Guides/DevLoop MCP

DevLoop MCP: all 28 tools

QualGent's MCP server gives coding agents hands on real devices — upload builds, run tests, read traces, file bugs, replay routines. Connect once; every tool below appears in your agent's toolbox.

Apps & files

5 tools

One prompt. The agent picks the tool, passes the build, and gets an app id back it can feed straight into the next call.

Coding Agent · devloop mcp

The agent launches the build, then confirms it actually rendered — because the tool tells it to. observe_screen hands back a real screenshot, which is what you see on the device.

Coding Agent · devloop mcp

One prompt. The agent reads back every build in the account — id, name, version and platform — and picks the one to test next.

Coding Agent · devloop mcp

One prompt. The agent resolves the build to a short-lived signed URL, then pulls the binary down — ready to install on a device.

Coding Agent · devloop mcp

One prompt. The agent retires the stale build and reports what it removed — a soft delete, so nothing is lost for good.

Coding Agent · devloop mcp

Test cases

5 tools

One prompt. The agent turns a described flow into a structured test case — steps, expected result and metadata — and gets an id back it can queue straight away.

Coding Agent · devloop mcp

One prompt. The agent patches just the step that changed and bumps the version — the rest of the case stays exactly as it was.

Coding Agent · devloop mcp

One prompt. The agent reads back every test case in the account — id, name, category and platform — and picks what to run next.

Coding Agent · devloop mcp

One prompt. The agent pulls the full case — every step and the expected result — so it knows exactly what to execute before queueing a run.

Coding Agent · devloop mcp

One prompt. The agent uploads a reference file and links it to the case, so the expected state rides along with every run.

Coding Agent · devloop mcp

Test runs

5 tools

One prompt. The agent queues the case on a real device and gets a run id back it can poll — the point where authoring turns into a live run.

Coding Agent · devloop mcp

One prompt. The agent reads the run board — what's running, what passed, what failed and on which device — and decides what to look at next.

Coding Agent · devloop mcp

One prompt. The agent reads the full result — status, duration, step tally and a link to the recorded Loop replay.

Coding Agent · devloop mcp

One prompt. The agent walks the per-step trace — each action, its status and how long it took — to see exactly what happened on device.

Coding Agent · devloop mcp

One prompt. The agent reads back the compiled plan — setup, act, verify — so the run is deterministic and reusable on the next build.

Coding Agent · devloop mcp

Bugs

6 tools

save_bug

File a new bug in your organization.

update_bug

Update an existing bug with sparse edits.

list_bugs

List bugs in your organization.

get_bug

Full detail plus attachment download URL.

attach_run_to_bug

Attach a test run to an existing bug.

attach_to_bug

Attach a local file to an existing bug.

Routines & loops

4 tools

record_routine

Record a multi-step routine agents can replay.

find_routine

Fetch recorded routines for an app and platform.

update_routine

Append a new version to an existing routine.

upload_loop

Convert a recording to MP4 and upload as a Loop.

Devices, credits & credentials

4 tools

list_devices

Available devices grouped by type.

list_categories

All test case categories for your org.

check_credits

Check credits before queueing runs.

list_credentials

Stored credentials — secrets never exposed.

Skills

3 skills

devloop-subagent-router

Routes a mobile QA request to the subagent that owns it.

devloop-troubleshooting

Classifies setup, device, auth and app-runtime failures.

qualgent-bugs

Drives the bug tools; takes a device only to reproduce.

Give your agent hands on real devices

Connect DevLoop and let it close the build → test → fix loop.