classifinder-mcpofficial
A
licenseA
qualityB
maintenanceEnables AI agents to scan text for leaked secrets and prompt injection markers, and redact them before reaching an LLM.
2
1
MIT
prompt-guard-mcp
Server Details
Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
TDQS
Score is being calculated.
Available Tools
2 toolsget_agent_wallet_statusInspect
Returns the calling agent's remaining free quota, USD balance, and total tokens saved.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | No |
scan_prompt_injectionInspect
B2A Indirect Prompt Injection & Jailbreak Firewall (0.005 USDC via x402): Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized text.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Untrusted text or HTML snippet to scan for hidden prompt injection or jailbreak payloads |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
- First observed
get_agent_wallet_status - First observed
scan_prompt_injection
Related MCP Connectors
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.
Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
1
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables 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
- AlicenseNot gradedqualityAmaintenanceProtects AI agents from prompt injection attacks, jailbreak attempts, and common web vulnerabilities by screening untrusted input through semantic LLM analysis and static pattern matching.210 npm2ISC
- AlicenseNot gradedqualityBmaintenanceEnables content inspection, sanitization, containment, and quarantine for LLM security, preventing prompt injection and credential leaks.MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.