A
licenseNot graded
qualityB
maintenanceInput/output safety gate for AI agents: detect prompt-injection/jailbreak, leaked secrets/PII, and URL/IP reputation. Deterministic, no LLM.
427 npm
1
MIT
sigma-gate
Server Details
Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.
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.
- Status
- Unhealthy
- Uptime
- 0.0% over 41 days
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- spektre-labs/sigma-gate
- GitHub Stars
- 0
- Server Listing
- sigma-gate
TDQS
A4.3/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have distinct purposes: 'guard' performs security checks on content, while 'guard_selftest' is a self-test to verify the guard works. There is no overlap or ambiguity.
Naming Consistency5/5
Both tool names use a consistent 'guard_' prefix with clear, descriptive suffixes. The naming pattern is uniform and predictable.
Tool Count4/5
With only 2 tools, the set is minimal but appropriate for a single-purpose security gate server. The self-test tool is a helpful addition without overcomplicating the surface.
Completeness4/5
The main tool covers the core capability—detecting secrets, injections, and PII—with a clear output. The self-test ensures functionality. Minor gaps like custom configuration or per-threat-class calls are absent but not essential.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
- First observed
guard - First observed
guard_selftest
Related MCP Connectors
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Deterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM.
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables deterministic zero-trust security for AI agents, providing prompt injection protection, PII scrubbing, and policy enforcement before agentic actions reach production systems.2Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides a pre-flight/post-flight firewall for LLM calls with comprehensive detection, classification, policy enforcement, reversible redaction, output safety, and immutable audit logging.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables scanning LLM prompts and responses for prompt injection, jailbreaks, PII leakage, secret leakage, and other malicious content using deterministic rules, returning verdicts and safe redacted text.1MIT
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.