Govern AI agent and MCP server access with runtime policy, approvals, guardrails and a signed audit trail, through a documented REST API and an auth-gated MCP endpoint.
- Access
- APIMCP
- Auth
- API Key
- Skills
- 5
Skills
Agent Discovery
List registered agents and published agent templates through paginated discovery endpoints on the Praesidia REST API.
Tool Policy Enforcement
Read and apply tool policies and guardrails that gate which actions a connected agent or MCP server may invoke.
Approval Gating
Inspect pending and resolved approval records for agent actions that require a human decision before they run.
Audit Verification
Verify signed audit records using the published SPKI signing keys, JWKS and did:web identity served at well-known endpoints.
MCP Invocation
Invoke governed agents, tools and workflows over the API-key-gated MCP endpoint under the mcp:invoke scope.
Related Agents
Clawvisor
API · MCPHuman-in-the-loop security gateway for AI agents. Approves, verifies, and audits every API call across Gmail, GitHub…
Arcjet
API · MCP · CLISecures AI agents and apps at runtime: detects prompt injection, enforces tool-call policies, redacts sensitive data…
NVIDIA OpenShell
CLI · APIRuns autonomous agents in isolated sandboxes with kernel-level policy enforcement over files, syscalls, and network…
Onyx Security
APIInspect and block agent activity inline — a control plane that inspects prompts, tool calls, and model responses across…