Security overview
MCP activity across your production agent estate · last 24 hours
Recent decisions
Policy outcomes in real time
| Agent / tool | Decision | Policy | Time |
|---|
Highest-risk identities
Policy coverage
Interceptor stream
Inspect every agent-to-tool decision and the policy path behind it.
| Agent / tool | Identity | Decision | Latency | Policy | Time |
|---|
Policy studio
Define, test, and deploy neutral controls across every adapter.
Production policies
Policy simulator
No production impact
Matched P-01 · amount exceeds $500 threshold. No downstream call was made.
Agents & MCP servers
Identity, trust, capabilities, and schema integrity in one inventory.
Approval queue
High-impact actions waiting for a human decision.
Audit & compliance
Tamper-evident evidence for every identity, policy, decision, and tool call.
Audit readiness
Evidence chain is complete through Oct 12, 2026 · 15:13 EDT.
Evidence ledger
Cryptographically chained entries
| Entry | Event | Actor | Control | Integrity | Timestamp |
|---|
Adapters
Native enforcement points connect the neutral MCP policy core to each platform.
Settings · 系统设置
Salesforce connection profiles (dev / test / prod) and global settings. Secrets are always masked.
Only one environment is active at a time. The adapter reads the active one per request — no restart needed. Switching environment requires re-running OAuth connect for that org.
admin: 全部权限 · approver: 审批+查看 · viewer: 只读。所有用户登录都需要 TOTP 二次验证。
Blocked tool call
evt-9f32 · trace trc-d10f78a2
Salesforce 连接设置指南 · Setup guide
OAUTH CALLBACK · THREE STEPS
新建策略 · New policy
WHO / WHAT / ACTION → ALLOW · DENY · ESCALATE