PromptScan
Server Details
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'scan_text' has a clearly defined and distinct purpose: detecting prompt injection attacks in text.
The naming is trivially consistent since there is only one tool. The tool name 'scan_text' follows a clear verb_noun pattern that would be appropriate if more tools were added.
A single tool is too few for a server called 'PromptScan' that appears to be focused on prompt injection detection. While the tool is well-described, a complete security scanning service would typically offer additional capabilities like batch scanning, history/audit logs, configuration management, or different scanning modes.
The tool surface is severely incomplete for a prompt injection scanning service. There's only a single scanning endpoint with no ability to manage scan configurations, view historical results, perform batch operations, or access related security features that would be expected in a comprehensive scanning API.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.
Scan text for prompt injection: risk score, verdict, matched spans. Built by Crypto Money Maker
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to scan untrusted web pages, files, and text for hidden prompt-injection attacks, receive verdicts, risk scores, and findings, reveal concealed characters, and sanitize content before use.MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables agents and applications to detect, inspect, and neutralize prompt injection, jailbreak attempts, and hidden instruction escapes in untrusted text before it is passed into prompts.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to scan untrusted web pages, emails, PDFs, and tool output for prompt injection across 17 languages, returning findings and cleaned text before the agent reads the content.MIT
- AlicenseNot gradedqualityBmaintenanceEnables users to scan untrusted text, files, and directory trees for prompt-injection patterns and receive severity-ranked, explainable verdicts before content reaches an agent. It runs locally and returns clean, review, or blocked verdicts for safer agent input.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.