Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
Glama couldn't complete the latest health check. 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.
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.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
scan_textSecurity scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Deterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM.
Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.
Add one secure layer between your agents and this server.
