agentation-mcp
Flagged as possibly malicious Reviewed: expected behaviour
Bawwab's static rules matched a pattern it treats as critical. Read the review notes: a reviewed false alarm is marked as such.
Why it was flagged
The static rules marked this “Flagged as possibly malicious” because of:
exfil.combo: Reads credentials and makes network calls (critical, 1× · first at dist/cli.js:2746)
- Kind
- MCP server
- Source
- npm
- Version
1.3.2- Popularity
- 146,311 npm downloads/week (2026-11-20)
- Link
- https://www.npmjs.com/package/agentation-mcp/v/1.3.2
- Scanned
- 2026-11-20T21:57:01+00:00
- Scan time
- 1.8 s
Review note: A setup and server CLI that checks for the user's local Claude Code config to register or verify its own MCP entry; the file is not sent anywhere.
Findings (2)
credential-access: Touches credentials or secrets high
dist/cli.js:2746
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
const claudeConfigPath = path.join(homeDir, ".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 setup wizard builds the path ~/.claude.json and only checks whether it exists, printing a found or not-found message before running 'claude mcp add' for this server.
Reviewed by Bawwab maintainers, 2026-11-20
exfil.combo: Reads credentials and makes network calls critical
dist/cli.js:2746
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0037 Data from Local SystemMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
const claudeConfigPath = path.join(homeDir, ".claude.json");
What this means: Credential access together with outbound requests in one file is the shape of data theft.
The rule's general advice: Do not install unless the flow is understood and benign. (see the review note for this case)
Expected for what this tool does
The path is only tested for existence in the wizard; the doctor command parses it locally to check for an 'agentation' MCP entry and prints pass or warn. No content from it is transmitted.
Reviewed by Bawwab maintainers, 2026-11-20
Dispute this result
Maintainer and think this is wrong? Open a dispute on GitHub with the target id mcp-npm-agentation-mcp-25c21c.