out of order. Builds started in
Noesis, and plugin builds while Olbrain moves accounts over, are still planned by Alchemist's
own model through the alchemist tool; the skill switches by itself.
On a build Claude plans, each agent has a budget: six passes per fix round, a stop after three passes in a row without a gain, four failed compiles and 120 draft test runs. When a build reaches one, Claude shows the best result so far and asks whether to continue (two more passes). A stronger model usually gets a build through its tests first time.
Before Alchemist publishes an agent, makes it live, merges agents or changes how one behaves,
it stops with an approval card. You decide how many of these Claude answers for you:
tell it in the chat, or put it in your CLAUDE.md, AGENTS.md or GEMINI.md, for example "Approve
plans and tests yourself; ask me before publishing." If you haven't said, Claude answers
every card itself in auto mode (Codex: running without approvals; Antigravity: set to proceed
without asking) and asks you otherwise.
It still asks for what only you can do, like sharing a Drive folder or a browser step.
On a build Claude plans, removing an agent, forgetting a customer, renaming or moving an
agent, changing a job's email address, and publishing despite failing tests always need your
own yes. Claude Code shows the card in its own dialog for you to confirm (type the agent's
name for anything that can't be undone); other apps give you a link to answer it in the
browser. If Claude Code gives you a link instead, run /mcp and reconnect Alchemist.
If Claude Code blocks an answer, answer the card on its build page, or allow the tool with
/permissions: mcp__plugin_alchemist_alchemist__alchemist_answer when installed as the plugin,
mcp__claude_ai_Alchemist__alchemist_answer when added as a claude.ai connector.
Use it
- Ask in plain words: "Use Alchemist to build an agent that answers questions about our pricing and hands refunds to a person."
/alchemist:build <what the agent should do>starts a build./alchemist:statusshows your account, organisation, builds and any cards waiting on you.- "Pick up my support agent build": Claude finds your build by name and carries on. Builds are private to you; a teammate changes your published agent in a new build of their own. Anything waiting on you comes first, and Claude doesn't start a duplicate.
- "Put my support agent on my website" or "call my intake job when our signup form is sent": Claude adds the chat snippet, or a server route that calls the agent, to your project. It never puts your API key in browser code.
- "Show me my support agent": Claude draws it as a read-only diagram (example below).
- "What can Alchemist do?" or "Can it answer calls on our phone number?": Claude checks the live capability list before saying yes or no.
- "Where is my ticket TKT-…?" or "Raise a ticket: our webhook job didn't run": Alchemist handles your Olbrain support tickets in the same session.
Best practices
Also on docs.olbrain.com.
-
Say who it serves and where it stops. Name who the agent talks to, what it does, what it must never do and when it hands over to a person. Add a few questions real customers ask: they become its tests.
Use Alchemist to build a chat agent for our website visitors. It answers pricing and delivery questions from our FAQ, never promises discounts, and hands refunds to support@acme.com. Customers often ask: "Do you deliver on Sundays?" and "Can I change my order after paying?" -
Build from your project. Start Claude Code or Codex in the folder that holds your docs, site or code. Your coding agent drafts the brief, plan and tests from it, and asks you only for what it can't find.
-
Decide which cards Claude answers. Put the rule in
CLAUDE.md,AGENTS.mdorGEMINI.md(see How a build works). Removing an agent, forgetting a customer and publishing despite failing tests always need your own yes: in Claude Code's dialog, or in the browser. -
Continue a build; don't start another. Say "pick up my support agent build"; a card waiting on you comes first.
still_runningis not an error: don't send the request again. To change a published agent, ask for the change: customers keep the live version until the new one is tested and published. -
Ask before ruling something out. "Can Alchemist …?" checks the live capability list. Charts in the chat, PowerPoint, PDF, Word and Excel files, and a job's multi-sheet Excel workbook are built in. What really can't be built yet, Alchemist reports to the Olbrain team itself.
-
Give a job a real input. Share one real example of what starts it (a webhook body, an email, a file): its live test runs on it before you publish. Say whether a list is one piece of work or many: a report or workbook from a whole list is one run, each invoice in an email is a run of its own. A job that does nothing with its input fails its test.
-
Let the tests drive fixes. Fix what a failing test shows, then test again. Don't start a new build to reset a budget; a stronger model usually gets through first time.
-
Keep keys out of the chat. Cards collect keys, passwords and signing secrets in the browser. If one is pasted into the chat, rotate it. Keep your Olbrain Access Key on your server, never in browser code.
-
Read errors by their code, not their words (Error codes).
service_unavailableis an outage on Olbrain's side: the build is kept, so wait, then say "continue".insufficient_credits: top up, then continue. -
Review it once it's live. "Review how my support agent did this week": Alchemist reads real conversations, groups what went wrong, turns failures into tests and proves a fix on them before you publish it.
Capabilities
Ask Claude "What can Alchemist do?" for the full, current list: it reads
alchemist_capabilities live, so it is never out of date.
You don't pick a type of agent. Describe the work; Alchemist decides.
| Agent | What it is |
|---|---|
| Chat agent | One person talks to it, turn by turn, in chat or by voice. |
| Automatic job | Runs by itself with nobody talking to it. Steps can wait hours or days, stop for a named person's approval (with reminders), call APIs and tools, and notify people. |
| Team of agents | One front door hands each question to the specialist that owns it, and can start automatic jobs. Customers reach it on website chat or WhatsApp. |
| Research agent | A person asks for a report in Noesis; it researches the sources and emails the report. A scheduled job can run it too. |
A job starts on a schedule, a webhook (Stripe, Shopify, GitHub and other signed senders), an email, a team's front door, or a new file in a Google Drive, cloud storage bucket, Dropbox or OneDrive folder. Agents answer on website chat, WhatsApp, Shopify storefront chat, your phone number and Microsoft Teams. They use tools from Olbrain's connector catalog, any REST API or your own MCP server, and answer from their knowledge files. Every agent gets a setup review and tests before it publishes. Anything Alchemist can't build yet goes to the Olbrain team as a request, with an id you can follow up on.
Commands and tools
| Command | What it does |
|---|---|
/alchemist:build <description> |
Start a build |
/alchemist:status |
Your account, organisation, builds and waiting cards |
| Tool | What it does |
|---|---|
whoami |
Who you are signed in as, and your organisations |
create_org |
Create an organisation and make it active |
select_org |
Switch your active organisation (everywhere you are signed in) |
list_members |
Who is in your organisation |
alchemist |
Start a build or add your words to one; on builds Alchemist's own model runs, one builder turn |
alchemist_state |
Where a build stands: its stage, the steps allowed next, waiting cards, budget and news. Marks the news it returns as seen |
alchemist_do |
Take one allowed build step (write the brief, build, write tests, run them, raise a card) |
alchemist_answer |
Send your choice on an approval card |
alchemist_builds |
List your builds, each with a state (running, needs you, stale, in progress, inactive, completed, published, archived, idle) and a readable label |
alchemist_build |
One build: its plan, agents, waiting cards and next step; with wait, follows a running turn and says what Alchemist, Cortex and Synapse did |
alchemist_edit_build |
Rename a build, or archive it (and bring it back), with an optional reason |
alchemist_rate_build |
Rate how a build session went (up or down, with an optional comment) |
alchemist_stop |
Stop the turn a build is running |
alchemist_connect |
Put a live agent on your website or call it from your code |
alchemist_capabilities |
What Alchemist can build and do, read live |
alchemist_show_agent |
One agent, or one of its published versions, as a read-only diagram |
Inviting people and joining an organisation happen in Noesis. Every build can also be opened there.
Error codes
A failed tool call has isError set. Its structuredContent, and its text as JSON, is one envelope:
{"error": {"code": "service_unavailable", "message": "Alchemist is unavailable right now. …", "retryable": true, "reference": "ab12cd34"}}
Branch on code. Show message to the user. reference (on Olbrain failures) finds the call in our logs.
| Code | Meaning | What to do | Retryable |
|---|---|---|---|
invalid_input |
An argument is missing or malformed | Fix it; don't resend as is | no |
not_found |
No such build, agent, card or organisation for this user | Re-read the build or list | no |
conflict |
Clashes with the current state (an op_id reused, a name taken) |
Re-read, then change the call | no |
forbidden |
The user's role doesn't allow it | An owner or admin changes it in Noesis | no |
no_organisation |
No organisation selected | create_org or select_org |
no |
limit_reached |
An account limit (organisations per user) | Tell the user | no |
insufficient_credits |
Out of Alchemist credits | Show the message and its link, then stop | no |
session_ended |
The Olbrain sign-in ended | Sign in to Alchemist again | no |
unauthorized |
No signed-in user on the call | Sign in | no |
unknown_tool |
No tool by that name | Use a listed tool | no |
rate_limited |
Too many calls | Wait, then call once more | yes |
service_unavailable |
Olbrain or its model provider failed; nothing the user did | Tell the user; don't retry in a loop | yes, later |
internal_error |
A bug in Alchemist | Give the user the reference |
no |
The same names are used inside results that succeed as calls:
- A build's
errors[]({code, message}):service_unavailable,insufficient_credits(withtopup_url),too_many_turns(three builds already running),stream_dropped(follow the build withalchemist_build; the turn may still be running),stream_failed. - A step's
op(alchemist_do,alchemist_answer):statusisdone,refusedorbusy. A refusal'sresultis{ok: false, error, hint}:erroris the code andhintsays what to fix. Retry once after fixing it, never unchanged.provider_unavailablemeans the same asservice_unavailable. - Statuses, not errors:
still_runningandqueued(follow withalchemist_buildwait),busy(wait, then send the same call with the sameop_id),already_started(thatrequest_idalready made the build).
Privacy and security
- Every tool call goes to
https://alchemist.olbrain.com, which acts as you in Olbrain. It keeps your Olbrain sign-in encrypted so you stay signed in; remove the connection to end it. - Keys and passwords for tools never pass through the chat. Approval cards collect them into your organisation's vault.
- Nothing goes live, merges or changes behaviour without an approval card. You answer it, or Claude does where you have let it: in auto mode it answers every card unless you tell it otherwise (see How a build works). What can't be undone, and publishing despite failing tests, always needs your own yes. Outside auto mode, Claude Code also asks your permission before sending each answer.
- Draft test runs, probes and compiles are counted per developer per day, to keep builds within their budget. Pricing does not change.
- Once an agent is live, its go-live steps call Olbrain's agent API at
https://webhook.olbrain.comwith your organisation's API key — to test it, upload a file for a job, start a job, or from the server route Claude adds to your app. You run those commands yourself, and the key stays in your own environment.
Olbrain's privacy policy and terms.
Links
olbrain.com · Noesis · Docs · Developers · Support
Licence
This plugin (its skills, commands and manifests) is MIT licensed. The Alchemist service it connects to at alchemist.olbrain.com is not part of it: using the service is covered by Olbrain's terms.
Olbrain Alchemist MCP 질문
Olbrain Alchemist MCP를 Claude Code에 추가하려면 어떻게 하나요?
터미널에서 claude mcp add --transport http alchemist-plugin https://alchemist.olbrain.com/mcp/를 실행합니다. 모든 프로젝트에서 사용할 수 있게 하려면 --scope user를 추가합니다.
Olbrain Alchemist MCP를 Cursor에 추가하려면 어떻게 하나요?
~/.cursor/mcp.json를 열고 mcpServers 아래에 서버를 추가합니다. 위 설치 섹션에 표시된 Cursor 구성을 사용합니다.
Olbrain Alchemist MCP는 어떤 도구를 제공하나요?
16개 도구를 제공합니다. 예: whoami, create_org, select_org, list_members, alchemist.
Alchemist로 무엇을 할 수 있나요?
Alchemist를 사용하면 평이한 언어로 agent를 설명할 수 있으며, Claude가 이를 바탕으로 Olbrain 조직 내에서 계획, 빌드, 테스트 및 게시를 수행합니다.