sentinel-scan-cli
sentinel-scan-cli is an MCP server, listed under model apis. It reaches openai. It needs OPENAI_API_KEY to authenticate. Its repository has 1 GitHub star and is licensed under MIT; we last read it on 2026-10-23.
Scans MCP manifests for tool poisoning, prompt injection, and rug-pulls, and provides an OWASP LLM Top 10 prompt-injection/jailbreak analysis for LLM applications using the command line interface. Connects to the MCP server.
Install
MCP servers are packaged differently from each other -- some run via npx, some as a Docker image, some as a plain script you clone and run. sentinel-scan-cli’s own README did not state one plainly enough for this page to quote it rather than guess, so it will not guess. The repository below states it.
What it reaches, and what it needs
Maintenance
MCP security scanner (CLI + MCP server): detects tool poisoning, prompt injection, and rug-pulls in MCP manifests. Also an OWASP LLM Top 10 prompt-injection/jailbreak CLI for LLM apps.
sentinel-scan-cli compared with similar servers
| Server | Reaches | Needs | Stars | Last update | Licence |
|---|---|---|---|---|---|
| sentinel-scan-cli (this page) | openai | OPENAI_API_KEY | 1 | 2026-08-25 | MIT |
| paperbanana | atlascloud, google, openai(1 shared) | ATLASCLOUD_API_KEY, GOOGLE_API_KEY, OPENAI_API_KEY | 2,412 | 2026-09-17 | MIT |
| ms-365-mcp-server | ms365, openai(1 shared) | MS365_MCP_ATTACHMENT_URL_KEY, MS365_MCP_CLIENT_SECRET, MS365_MCP_OAUTH_TOKEN, OPENAI_API_KEY | 1,068 | 2026-10-23 | MIT |
| just-prompt | anthropic, deepseek, gemini, groq, openai(1 shared) | ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, OPENAI_API_KEY | 739 | 2025-08-10 | — |
| flama | anthropic, openai(1 shared) | None listed | 304 | 2026-10-13 | Apache-2.0 |
| mcp-ragdocs | openai, qdrant(1 shared) | OPENAI_API_KEY, QDRANT_API_KEY | 265 | 2025-07-18 | MIT |
Ranked by services in common with sentinel-scan-cli, then by stars. Figures are from each repository when we last read it.
Common questions about sentinel-scan-cli
- What does sentinel-scan-cli do?
- Scans MCP manifests for tool poisoning, prompt injection, and rug-pulls, and provides an OWASP LLM Top 10 prompt-injection/jailbreak analysis for LLM applications using the command line interface. Connects to the MCP server.
- How do I install sentinel-scan-cli?
- Its README did not state an install command plainly enough for us to quote one, so we do not guess. The repository has the instructions: https://github.com/Ventrova/sentinel-scan-cli
- What does sentinel-scan-cli connect to, and what does it need?
- It reaches openai. The credentials we found in its source are OPENAI_API_KEY.
- Is sentinel-scan-cli official and is it maintained?
- We found nothing naming it as a vendor’s official server. Its repository has 1 GitHub star and its state in our directory is listed. Its last commit we recorded was on 2026-08-25.
- What licence does sentinel-scan-cli use?
- The repository declares the MIT licence.
More MCP servers for model apis
- wigolo5,498 stars
- KiCAD-MCP-Server2,905 stars
- modelcontextprotocol2,589 stars
- paperbanana2,412 stars
- gemini-mcp-tool2,294 stars
- telegram-mcp1,879 stars