opencode-bridge

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

8/8 tools missing one or more hints — delegate_task (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); continue_task (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); task_progress (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +5 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

3 tools describe read intent but their handlers mutate — abort_task (line 185: spawn("schtasks", ["/Run", "/TN", "opencode-serve"], { detached: true, stdio: "ignore" })); list_tasks (line 185: spawn("schtasks", ["/Run", "/TN", "opencode-serve"], { detached: true, stdio: "ignore" })); list_models (line 185: spawn("schtasks", ["/Run", "/TN", "opencode-serve"], { detached: true, stdio: "ignore" }))

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

Tool test coverage

Only 1/8 tools referenced in tests (13%)

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

Shell command execution

1 child_process/subprocess call in production code — runs shell commands (src/index.ts:185)

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

Secrets stay with their owner

2 secret/sensitive values flow into network calls (MCP_SSE_TOKEN_ENV → dynamic, MCP_SSE_TOKEN_ENV → dynamic)

Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)

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

Tool description accuracy

abort_task: description implies read-only but handler writes/deletes/executes; list_models: description implies read-only but handler writes/deletes/executes

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