mcp-server-ollama-deep-researcher

Tool annotations

No tools have read-only/destructive annotations

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

All four hints declared on every tool

3/3 tools missing one or more hints — research (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); configure (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). 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

1 tool describes read intent but its handler mutates — research (line 120: spawn(command, [)

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

Tool inputs are validated

2/3 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.

Shell command execution

1 child_process/subprocess call in production code — runs shell commands (src/index.ts:120)

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

Secrets never reach shell commands

1 secret value passed to shell commands — possible command injection

Never pass secrets through shell commands. Use library APIs that accept credentials as arguments.

Secrets not logged

1 secret value sent to console.log

Redact or omit secret values from log output.

Tool description accuracy

research: description implies read-only but handler writes/deletes/executes

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