AI 클라이언트가 EAS를 통해 Expo 빌드 디버깅, 워크플로 실행 관리, 자격 증명 감사 및 앱 업데이트 배포를 수행할 수 있도록 지원합니다.
다른 이름 foreverworks/mcps, eas, @foreverworks/mcp-eas
- 스타
- 5
- Tools
- 23
- 다운로드, 30일
- 645
- 최신 버전
- 0.1.3
- 마지막 커밋
- 2026년 11월 16일
- 라이선스
- MIT
Expo Application Services MCP란?
AI 클라이언트가 EAS를 통해 Expo 빌드 디버깅, 워크플로 실행 관리, 자격 증명 감사 및 앱 업데이트 배포를 수행할 수 있도록 지원합니다. 23개 도구를 제공합니다. 예: health, list_projects, list_builds.
프로젝트 README에서 생성된 요약
Expo Application Services MCP server 정보
이 MCP server는 AI 클라이언트를 사용하는 개발자가 Expo Application Services를 통해 모바일 애플리케이션 라이프사이클을 관리할 수 있도록 지원합니다. 작업 로그, 단계별 결과, Apple 또는 Google의 특정 에러 텍스트를 검사하여 실패한 iOS 또는 Android 빌드를 디버깅할 수 있습니다. 또한 자격 증명을 감사하여 만료 예정인 인증서나 누락된 App Store Connect 키를 식별함으로써 제출 프로세스가 중단되지 않도록 관리할 수 있습니다.
사용자는 Expo 액세스 토큰을 사용하여 server에 연결하며, Developer 역할을 가진 로봇 사용자의 토큰을 파일에 저장하여 사용하는 것이 권장됩니다. 이 server는 Node를 통해 로컬에서 작동하며 Claude Desktop, Cursor, Claude Code와 같은 클라이언트를 지원합니다. 대부분의 작업은 읽기 또는 쓰기 방식이지만, dispatch_workflow 도구는 EAS 빌드 크레딧을 소모하는 워크플로 실행을 트리거하므로 비용 발생 도구로 분류됩니다. 따라서 실행 전 사용자의 명시적인 승인이 필요합니다.
디버깅 외에도 기존 그룹을 프로덕션으로 승격하거나, 롤아웃 비율을 높이거나, 업데이트를 되돌리는 방식으로 앱 업데이트를 관리할 수 있습니다. 또한 App Store 또는 Play Store로의 빌드 제출을 처리하고, 실행 중인 빌드나 워크플로 실행을 취소할 수도 있습니다.
활용 사례
- 1실패한 빌드 디버깅어시스턴트에게 iOS 워크플로 실패를 유발한 특정 원인과 로그 단계를 찾아달라고 요청하세요.
- 2앱 자격 증명 감사향후 30일 이내에 만료되는 인증서가 있는지 또는 필수 키가 누락된 번들 ID가 있는지 확인하세요.
- 3업데이트 롤아웃 관리제어된 롤아웃을 위해 특정 프로덕션 업데이트를 받는 기기의 비율을 높이세요.
- 4자동화된 워크플로 트리거지정된 브랜치에서 특정 GitHub 워크플로 파일을 실행하고 진행 상황을 모니터링하세요.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
Expo Application Services MCP 설치 방법
형식 확인: 2026년 11월 10일Cursor에 추가Goose에 추가Claude Code에 Expo Application Services MCP 설치
$ claude mcp add --env 'EXPO_TOKEN_FILE=<EXPO_TOKEN_FILE>' eas -- npx -y @foreverworks/mcp-easCursor에 Expo Application Services MCP 설치
~/.cursor/mcp.json
{
"mcpServers": {
"eas": {
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-eas"
],
"env": {
"EXPO_TOKEN_FILE": "<EXPO_TOKEN_FILE>"
}
}
}
}VS Code에 Expo Application Services MCP 설치
.vscode/mcp.json
{
"servers": {
"eas": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-eas"
],
"env": {
"EXPO_TOKEN_FILE": "<EXPO_TOKEN_FILE>"
}
}
}
}VS Code CLI에 Expo Application Services MCP 설치
$ code --add-mcp '{"name":"eas","type":"stdio","command":"npx","args":["-y","@foreverworks/mcp-eas"],"env":{"EXPO_TOKEN_FILE":"<EXPO_TOKEN_FILE>"}}'Claude Desktop에 Expo Application Services MCP 설치
claude_desktop_config.json
{
"mcpServers": {
"eas": {
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-eas"
],
"env": {
"EXPO_TOKEN_FILE": "<EXPO_TOKEN_FILE>"
}
}
}
}Codex에 Expo Application Services MCP 설치
$ codex mcp add eas --env 'EXPO_TOKEN_FILE=<EXPO_TOKEN_FILE>' -- npx -y @foreverworks/mcp-easCodex config.toml에 Expo Application Services MCP 설치
~/.codex/config.toml
[mcp_servers.eas] command = "npx" args = ["-y", "@foreverworks/mcp-eas"] [mcp_servers.eas.env] EXPO_TOKEN_FILE = "<EXPO_TOKEN_FILE>"
Gemini CLI에 Expo Application Services MCP 설치
$ gemini mcp add -s user -e 'EXPO_TOKEN_FILE=<EXPO_TOKEN_FILE>' eas npx -- -y @foreverworks/mcp-easGemini settings.json에 Expo Application Services MCP 설치
~/.gemini/settings.json
{
"mcpServers": {
"eas": {
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-eas"
],
"env": {
"EXPO_TOKEN_FILE": "<EXPO_TOKEN_FILE>"
}
}
}
}Expo Application Services MCP 도구 23
README에서 감지됨healthlist_projectslist_buildsget_buildlist_workflowsvalidate_workflowlist_workflow_runsget_workflow_runwait_for_runget_job_logslist_submissionsget_submission
| health | — | |
| list_projects | — | |
| list_builds | — | |
| get_build | — | |
| list_workflows | — | |
| validate_workflow | — | |
| list_workflow_runs | — | |
| get_workflow_run | — | |
| wait_for_run | — | |
| get_job_logs | — | |
| list_submissions | — | |
| get_submission | — |
도구 23개 모두 보기도구 수 줄이기
audit_credentialslist_fingerprintslist_updatescancel_buildcancel_workflow_runset_submit_keysubmit_buildrepublish_updateset_rolloutrevert_rolloutdispatch_workflow
| audit_credentials | — | |
| list_fingerprints | — | |
| list_updates | — | |
| cancel_build | — | |
| cancel_workflow_run | — | |
| set_submit_key | — | |
| submit_build | — | |
| republish_update | — | |
| set_rollout | — | |
| revert_rollout | — | |
| dispatch_workflow | — |
구성
EXPO_TOKEN_FILE필수Path of a file holding an Expo access token.
EAS_PROJECTThe project a call means when it names none, as @account/slug.
| 이름 | 설명 | 유형 |
|---|---|---|
| EXPO_TOKEN_FILE | Path of a file holding an Expo access token. | 필수 |
| EAS_PROJECT | The project a call means when it names none, as @account/slug. |
자동 검사
2026년 11월 12일에 실행됨전체 보고서 →자동 검사를 통과했습니다. 이는 보안 감사가 아닙니다. 코드를 직접 읽고 서버에 필요한 최소한의 권한만 부여하십시오. 검사 방식
- 소스 저장소 연결 및 접근 가능통과
- 오픈 소스 라이선스 (OSI)통과
- 최근 1년 내 커밋 또는 릴리스통과
- 패키지 이름이 인기 패키지와 유사하지 않음통과
- 원격 엔드포인트가 HTTPS 사용검사되지 않음
- 파괴적인 도구에 라벨 표시됨통과
- 모델에 대한 숨겨진 지침 없음통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음통과
README
GitHub에서 보기Expo Application Services MCP server
Find out from your AI assistant why an Expo app's build, workflow run or store
submission failed, through Expo Application Services
(EAS): job logs by step, Apple's or Google's error text, a credentials audit,
fingerprints and update channels. It can also cancel builds and runs, submit
an existing build, republish or roll out an update, set the App Store Connect
key a bundle id submits with, and dispatch a workflow. dispatch_workflow is
the one money tool: your client asks you before each call.
You need an Expo account with an EAS project, and an access token in a file, ideally a robot user's with the Developer role. A dispatch runs a workflow file from the project's GitHub repository, and its build jobs spend build credits on your Expo plan.
What you can ask
- "Why did the last iOS workflow run of @acme/my-app fail?"
- "Does every iOS bundle have a key set for TestFlight submissions, and does any certificate expire in the next 30 days?"
- "Run ios-beta.yml on main and tell me when it finishes."
- "Which fingerprints have updates but no build yet?"
- "Promote the latest update on the staging branch to production."
- "Raise the rollout of the latest production update to 50%."
Install
With Claude Code:
claude mcp add eas -e EXPO_TOKEN_FILE="<path to Expo token file>" -- npx -y @foreverworks/mcp-eas
Claude Desktop (Settings, Developer, Edit Config) and most other clients read the same command as JSON:
{
"mcpServers": {
"eas": {
"command": "npx",
"args": ["-y", "@foreverworks/mcp-eas"],
"env": {
"EXPO_TOKEN_FILE": "<path to Expo token file>"
}
}
}
}
Each runs the published package on Node 22.19 or newer. VS Code and the Claude Desktop bundle ask for each setting as they add the server; leave an optional one empty. Cursor reads each from your environment instead (${env:EXPO_TOKEN_FILE} and so on), so set them before you start Cursor. The commands above set only what is required; Configuration has the rest.
From a clone
git clone https://github.com/foreverworks/mcps.git && cd mcps
npm ci && npm run build
claude mcp add eas -e EXPO_TOKEN_FILE="<path to Expo token file>" -- node "$PWD/servers/eas/dist/index.js"
In a JSON configuration, the command is node and its one argument the full path of servers/eas/dist/index.js. To share one running copy between several clients over HTTP, see docs/deploying.md.
Configuration
| Variable | Required | Meaning |
|---|---|---|
EXPO_TOKEN_FILE |
yes, or EXPO_TOKEN |
File holding the Expo access token. It is read again after a 401, so a replaced token works without a restart. |
EXPO_TOKEN |
no | The token itself (eas-cli's own name), for a local stdio run. |
EAS_PROJECT |
no | The project a call means when it names none and the token sees several: @account/slug, a slug or an id. |
EAS_PRODUCTION_CHANNELS |
no | Comma-separated channel names whose updates reach real users; default production. A republish or a rollout names the ones it reaches. |
EXPO_API_URL |
no | The GraphQL endpoint; default https://api.expo.dev/graphql. |
validate_workflow reads a file given by path from MCP_FILE_ROOTS. That
and the other variables every server shares (transport, limits, what tools
may do) are in docs/configuration.md.
Getting a robot user's token
Make a robot user for the server: it belongs to the account rather than to a person, its role bounds what the server can do, and you can revoke it on its own. At expo.dev, in the account's settings:
- Open Robots and Create robot, with a name that says where it runs.
Give it the Developer role, which is enough for every tool here (build,
submit, credentials; no billing, no members). Viewer limits the server
to the reads: every write then answers
forbidden. - On the robot, Create access token. Expo shows it once: save it in a
file readable only by you (
chmod 600). - Point
EXPO_TOKEN_FILEat that file.
Expo access tokens do not expire; to rotate one, replace the file.
First run
- Ask your assistant to run the EAS
healthcheck. It says whether the token works, as which actor (ideally a robot user), and the accounts and projects it sees. - If it sees several projects, set
EAS_PROJECT, or name the project in each request (list_projectsgives the names). - Ask for a credentials audit (
audit_credentials) to see what is missing or about to expire.
Tools
read changes nothing; write changes something at EAS or in a store without spending build credits; money spends EAS build credits, and your client asks you before each call.
| Tool | Access | What it does |
|---|---|---|
health |
read | The token is accepted; its actor (ideally a robot user), accounts and visible projects. |
list_projects |
read | The projects the token sees, per account: what project takes everywhere. |
list_builds |
read | Builds, newest first, by platform, status, profile, bundle id or package, commit, fingerprint. |
get_build |
read | One build: artifacts, fingerprint, runtime, timings, error; for an ERRORED build the failed step and its line, from the log. |
list_workflows |
read | The project's .eas/workflows files. |
validate_workflow |
read | Checks a workflow file before it runs, at a ref or as a file: valid or not, each problem EAS's validator names, the jobs, and the builds a dispatch would spend credits on. |
list_workflow_runs |
read | Runs, newest first, by file, status or ref; each FAILURE run carries reason, read from its failed jobs' logs. |
get_workflow_run |
read | A run's jobs (type, status, outputs, artifacts) and, when it failed, why per job, with the failed step's tail. |
wait_for_run |
read | Waits for a run or a build to end (up to 14 minutes a call), reporting progress, then answers like get_workflow_run or get_build. |
get_job_logs |
read | A job's log by step: every step's result, and one step's last lines (the failed one by default). |
list_submissions |
read | Submissions with Apple's or Google's error text (for a workflow's submission it lives on the job, which this reads). |
get_submission |
read | One submission, and for an ERRORED one the failed step of its log. |
audit_credentials |
read | Per bundle id and package: certificate and profile with expiry, the App Store Connect key for submissions, push key, keystore fingerprints, Play service account; what is missing, expired or expiring in 30 days. |
list_fingerprints |
read | Fingerprints, newest first or by hash, with the builds and updates that carry each. |
list_updates |
read | Channels and the branches they serve (production marked), and per branch the latest update for each platform and runtime. |
cancel_build |
write | Cancels a queued or running build. |
cancel_workflow_run |
write | Cancels a run that has not ended. |
set_submit_key |
write | Sets or clears the App Store Connect API key EAS submits one bundle id with, by its Apple key id or EAS id; answers with the bundle's audit after. |
submit_build |
write | Submits an existing FINISHED build: iOS to App Store Connect, Android to a Play track; refuses one that differs from expect_version or expect_build_number. |
republish_update |
write | Puts an existing update group on a branch again (a rollback or a promotion), uploading nothing; refuses a group of another project, a signed one, one in a rollout, or one not from expect_commit. |
set_rollout |
write | Raises an update group's rollout to a percentage of its branch's devices; 100 rolls it out to all. The same percentage again changes nothing. |
revert_rollout |
write | Ends a rollout by sending its devices back to the update before it; deletes nothing. |
dispatch_workflow |
money | Runs a workflow file at a git ref the repository already has; its build jobs spend EAS build credits. |
Money
The only way this server starts a build is a workflow run, so
dispatch_workflow is the one money tool. It is marked so in tools/list,
and your client asks you to approve each call (Claude Code does, in every
permission mode). Before the call, the server reads the workflow file at that
ref from EAS (which runs nothing), and the run starts that revision of the
file, so it runs those jobs even if the branch moves in between. With
MCP_CONFIRM=elicit the server asks you itself instead, in one line naming
each build job's platform and profile:
eas: Run EAS workflow ios-beta.yml of @acme/my-app at main: builds ios preview (if its condition holds); may spend EAS build credits.
The line names no commit: EAS keys a revision by its content and reports the commit where it first saw that content, not where the ref points now. A file without build jobs says it spends no build credits.
The other changes spend nothing, so they are write, though a republish or a
rollout reaches a branch's devices at their next launch, production included
(each answer names the production channels it reached), and another republish
undoes it.
submit_build and republish_update take an id the model copies, and a
miscopied one would ship something else unnoticed. So each answer says what
shipped (a build's platform, profile, app version, build number and commit; a
group's project, source branch, commit and message), and each checks what you
expect before sending: expect_version and expect_build_number for a
build, expect_commit (a prefix of 7 or more characters) for a group. A
group from another project is always refused.
Troubleshooting
config: "neither EXPO_TOKEN_FILE nor EXPO_TOKEN is set". Give the
server a token (Getting a robot user's token).
auth. EAS refused the token: the robot or its token was deleted or
revoked. Check them at expo.dev (account settings, Robots) and replace the
token file; it is read again on the next call.
forbidden. The robot lacks the permission: writes need the Developer
role on the project's account. Change its role at expo.dev (account settings,
Members).
not_found. Check the id or name: list_projects, list_builds,
list_workflow_runs and list_submissions give them. A project of another
account answers not_found too.
input. The arguments failed a check here or at EAS: a build or group
other than the one you expected, a rollout percentage lower than now, a ref
that is not a git ref. For a workflow file, issues lists every problem EAS's
validator named, field by field (jobs.build.params.platform: Required).
Nothing changed.
refused. EAS declined as the message says (a build that already ended,
a workflow file that is not on that ref). Nothing changed.
outcome_unknown after a dispatch, a submission or another change. The
connection dropped after the request left, so nobody knows whether EAS acted.
Look first (get_workflow_run, get_build, list_submissions): repeating a
dispatch or a submission does it twice.
A submit job fails at "Prepare credentials" with a message that names
nothing. The bundle id usually has no App Store Connect key set for
submissions, often a development twin of one that has it.
audit_credentials shows it, and set_submit_key sets a key the account
already holds.
wait_for_run answers done: false. The run is waiting for an approval,
or still going after the minutes you gave. Call it again; the run is not
affected.
rate_limited. EAS is throttling the token; wait a minute. api
with status 0 means EAS was unreachable; another status, that it failed:
retry later, and check status.expo.dev if it
persists. drift means EAS's API changed (a query no longer validates):
please report it with the message.
How it works
One GraphQL endpoint, https://api.expo.dev/graphql. A query repeats
after a 5xx or a dropped connection; a mutation is never repeated blind and
fails as outcome_unknown. The projects the token sees are kept for 5
minutes, shared by every client of an HTTP process. EAS answers errors with
HTTP 200 and an errors list, which src/infra/graphqlErrors.ts maps:
*_NOT_FOUND is not_found, VALIDATION_ERROR is input, another USER
error is refused, GRAPHQL_VALIDATION_FAILED is drift.
Queries written from the schema, holding no secret. The queries in
src/infra/easApi/queries.ts come from EAS's introspection and eas-cli
24.10's own, validated against the live schema; EAS validates each one on
every request too, so a removed field fails loudly as drift. None selects a
secret: no P12 or its password, no provisioning profile file, no keystore or
its passwords, no .p8, no FCM key, no environment variable value.
set_submit_key names a key the account already holds; nothing is uploaded.
Logs are signed Cloud Storage URLs, fetched without the token:
brotli-compressed, one JSON object per line. src/domain/logs.ts groups them
by step and picks the line that says why a failed step failed (the last it
printed that is not the builder's "exited with non-zero code").
Rollouts
An update published with eas update --rollout-percentage reaches that share
of the devices on its branch and runtime; the others keep the update before
it. list_updates shows a group's rolloutPercentage. From there:
- Further:
set_rolloutwith a higher percentage moves every platform of the rollout together (or one, withplatform). EAS only lets a rollout grow, so a lower number is refused with a pointer to the revert. At 100 every device gets the update, which ends the rollout. - Back:
revert_rolloutpublishes the update before it on the branch again, naming the rollout it ends (EAS requires that to publish over a rollout in progress). Unlike eas-cli, it deletes no rollout group. A second revert, or one after a newer publish, is refused instead of publishing twice, because the rollout must still be the latest update for its platform and runtime. - Not covered: reverting a rollout with no update before it (the
branch's first on its runtime), which means going back to the update
embedded in the app and needs the project's
expo-updatesversion (eas update:revert-update-rolloutdoes that); and rollouts between two branches on a channel (eas channel:rollout).
Checking a workflow before it runs
validate_workflow answers "will this file run?" without a checkout or
spending anything. Give it workflow and git_ref to check the copy a
dispatch would run, or path for a file you are still editing (inside the
server's file roots; over HTTP, copy it there, or have a script send it as
content_base64 with its sha256). It parses the YAML as a dispatch does
(merge keys on, as EAS reads them), so it lists the build jobs a dispatch
line would name, then asks EAS's own validator, as eas workflow:validate
does. That command also checks that each build job's profile exists in your
eas.json; this cannot.
npx tsx scripts/smoke.ts drives the built server read-only and checks that
dispatch_workflow is the one money tool (--project, --workflow, and
--expect-key <Apple key id> to fail unless every iOS bundle has that submit
key).
Limitations
- No build from a local tree (
eas build, oreas workflow:runwithout--ref). That uploads the working directory, which is slow and can hang, and nobody could see what is built; dispatch at a ref instead. - No
eas updatepublish, only republishing an existing group, and no credential uploads: certificates, profiles, keystores and keys stay whereeas credentialsputs them. submit_builduses what EAS already holds for the build's identifier;audit_credentialssays what is missing first.- The token sees what its robot sees: a project of another account is invisible.
- Rollouts: per-update rollouts only, and no revert to the embedded update (Rollouts).
Other servers for Expo Application Services
Searched 2026-10-15. Expo publishes one, and two community servers touch EAS:
- Expo MCP Server, hosted by Expo: Streamable HTTP, with a person's
OAuth sign-in in a browser. It starts, cancels and reads builds and their
logs; creates, validates, runs, cancels and reads workflow runs and job
logs; submits a finished build; reads TestFlight crashes and feedback, App
Store and Google Play reviews (and replies) and Play crashes; and searches
the docs. With the
expo-mcppackage it drives a local simulator. It is ahead of this one on writing workflows, building from a profile, crashes and store reviews. shipstoreson PyPI: stdio, maintained; five EAS tools that run eas-cli in a project folder, beside many App Store Connect and Play Console tools.expo-mcp-serveron GitHub: stdio; builds, updates and submissions; unchanged since December 2025.
This one adds what they lack: a credentials audit per bundle id and package; submissions listed with Apple's or Google's error text; each failed run's reason in the list itself; fingerprints, update channels and republishing an update group; and setting the App Store Connect key a bundle id submits with. It signs in as a robot user whose role bounds what it may do, with the token in a file, so it can run as a shared service; Expo's server signs in only interactively.
Expo Application Services MCP 질문
Expo Application Services MCP를 Claude Code에 추가하려면 어떻게 하나요?
터미널에서 claude mcp add --env 'EXPO_TOKEN_FILE=<EXPO_TOKEN_FILE>' eas -- npx -y @foreverworks/mcp-eas를 실행합니다. 모든 프로젝트에서 사용할 수 있게 하려면 --scope user를 추가합니다.
Expo Application Services MCP를 Cursor에 추가하려면 어떻게 하나요?
~/.cursor/mcp.json를 열고 mcpServers 아래에 서버를 추가합니다. 위 설치 섹션에 표시된 Cursor 구성을 사용합니다.
Expo Application Services MCP는 어떤 도구를 제공하나요?
23개 도구를 제공합니다. 예: health, list_projects, list_builds, get_build, list_workflows.
실패한 Expo 빌드를 어떻게 디버깅하나요?
이 MCP server를 사용하여 Apple 또는 Google의 단계별 작업 로그와 에러 텍스트에 접근함으로써 빌드, 워크플로 실행 또는 스토어 제출 실패 원인을 파악할 수 있습니다.
이 server를 사용하려면 무엇이 필요한가요?
EAS 프로젝트가 포함된 Expo 계정과 액세스 토큰이 필요하며, Developer 역할이 부여된 로봇 사용자의 토큰을 사용하는 것이 좋습니다.
워크플로를 실행하면 비용이 발생하나요?
네, 워크플로를 호출하면 Expo 플랜의 EAS 빌드 크레딧을 사용하는 빌드 작업이 실행됩니다.