cybersecurity-vuln-mcp

Tool annotations

9/53 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

47/53 tools missing one or more hints — entity_search_global (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); entity_get_lei_record (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); entity_search_uk_companies (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +44 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.

Descriptions match behaviour

2 tools describe read intent but their handlers mutate — intel_company_news (line 151: itemRegex.exec(xml)); intel_company_profile (line 151: itemRegex.exec(xml))

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

Tool inputs are validated

52/53 tool handlers declare input schemas (98%)

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

Tool handlers catch errors

43/53 tool handlers wrap calls in try/catch (81%)

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

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

1 child_process call — runs shell commands

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

Tool description accuracy

intel_company_news: description implies read-only but handler writes/deletes/executes; intel_company_profile: description implies read-only but handler writes/deletes/executes

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