A
licenseA
qualityA
maintenancePolicy-based governance for AI agent tool calls. YAML policies, approval gates, risk assessment, and audit logging across LangChain, OpenAI, Anthropic, and MCP.
5
51 PyPI
15
MIT
MCP Permission Guard
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 Guardevaluate shell_command 'rm -rf /'"
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.
MCP Permission Guard — Pre-Action Authorization for AI Agents
Intent-based permission system with risk scoring, rule engine, and audit trail. Zero dependencies, pure Python stdlib.
The Problem
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: blackwall-mcp
The Solution
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.
Tools (11)
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 |
Intent Categories
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)
Tests
python -m pytest tests/ -v # 38 tests, all passingInspiration
nah — Intent-level permission guards
Open Agent Passport — Pre-action authorization
Beyond Permission Prompts — Structured authorization
Claude Code Auto Mode — Two-stage classifier
License
MIT — AMEOBIUS
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessSyncing
Related MCP Connectors
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Related MCP Servers
- AlicenseAqualityDmaintenanceA pre-action risk gate for AI agents. Your agent calls the forecast tool before any irreversible action — send email, run SQL, make a payment, delete a file — and gets a risk score (0–100) and a GO / CONFIRM / STOP verdict in a few seconds.198 npmMIT
- AlicenseBqualityCmaintenanceAn MCP server that enforces runtime authorization for tool calls using Stage0 policy validation, preventing AI agents from executing unauthorized actions before they happen.6MIT
- AlicenseAqualityAmaintenanceLocal zero-trust permission gateway for AI agents. Enforces policy-based tool authorization, human approvals, scoped permissions, and cryptographically verifiable audit logs.477 PyPI5Apache 2.0