Agent Switchboard
O

Onyx Security

by Onyx Security

Verified

Inspect and block agent activity inline — a control plane that inspects prompts, tool calls, and model responses across browser AI, coding agents, and MCP servers.

Access
API
Auth
API Key
Skills
3

Skills

  • Inline Guardrails

    Evaluates prompts and responses at call time through pre-call, post-call, and during-call hooks that can block traffic.

  • Tool Call Inspection

    Reviews agent tool invocations against policy before execution, stopping unsafe actions on connected systems.

  • Shadow Agent Discovery

    Surfaces unsanctioned AI agents, browser extensions, and MCP servers running across an organization.

Securityagent-guardrailsruntime-inspectiontool-call-blockingshadow-ai-discoverymcp-securityenterprise-policyai-control-plane
Visit Agent

Related Agents

Archestra

MCP · API

Run MCP servers for an enterprise behind one gateway — a curated registry, dynamic tool loading, prompt-injection…

Verifiedby Archestra · Infrastructure & Ops, Security · 3 skills · OAuth 2.0

Praesidia

API · MCP

Govern AI agent and MCP server access with runtime policy, approvals, guardrails and a signed audit trail, through a…

Verifiedby Squad Technology SRL · Security, Infrastructure & Ops · 5 skills · API Key

OpenSandbox

API · MCP · CLI

Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem…

Verifiedby OpenSandbox Group · Infrastructure & Ops, Code & DevTools · 5 skills · API Key

Arcjet

API · MCP · CLI

Secures AI agents and apps at runtime: detects prompt injection, enforces tool-call policies, redacts sensitive data…

Verifiedby Arcjet · Security, Infrastructure & Ops · 5 skills · API Key
onyx-security
Inspect and block agent activity inline — a control plane that inspects prompts, tool calls, and model responses across browser AI, coding agents, and MCP servers.
fields
nameOnyx Security
providerOnyx Security
urlhttps://www.onyx.security
categoriessecurity
accessapi
authapiKey
streamingfalse
pushfalse
verifiedtrue
officialfalse
tagsagent-guardrails, runtime-inspection, tool-call-blocking, shadow-ai-discovery, mcp-security, enterprise-policy, ai-control-plane
skills
inline-guardrailsInline GuardrailsEvaluates prompts and responses at call time through pr…
tool-call-inspectionTool Call InspectionReviews agent tool invocations against policy before ex…
shadow-agent-discoveryShadow Agent DiscoverySurfaces unsanctioned AI agents, browser extensions, an…
→ https://www.onyx.security