Guardrails & policy MCP servers

Deadline-aware governance for AI agents: PII scan always, safety check if it fits the deadline

Safety-first OPNsense firewall MCP: read-only by default, planned and auto-reverting writes.

Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.

Manage MagicSword endpoints, alerts, policies, and private intelligence through MCP.

Gateway in front of MCP tools: critical arguments are checked against trusted sources and a policy.

Approval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.

Read-only MCP for FINOS AI governance risks, controls and crosswalks. Independent project.

MCP gateway that checks each agent tool call against a signed grant and policy, and signs a receipt

Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.

Governed MCP gateway: approved tools only, each call policy-checked and recorded per agent

Policy-enforcing MCP proxy with portable evidence output.

Keycloak admin for AI agents — realms, users, clients, roles; safe-by-default governance.

Policy-gated agent spend with signed receipts and rail-extract audit

Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.

Zero-egress AI Agent Firewall: SARA prompt injection defense, AST context pruning & MCP governance.

Governance validation for Semantic Data Charter instances; returns OASIS XACML decisions.

AI agents' spatial awareness inside Autodesk Maya: audit, rollback safety, visual loop (Beta)

Governance-grade knowledge-base format (OKF-compatible) plus CLI and single-writer MCP server

Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.

Expose trusted GNU Make targets as governed MCP tools without a generic shell.

Draft SOC 2 policies from your AI assistant, via MCP

Graph-powered codebase reasoning, impact analysis, and governance tools over MCP.

Safety-first MCP server for ROS 2 robot arms: server-side safety envelope, human approval, audit

The open-source governance layer for AI agents. Byte-identical run receipts, 40+ adapters, air-gap.

Pre-sign EVM tx/approval safety for AI agents: decode calldata, flag drainers, return GO/HOLD/BLOCK.

Runtime permission, approval, and audit layer for AI agent tool execution.

Advisory MCP tools: policy score, reasoning checklist, compression. To enforce, use delentia-guard.

Check if references exist or were retracted, look up journal AI policies, and preview manuscripts.

Static preflight safety gate for MCP servers — scan configs before you run them. Never executes.

Causal guardrail: pass/caution/hold verdict on a causal claim before an agent acts.

Permission-gated superuser (sysadmin) MCP agent with enterprise guardrails and audit.

Check finite candidate proposals against separate policy and evidence, with canonical hash receipts.

Walkability and pedestrian safety for any US address: scores, neighborhoods, deadly roads.

Recall and calibrate agent tool calls against verified policy lessons from Achromat MOM.

The open routing layer for AI tools: tool calls routed per policy, decision on every result.

Autonomous and governed SRE & MLOps control plane for AI agent platforms.

MCP server for CIPP — M365 multi-tenant management for MSPs (users, tenants, policies).

Build a governed style profile from your own past work so a generative apprentice produces...

Turn a described vehicle noise into a ranked, testable differential diagnosis with a safety...

Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.

Django admin models over MCP: CRUD, actions, history, autocomplete — capped by Django permissions.

Journals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval

Read public privacy policies: dated source excerpts, follow-up questions and change comparisons.

Governed OT data tap: 15 field protocols + cross-protocol RCA brain; audit + MOC gating.

Manage ipTIME routers through a local, safety-gated MCP server with firmware-aware capabilities.

Open-source governance for MCP agents: useful autonomy without unlimited authority

Record what your AI did as tamper-evident evidence for ISO 42001, EU AI Act and SOC 2. Hash-only.

Autonomous AI microservices: 55 dynamic guardrails, contract audits & oracles via L402/x402/MPP.

Spend limits for AI agents that pay with x402: every paywall is policy-checked before a cent moves.

The safety gate between AI agents and your servers: typed, policy-checked, audited ops tools.