Server providing Argo CD integration for MCP clients.
Nothing to run from here
Expo Application Services is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
30
downloads a day
local
runs on your machine
537
downloads in 30d
What it does
Find out why an Expo build, workflow run or store submission failed, and roll out updates.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'EXPO_TOKEN_FILE=${EXPO_TOKEN_FILE}' --transport stdio expo-application-services-mcp '--' npx -y @foreverworks/mcp-eas
# 2 — ask your agent for something these tools do
# list_builds, get_build, cancel_build and 20 more
It needs EXPO_TOKEN_FILE: this reads it from your environment, so export it first.
Expo Application Services costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Expo Application Services as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads EXPO_TOKEN_FILE (Path of a file holding an Expo access token) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx EXPO_TOKEN_FILE … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'EXPO_TOKEN_FILE=${EXPO_TOKEN_FILE}' --transport stdio expo-application-services-mcp '--' npx -y @foreverworks/mcp-easReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: EXPO_TOKEN_FILE — Path of a file holding an Expo access token.. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
23 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
A project's builds, newest first, filtered by platform, status, profile, bundle id or package, commit or fingerprint. Each
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| platform | yes | — | |
| status | string | no | — |
| profile | string | no | The eas.json build profile, e.g. "production". |
| app_identifier | string | no | A bundle id or package, e.g. com.example.app.dev. |
| commit | string | no | The full git commit hash the build was made from. |
| fingerprint | string | no | Builds carrying this fingerprint hash. |
| limit | yes | — | |
| offset | yes | — |
One build: its artifacts (the .ipa/.aab URL), fingerprint, runtime version, channel, timings and error. A build that
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build | yes | — | |
| steps | yes | — | |
| lines | yes | — |
Cancel a build that is queued or running. EAS refuses one that has already ended, and says so; nothing else changes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build | yes | — |
Per bundle id (iOS) and package (Android) of a project: the distribution certificate and provisioning profile with their
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| platform | yes | — | |
| identifier | string | no | One bundle id or package. Default: every one the project has credentials for or has built. |
Set (or clear) the App Store Connect API key EAS uses to submit one iOS bundle id, as eas credentials does. Without one,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| bundle_id | string | yes | The iOS bundle id whose submissions use the key, e.g. com.example.app.dev. |
| key | string | no | The App Store Connect API key, by its 10-character Apple key id (e.g. "ABCDE12345") or its EAS id; the account must already hold it. |
| clear | boolean | no | Remove the key set for submissions instead (eas submit for this bundle then fails until one is set). |
Check that the Expo access token is present and accepted: which actor it is (a robot user, ideally), its accounts and the
No parameter schema on file.
The EAS projects this token can see, per account, with their full names (@account/slug) and ids: what every other tool's
No parameter schema on file.
A project's App Store Connect and Google Play submissions, newest first: status, the build (identifier, version, build
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| platform | yes | — | |
| status | string | no | — |
| limit | yes | — | |
| offset | yes | — |
One submission with Apple's or Google's error text; one that ERRORED also carries failedStep from its log (its own, or the
| Parameter | Type | Required | Notes |
|---|---|---|---|
| submission | yes | — | |
| steps | yes | — | |
| lines | yes | — |
Submit an existing FINISHED build: iOS to App Store Connect (TestFlight), Android to a Google Play track. It uses what EAS
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build | yes | — | |
| asc_app_id | string | no | iOS: the App Store Connect app id. Default: the app App Store Connect has for the build's bundle id, asked through its key. |
| what_to_test | string | no | iOS: TestFlight's What to Test; Android: the release notes. |
| groups | array | no | iOS: TestFlight groups to add the build to. |
| track | string | no | Android: the Google Play track. Default "internal". |
| release_status | string | no | Android: the release status on the track. |
| rollout | number | no | Android: the staged rollout fraction, with release_status in_progress. |
| expect_version | string | no | The app version the build must have, e.g. "1.4.2". Checked before anything is submitted, so a wrongly copied build id fails instead of shipping another build. |
| expect_build_number | string | no | The build number the build must have (iOS CFBundleVersion, Android versionCode), e.g. "42". Checked the same way. |
A project's fingerprints (the hash of its native side), newest first, or one by hash: how many builds and updates carry
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| hash | string | no | One fingerprint hash (a build's or a fingerprint job's output). |
| limit | yes | — |
A project's EAS Update channels with the branches they serve (production ones marked), and per branch the latest update for
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — |
Raise an update group's rollout to a percentage of the devices on its branch and runtime, as eas update:edit does; 100 rolls
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| group | string | yes | The update group in the rollout (list_updates shows each branch's latest groups with their rolloutPercentage). |
| percentage | integer | yes | The share of devices to get it, higher than now; 100 rolls it out to every device. |
| platform | yes | Only this platform's update of the group. Default: every platform in the rollout. |
End an update group's rollout by sending every device on its branch and runtime back to the update before it, as eas
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| group | string | yes | The update group in the rollout (list_updates shows each branch's latest groups with their rolloutPercentage). |
| platform | yes | Only this platform's rollout. Default: every platform in it. |
Put an existing update group on a branch again, as eas update:republish does: roll a branch back to an earlier group, or
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| group | string | yes | The update group to put on the branch again (list_updates gives groups). |
| branch | string | yes | The update branch to republish onto, e.g. "production". |
| platform | yes | Only this platform's update of the group. Default: every platform in it. | |
| message | string | no | The new update's message. Default: names the group republished. |
| expect_commit | string | no | The commit the group must have been published from (a hash, or a prefix of at least 7 characters). Checked before anything is published. |
A project's EAS workflow files (.eas/workflows/*.yml), by file name: what list_workflow_runs and dispatch_workflow take.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — |
A project's workflow runs, newest first, optionally of one workflow file, status or ref: status, ref, commit, trigger (a
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| workflow | string | no | The workflow file name, e.g. "ios-build.yml" (the extension may be left out). |
| status | string | no | — |
| git_ref | string | no | Only runs requested at this ref, e.g. "refs/heads/main". |
| limit | yes | — | |
| cursor | string | no | nextCursor from the previous call, to read on. |
| reasons | boolean | no | Read each FAILURE run's failed jobs' logs for its one-line reason (a request or two per failed run). |
One workflow run with its jobs: each job's type, status and outputs (build_id, fingerprint hashes, app_build_version...) and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run | yes | — | |
| lines | yes | — |
Wait until a workflow run or a build ends (give run or build), looking every 15 s, and answer as get_workflow_run or
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run | yes | — | |
| build | yes | — | |
| minutes | integer | no | How long to wait at most (a request over HTTP is cut at 15 minutes by default); call again to keep waiting. |
| lines | yes | — |
A workflow job's log, by step: every step with its result and size, and the last lines of one step (the failed one by
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job | yes | — | |
| step | string | no | A step's name, or part of it. Default: the failed step, else the last. |
| lines | integer | no | How many of the step's last lines. |
Check an EAS workflow file before it runs, the way eas workflow:validate does, without a checkout: the file as the
No parameter schema on file.
Run an EAS workflow file at a git ref the project's GitHub repository already has. EAS reads the file and the code from
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | yes | — | |
| workflow | string | yes | The workflow file name, e.g. "ios-build.yml" (the extension may be left out). |
| git_ref | string | yes | A ref the project's GitHub repository already has: a branch ("main"), "refs/heads/<branch>", "refs/tags/<tag>" or a commit hash. |
| inputs | object | no | The workflow_dispatch inputs the file declares, by name. |
Cancel a workflow run that has not ended, with its running jobs (a build in progress stops spending).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run | yes | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Expo Application Services or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 0.1.2 · scanned 3 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest1c9082f50e7411c5b132c2ec4bfab006835a71a21163871f5b351330e81b0491
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (23 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_builds | no tags | |
| get_build | no tags | |
| cancel_build | no tags | |
| audit_credentials | no tags | |
| set_submit_key | no tags | |
| health | no tags | |
| list_projects | no tags | |
| list_submissions | no tags | |
| get_submission | no tags | |
| submit_build | no tags | |
| list_fingerprints | no tags | |
| list_updates | no tags | |
| set_rollout | no tags | |
| revert_rollout | no tags | |
| republish_update | no tags | |
| list_workflows | no tags | |
| list_workflow_runs | no tags | |
| get_workflow_run | no tags | |
| wait_for_run | no tags | |
| get_job_logs | no tags | |
| validate_workflow | no tags | |
| dispatch_workflow | no tags | |
| cancel_workflow_run | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest1c9082f50e7411c5
Scanned2026-11-03
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.2. Pin a release below and the command asks for exactly that one.
0.1.2
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Expo Application Services can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.