Damn Vulnerable Model Context Protocol (DVMCP)

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

49/49 tools missing one or more hints — get_user_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_user_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_company_data (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +46 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 — file_manager deletes at line 42 (os.remove(path)); execute_python_code deletes at line 77 (os.unlink(temp_file_path))

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 — port_scan (line 127: result = subprocess.check_output(command, shell=True, stderr=subprocess.STDOUT)); get_weather (line 41: with open(state_file, 'w') as f:)

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

Tool inputs are validated

46/49 tool handlers declare input schemas (94%)

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

Tool handlers catch errors

25/49 tool handlers wrap calls in try/catch (51%)

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

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tests exist

No test files found

Add tests that exercise each declared tool.

No access to sensitive paths

Reads sensitive paths: /tmp/dvmcp_challenge3/private/system_credentials.txt, /tmp/dvmcp_challenge8/sensitive/credentials.txt

Remove reads of sensitive system paths. If you genuinely need them, document why in the README.

Shell command execution

5 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

port_scan: description implies read-only but handler writes/deletes/executes; get_weather: description implies read-only but handler writes/deletes/executes

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