MCP Tool Integration · Public

agent-device

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configurationPermission boundariesAcceptance checks

Best fitDevelopers who need Claude, Cursor, Codex, or another MCP-capable AI host to call external tools safely.

Check whether this project matches your task before installing it.

What it can doMCP setup guidance, host configuration checks, tool permission boundaries, recovery steps, and acceptance checks

Review the portable capability path.

Before continuingVerify in a sandbox

Do not treat a preview pack as a proven local install.

GitHub snapshotstars unavailable

forks unavailable · contributors unavailable

Doramagic.ai Last verification date: 2026-06-20 Verification method: source evidence, semantic profile, public page gate, and static build acceptance.

Official first step Read manual preview Source repository

Publication status · 2026-06-20

What is agent-device?

agent-device helps connect external tools, services, or data sources to AI hosts that support MCP.
Best fit: Developers who need Claude, Cursor, Codex, or another MCP-capable AI host to call external tools safely.
Not for: Not for users who cannot change host configuration, grant tool permissions, or isolate network, file, and credential access.
Capability added to an AI workflow: MCP setup guidance, host configuration checks, tool permission boundaries, recovery steps, and acceptance checks
First safe verification step: Verify the MCP server command, permission scope, and rollback path in a non-primary host configuration first.
Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
Top risk: May increase setup, validation, or first-run risk for the user.
Evidence base: https://github.com/callstack/agent-device, https://www.npmjs.com/package/agent-device, https://github.com/callstack/agent-device#readme, Human Manual

Quick decision

Use this section to decide whether the project is worth a deeper read.

Best forDevelopers who need Claude, Cursor, Codex, or another MCP-capable AI host to call external tools safely.

Match the project to your task before installing it.

CapabilityMCP setup guidance, host configuration checks, tool permission boundaries, recovery steps, and acceptance checks

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

Repositorycallstack/agent-device

stars unavailable · forks unavailable

What it can do

Translate the upstream project into concrete capabilities the user can judge before installing.

System Architecture & Daemon

Related topics: Platform Backends & Runtime, AI Agent Integration & CLI Surface

Source: https://github.com/callstack/agent-device / Human Manual

Platform Backends & Runtime

Related topics: System Architecture & Daemon, Replay System & E2E Workflows

Source: https://github.com/callstack/agent-device / Human Manual

Replay System & E2E Workflows

Related topics: System Architecture & Daemon, AI Agent Integration & CLI Surface

Source: https://github.com/callstack/agent-device / Human Manual

AI Agent Integration & CLI Surface

Related topics: System Architecture & Daemon, Replay System & E2E Workflows

Source: https://github.com/callstack/agent-device / Human Manual

Doramagic Pitfall Log

Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.

Source: Doramagic discovery, validation, and Project Pack records

Sources: https://github.com/callstack/agent-device, Human Manual, Project Pack evidence, and downstream validation signals.

Community Discussion Evidence

Project-level external discussion stays visible on the detail page, not only inside the manual.

Starsstars unavailable

Forksforks unavailable

Contributorscontributors unavailable

Licenseunknown

Community Discussion Evidence

12 source-linked items

Review these external discussions before using agent-device with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.

01
Comparisons with https://mobilenext.ai/#products
github / github_issue
02
Apps discovery should default to user-installed apps and make all-apps e
github / github_issue
03
Implement Android CPU and memory sampling in perf payload
github / github_issue
04
Native diagnostics API rollout
github / github_issue
05
Add narrow debug symbols workflow for crash symbolication
github / github_issue
06
Add Android native CPU and Perfetto profiling under perf
github / github_issue
07
v0.17.6
github / github_release
08
v0.17.5
github / github_release
09
v0.17.4
github / github_release
10
v0.17.1
github / github_release
11
v0.17.0
github / github_release
12
v0.16.14
github / github_release

How to start

Only source-backed commands are shown here. Verify them in an isolated environment first.

Try the prompt first

Test the workflow without installing the upstream project.

preview

Read the Human Manual

Understand inputs, outputs, limits, and failure modes.

manual

Take context to your AI host

Use the compiled assets in your preferred AI environment.

context

Run sandbox verification

Confirm install commands and rollback before using a primary environment.

verify

npm install -g agent-device@latest

Official start command · https://github.com/callstack/agent-device#readme · verified: yes

Human Manual

The English page must expose the real manual, not a short placeholder.

8+ sections · Human Manual

agent-device Manual

agent-device is a CLI that gives AI agents token-efficient access to iOS, Android, TV, and desktop automation. The Platform Backends & Runtime layer is the abstraction that makes this poss...

Open the full manual

https://github.com/callstack/agent-device Project Manual
Table of Contents
System Architecture & Daemon
Related Pages
Purpose and Scope
Layered Architecture
Runtime and Backend Boundary
Command Families

System Architecture & Daemon

Related topics: Platform Backends & Runtime, AI Agent Integration & CLI Surface

Source: https://github.com/callstack/agent-device / Human Manual

Platform Backends & Runtime

Related topics: System Architecture & Daemon, Replay System & E2E Workflows

Source: https://github.com/callstack/agent-device / Human Manual

Replay System & E2E Workflows

Related topics: System Architecture & Daemon, AI Agent Integration & CLI Surface

Source: https://github.com/callstack/agent-device / Human Manual

AI Agent Integration & CLI Surface

Related topics: System Architecture & Daemon, Replay System & E2E Workflows

Source: https://github.com/callstack/agent-device / Human Manual

Doramagic Pitfall Log

Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.

Source: Doramagic discovery, validation, and Project Pack records

AI Context Pack and portable assets

After deciding to continue, take the project context into your own AI host.

Complete pack plus user-owned assets

These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.

Download complete pack Read Human Manual

BundleComplete Project Pack AssetAI Context Pack AssetBoundary & Risk Card AssetHuman Manual AssetPitfall Log AssetPrompt Preview AssetQuick Start EvidenceREPO_INSPECTION.json

Preflight checks

Treat this page as a planning asset, not proof that your local environment is ready.

The manual is generated from source-linked project files and Doramagic validation signals.
Community evidence warnings stay visible instead of being converted into marketing claims.
This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.

Pitfall Log and verification risks

Doramagic surfaces high-risk items before users treat a candidate capability as verified.

medium

Installation risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Installation risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Configuration risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Capability evidence risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Capability evidence risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Maintenance risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Security or permission risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Security or permission risk requires verification

May increase setup, validation, or first-run risk for the user.