Compatibility should be demonstrated through the actual client, not inferred from a familiar filename. Muse's existing record has a narrow scope and cannot certify another client's plugin format.
- 1Documented format
- 2Client install
- 3Discovery
- 4Bounded task
Work through the example
Preserve positive and negative fields in the verification record. Leave unsupported client capabilities explicitly unknown.
Start with a disposable branch and synthetic data. Write the expected outcome before changing the implementation, then keep the first failing result. This prevents a later repair from quietly redefining the task. The procedure below is grounded in the repository reference; its examples must still be checked against your project and installed toolchain.
Implementation reference
The following focused section is adapted from the maintained project guide. It preserves the source’s examples and limitations.
{
"checkedAt": "2026-09-16T23:07:13.850Z",
"museVersion": "Muse Code 1.3.0 (1.3.0-R3233.1)",
"serverPackage": "ios-agent-mcp",
"serverVersion": "2.7.0",
"toolCount": 36,
"tools": [
"review_app_intents",
"review_swift_concurrency",
"review_swift_architecture",
"review_swiftui",
"check_availability_guards",
"audit_app_store_readiness",
"analyze_swift_project",
"lint_skill",
"review_swift_memory",
"review_swift_security",
"review_swift_testing",
"review_swift_performance",
"search_apple_technologies",
"get_apple_technology",
"get_apple_updates",
"plan_ios_app",
"plan_app_icon",
"search_local_references",
"read_local_reference",
"get_reference_outline",
"simulator_list",
"simulator_boot",
"simulator_shutdown",
"install_app",
"launch_app",
"terminate_app",
"open_deep_link",
"screenshot",
"build_project",
"run_tests",
"simulator_environment",
"simulator_show",
"simulator_preview_start",
"simulator_preview_stop",
"create_app",
"prepare_issue_report"
],
"stopHookExecuted": true,
"provider": "echo",
"modelSessionVerified": false,
"prePostHooksVerified": false,
"observerVerified": false
}
Acceptance and failure review
| Checkpoint | What to inspect | If it does not match |
|---|---|---|
| Documented format | Confirm the input and environment | Preserve the failure and return to this step |
| Client install | Inspect the intermediate artifact | Preserve the failure and return to this step |
| Discovery | Run the focused check | Preserve the failure and return to this step |
| Bounded task | Record the observed result | Preserve the failure and return to this step |
Ask the agent to explain the smallest change that resolves the observed mismatch. Keep unrelated refactors out of the repair. A change that makes a warning disappear is not enough if the behavior or ownership contract has changed. Re-run the same acceptance check so the before and after results are comparable.
Evidence and limits
Antigravity packaging and a Muse model-driven session are blocked pending real client tests.
This is an educational guide. Its presence in the series does not certify a completed client-specific lab. The series evidence record separates executed checks from exercises and blocked environments.
Inspect the source used in this lesson.
Related reading
- Which Muse Code MCP settings actually work with a local Swift review server?
A reproducible Muse 1.3.0 connection check, with the exact configuration and clear limits on what discovery proves.
- Gemini CLI: connect once and review one iOS feature
Avoid duplicate connections and keep setup evidence separate from app evidence.
What to do next
Next: Verifying a skill across clients: the client verification record method