Expo MCP

Live

API KEY

MOBILE BUILDS

Developer Tools

Expo MCP gives agents authenticated access to your mobile builds: trigger EAS builds, run workflows, triage store crashes, and answer user reviews.

  • Per-user credentials: each call uses the actual user's key, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Expo MCP
agent · Acme Q3
Run
Did the latest iOS build pass, and are there new crashes in TestFlight?
S
expomcp_build_list
96ms
Release agent
Build 214 (iOS, production profile) finished 09:41 UTC. 2 new TestFlight crashes on iPhone 15, both in PaymentSheet, stack traces attached.
Sources: 1 build, 2 crash reports
expomcp
3 tool calls
18:29
Message Claude...

Tools your release agent reaches for on Expo, scoped per user.

CALL ANY TOOL
Run mobile builds end to end: list and trigger EAS builds, read logs, submit to the stores, and triage crashes from TestFlight and Play Vitals.
expomcp_build_list
List builds
List recent EAS builds for a project by appId or full name, the starting point for any status check.
Parameters
Name
Type
Required
Description
appFullName
string
Optional
The full name of the app e.g. @owner/my-app. Either appId or appFullName is required.
appId
string
Optional
The Expo project/app ID (UUID). Either appId or appFullName is required.
limit
number
Optional
Maximum number of builds to return (default: 10, max: 100)
platform
string
Optional
Filter builds by platform
status
string
Optional
Filter builds by status
expomcp_build_info
Get build info
expomcp_build_logs
Get build logs
expomcp_build_run
Trigger build
expomcp_build_submit
Submit to stores
expomcp_workflow_run
Run workflow
expomcp_playstore_crashes
Get Play crashes
expomcp_testflight_crashes
Get TestFlight crashes
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Expo tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["expomcp"], toolNames: [
    "expomcp_build_list",
    "expomcp_build_logs",
    "expomcp_build_run"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Did the latest iOS build pass?" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["expomcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "List the last 5 EAS builds and their status." }],
  tools,
});

// Execute the tool call with the user's vaulted Expo credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["expomcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Pull the logs for the failed Android build." }],
  tools,
});

// Tool call runs with the user's vaulted Expo credential
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["expomcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "expo_release_agent",
  model: "gemini-2.5-pro",
  instruction: "Manage Expo builds and releases for the signed-in user.",
  tools,
});

await agent.run("Trigger a production build for @acme/storefront.");
Try these prompts
Copy any prompt into your agent. Each maps directly to an Expo tool. Click to copy, paste into your agent, done.
Builds and releases
Copy the prompt
Copied
List the last 5 EAS builds and their status.
Copy the prompt
Copied
Trigger a production iOS build and pull the logs if it fails.
Copy the prompt
Copied
Submit the latest passing Android build to Google Play.
Crashes and feedback
Copy the prompt
Copied
Any new TestFlight crashes since yesterday? Show stack traces.
Copy the prompt
Copied
List the top ANR issues from Play Vitals this week.
Copy the prompt
Copied
Pull this week's App Store reviews rated 2 stars or lower.
CI/CD workflows
Copy the prompt
Copied
Run the release workflow for @acme/storefront.
Copy the prompt
Copied
Why did the last workflow run fail? Fetch the job logs.
Copy the prompt
Copied
Validate the new deploy workflow YAML before I merge it.
SEE HOW AUTH WORKS
Your users connect once. Their Expo credentials stay vaulted, every call is scope-checked, and every action is logged.
1
Authorize
Your user connects
Expo MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Expo MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Expo MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Expo MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other developer connectors.
ENGINEERING
DevOps assistant agent
Triage GitHub incidents, open Linear tickets, and notify the on-call channel in Slack with context already attached.
ENGINEERING
Auto-release notes agent
Group merged GitHub PRs by feature, fix, or chore and publish release notes per tag. No manual changelog grooming.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with identity, scope enforcement, and audit. Connectors follow.
01.
Shared tokens break per-user analytics
A shared Expo key looks fine in a demo. In production every build trigger and store submission looks like one service account, and you cannot tell who shipped what. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Expo today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Expo as the user or through a shared key?
As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every build, submission, and review reply in your audit trail is attributed to a real user, not a shared service account.
Where is the Expo API key stored?
In an AES-256 encrypted vault with per-tenant namespacing. Keys are resolved at request time, never enter LLM context, and can be revoked from one dashboard.
Can I limit what the agent does in Expo?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example build_list and build_logs without build_submit or build_cancel. Scalekit also enforces scope checks before every API call.
What happens when a user revokes access?
The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.
Can the agent post public store replies without review?
Only if you allow it. appstore_reply_review and playstore_reply_review publish visible responses, so most teams exclude them via the listScopedTools filter and keep the agent read-only on reviews. Excluded tools are never offered to the model and calls to them are blocked.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""expomcp"": {
""url"": ""https://mcp.scalekit.com/expomcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.expomcp]
url = ""https://mcp.scalekit.com/expomcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""expomcp"": {
""url"": ""https://mcp.scalekit.com/expomcp"",
""type"": ""http""
}
}
}