ielts-speaking-coach MCP Server

All four hints declared on every tool

9/9 tools missing one or more hints — initialize_ielts_workspace (missing: idempotentHint); set_training_selection (missing: idempotentHint); open_dashboard (missing: idempotentHint), +6 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.

Tool annotations match behaviour

4 read-only tools perform write/delete/exec — get_training_context (line 70: fs.mkdir(reportsDir, { recursive: true })); list_question_bank (line 70: fs.mkdir(reportsDir, { recursive: true })); list_practice_history (line 70: fs.mkdir(reportsDir, { recursive: true }))

Either remove the readOnlyHint:true annotation, or remove the write/delete call from the tool handler.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — open_dashboard deletes at line 670 (fs.unlink(resolved))

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

3 tools describe read intent but their handlers mutate — get_training_context (line 70: fs.mkdir(reportsDir, { recursive: true })); list_question_bank (line 70: fs.mkdir(reportsDir, { recursive: true })); list_practice_history (line 70: fs.mkdir(reportsDir, { recursive: true }))

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

Tool inputs are validated

6/9 tool handlers declare input schemas (67%)

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

Tests exist

No test files found

Add tests that exercise each declared tool.

No eval / new Function

1 eval() or new Function() call — dynamic code execution

Replace eval / Function with explicit parsing or safer alternatives.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.17.5 (high), @modelcontextprotocol/sdk@1.17.5 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

4 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Tool description accuracy

3 tools have description/behavior mismatches: get_training_context: description implies read-only but handler writes/deletes/executes; list_question_bank: description implies read-only but handler writes/deletes/executes; list_practice_history: description implies read-only but handler writes/deletes/executes

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