Bawwab: Top 302 scan

opensearch-mcp-server-py

Not malicious, needs a look Reviewed: expected behaviour

Bawwab's static rules found patterns that deserve a human look. This is not a finding that the package is malicious; the review notes below say what each pattern turned out to be.

Why it was flagged

The static rules marked this “Not malicious, needs a look” because of:

Kind
MCP server
Source
pypi
Version
0.12.0
Popularity
38,343 PyPI downloads/week (2026-11-20)
Link
https://pypi.org/project/opensearch-mcp-server-py/0.12.0/
Scanned
2026-11-20T22:15:53+00:00
Scan time
4.0 s
Review note: Both flags come from an opt-in installer command that registers the server and its memory hooks in the user's AI client configs.

Findings (2)

credential-access: Touches credentials or secrets high

src/mcp_server_opensearch/install_hooks.py:12

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

- Claude Code: Patches hooks map in .claude/settings.json

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The 'install-hooks --client claude-code' command, run by the user, adds a UserPromptSubmit hook (echoes a 'search memory' prompt) and a Stop hook (asks the agent to save facts to memory) to .claude/settings.json. The base64 in the Stop hook only encodes that JSON prompt. Documented in the module docstring.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

src/mcp_server_opensearch/installer.py:38

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

'mcp_path': Path.home() / '.claude.json',

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The installer writes the server's MCP entry into ~/.claude.json (or the Kiro or Cursor config) when the user runs the install command. It reads no secrets.

Reviewed by Claude (AI-assisted review), 2026-11-21

1 low-severity notes (informational, do not affect the result)

install-dir-access: Reads or writes Claude's install folders low

src/mcp_server_opensearch/install_hooks.py:236

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

return Path('.claude') / 'settings.json'

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

Dispute this result

Maintainer and think this is wrong? Open a dispute on GitHub with the target id mcp-pypi-opensearch-mcp-server-py-da5d72.