Expo Agent Bridge
NPM · EXPO-MCP-BRIDGE
Let AI agents see, tap, type, scroll, screenshot and debug your Expo app on a real phone.
Available components
Last scanned (19 hours ago)
Scores higher than 38% of npm servers
Category Testing and QA
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- A known CVE affects braces, but no fixed version has been published, so there is nothing to upgrade to. View diagnostics → Partial
- No install/post-install scripts declared.Pass
- 77 of 273 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability66
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1303 tokens (~76/item across 17 items; 17 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage91
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 72% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "app_eval" implies "eval" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 22 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 21 Oct 26 51
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 23 Oct 2026 · Analysed npm/expo-mcp-bridge@0.3.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-vfj7-8cjw-p6xm | CVE-2026-93687 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | no |
Background: What a vulnerability scan can and cannot prove →
Dependencies 273 packages
| Packages resolved | 273 |
|---|---|
| Stale | 77 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
app_batch ~100
Run several actions in one call (fastest way to fill forms or walk a flow). Returns the screen once at the end. Steps: {action:"tap"|"type"|"scroll"|"toggle"|"navigate"|"wait"|"dismiss_keyboard", ...that tool's args}.
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | full screen instead of a diff |
| snapshot | boolean | – | report the screen afterwards (default true) |
| steps | array | yes | – |
No output schema declared.
No examples provided.
app_dismiss_keyboard ~16
Hide the on-screen keyboard.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
app_eval ~52
Run JavaScript inside the app (dev only) and return the JSON result. Expression or statements with return. `bridge` and `RN` (react-native) are in scope.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
No output schema declared.
No examples provided.
app_layout ~52
Positions (dp, window coordinates) and font sizes of elements on the current screen. For layout checks and visual work; app_snapshot is cheaper for acting.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | max elements, default 250 |
No output schema declared.
No examples provided.
app_logs ~80
Console logs and JS errors captured in the app.
| Name | Type | Req | Description |
|---|---|---|---|
| clear | boolean | – | – |
| level | string | – | "error" = errors only, "warn" = warnings and errors |
| limit | integer | – | default 50 |
| search | string | – | – |
| since | integer | – | only entries after this cursor (returned as "cursor") |
No output schema declared.
No examples provided.
app_navigate ~80
Open a route (expo-router path like "/settings") or a full deep link.
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | full screen instead of a diff |
| path | string | yes | – |
| replace | boolean | – | replace the current screen instead of pushing (keeps the stack shallow) |
| snapshot | boolean | – | report the screen afterwards (default true) |
No output schema declared.
No examples provided.
app_network ~77
HTTP requests made by the app (fetch/XHR) with status, timing and truncated bodies.
| Name | Type | Req | Description |
|---|---|---|---|
| bodies | boolean | – | include request/response bodies (default false) |
| failedOnly | boolean | – | – |
| limit | integer | – | default 30 |
| search | string | – | substring of URL |
| since | integer | – | – |
No output schema declared.
No examples provided.
app_reload ~19
Reload the JS bundle (like pressing r in Metro).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
app_screenshot ~140
JPEG screenshot of the app. Use only for visual/layout questions; app_snapshot is cheaper for finding elements. With saveTo, writes the file and returns only its path (no image tokens).
| Name | Type | Req | Description |
|---|---|---|---|
| area | string | – | auto (default) = visible screen; window = whole window incl. overlays |
| fullScroll | boolean | – | capture the whole content of the main scroll view as one tall image |
| maxWidth | integer | – | pixels, default 400 |
| quality | number | – | 0-1, default 0.6 |
| saveTo | string | – | file path (.jpg) to save instead of returning the image |
No output schema declared.
No examples provided.
app_scroll ~123
Scroll a list/ScrollView (first one on screen if no target).
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | – | pixels, default ~70% of screen |
| direction | string | – | – |
| full | boolean | – | full screen instead of a diff |
| ref | string | – | ref from the last snapshot, e.g. "e4" |
| snapshot | boolean | – | report the screen afterwards (default true) |
| testID | string | – | testID prop of the element |
| text | string | – | visible label/placeholder (exact match first, then contains) |
No output schema declared.
No examples provided.
app_snapshot ~51
Compact text outline of the current screen (buttons, inputs, text, lists) with refs like [e3] to act on. Prefer this over screenshots.
| Name | Type | Req | Description |
|---|---|---|---|
| maxLines | integer | – | default 400 |
No output schema declared.
No examples provided.
app_status ~23
Check whether the mobile app is connected and show device info. Call first.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
app_tap ~114
Press a button/pressable element. Returns what changed on screen plus any new errors.
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | full screen instead of a diff |
| long | boolean | – | long press |
| ref | string | – | ref from the last snapshot, e.g. "e4" |
| snapshot | boolean | – | report the screen afterwards (default true) |
| testID | string | – | testID prop of the element |
| text | string | – | visible label/placeholder (exact match first, then contains) |
No output schema declared.
No examples provided.
app_toggle ~103
Flip a Switch (or set it with value).
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | full screen instead of a diff |
| ref | string | – | ref from the last snapshot, e.g. "e4" |
| snapshot | boolean | – | report the screen afterwards (default true) |
| testID | string | – | testID prop of the element |
| text | string | – | visible label/placeholder (exact match first, then contains) |
| value | boolean | – | – |
No output schema declared.
No examples provided.
app_type ~137
Set text in an input (replaces by default). Target by ref, testID, or placeholder text.
| Name | Type | Req | Description |
|---|---|---|---|
| append | boolean | – | – |
| full | boolean | – | full screen instead of a diff |
| ref | string | – | ref from the last snapshot, e.g. "e4" |
| snapshot | boolean | – | report the screen afterwards (default true) |
| submit | boolean | – | fire onSubmitEditing (like pressing enter) |
| testID | string | – | testID prop of the element |
| text | string | – | visible label/placeholder (exact match first, then contains) |
| value | string | yes | – |
No output schema declared.
No examples provided.
app_wait ~69
Wait until text or a testID appears (or disappears with gone=true). Cheaper than polling snapshots.
| Name | Type | Req | Description |
|---|---|---|---|
| gone | boolean | – | – |
| testID | string | – | – |
| text | string | – | – |
| timeout | integer | – | ms, default 5000, max 30000 |
No output schema declared.
No examples provided.
device_key ~67
Press a hardware/system key on an Android device via adb (USB or Wi-Fi debugging): volume_up, volume_down, mute, back, home, app_switch, enter, tab, delete, power, menu, escape.
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | – |
| repeat | integer | – | – |
No output schema declared.
No examples provided.
How do I install the Expo Agent Bridge MCP server?
Expo Agent Bridge runs locally as an npm package, launched with npx -y expo-mcp-bridge. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · expo-mcp-bridge
claude mcp add rudrasamadhiya-expo-mcp-bridge -- npx -y expo-mcp-bridge
What is the Expo Agent Bridge MCP server?
Expo Agent Bridge is an MCP server listed in the public MCP registry as io.github.Rudrasamadhiya/expo-mcp-bridge. Let AI agents see, tap, type, scroll, screenshot and debug your Expo app on a real phone. This page covers its npm package (expo-mcp-bridge).
Is the Expo Agent Bridge MCP server safe to use?
Expo Agent Bridge scores 66 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 23 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Expo Agent Bridge MCP server expose?
Expo Agent Bridge exposes 17 tools: app_status, app_snapshot, app_layout, app_screenshot, app_batch, and 12 more. Their descriptions and schemas cost roughly 1,303 tokens of context every time the server is loaded.
Is the Expo Agent Bridge MCP server still maintained?
Expo Agent Bridge is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Expo Agent Bridge MCP server under?
Expo Agent Bridge declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.