expo-mcp

Tool annotations

16/48 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

32/48 tools missing one or more hints — automation_tap (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); automation_tap_by_testid (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); automation_take_screenshot (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +29 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

2 tools perform destructive updates without destructiveHint — automation_take_screenshot deletes at line 55 (fs.promises.rm(outputPath, { force: true })); automation_take_screenshot_by_testid deletes at line 55 (fs.promises.rm(outputPath, { force: true }))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Descriptions match behaviour

2 tools describe read intent but their handlers mutate — automation_take_screenshot (line 55: fs.promises.rm(outputPath, { force: true })); automation_take_screenshot_by_testid (line 55: fs.promises.rm(outputPath, { force: true }))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

45/48 tool handlers declare input schemas (94%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

35/48 tool handlers wrap calls in try/catch (73%)

Wrap each tool handler body in try/catch and return a structured error response.

Tool test coverage

Only 0/48 tools referenced in tests (0%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

2 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Tool description accuracy

automation_take_screenshot: description implies read-only but handler writes/deletes/executes; automation_take_screenshot_by_testid: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.