Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-permission-guard evaluate risk of deleting a file"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Intent-based permission system with risk scoring, rule engine, and audit trail. Zero dependencies, pure Python stdlib.
Agents execute destructive actions without guardrails. Binary allow/deny prompts don't work (93% auto-approved). The "lethal trifecta" — private data + untrusted content + external communication — creates risks no single tool can detect.
Related MCP server: AgentWard
MCP Permission Guard classifies tool calls into 14 intent categories, scores risk 0-100, evaluates rules, and produces deterministic allow/deny/ask decisions with full audit trail.
Tool | What it does |
| Map tool call → intent category (14 types) |
| Score 0-100 with lethal trifecta detection |
| Add allow/deny/ask rule by intent |
| Full evaluation: classify + risk + rules → decision |
| Query decision history |
| Show all registered rules |
| Delete a rule |
| Global policy: allow_all / deny_all / ask_all / rules_based |
| Read current policy |
| Decision statistics |
| Clear all state |
filesystem_read (10) · filesystem_write (40) · filesystem_delete (80) · network_outbound (50) · network_inbound (30) · code_execution (60) · shell_command (70) · database_write (65) · database_read (20) · credentials_access (90) · config_change (55) · user_management (85) · service_restart (60) · package_install (75)
python -m pytest tests/ -v # 38 tests, all passingnah — Intent-level permission guards
Open Agent Passport — Pre-action authorization
Beyond Permission Prompts — Structured authorization
Claude Code Auto Mode — Two-stage classifier
MIT — AMEOBIUS
This server cannot be deployed
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
Pre-action allow/deny for AI agents. 24 statutes, 13 jurisdictions: EU AI Act, GDPR, DPDP.
