搜索「Policy」的结果

io.github.AIops-tools/ai-guardian

Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

io.github.kanywst/mcp-opa-authz

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

com.scopeblind/protect-mcp

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

io.github.ECD5A/orchestrui

Deterministic UI policy, discovery and audits for coding agents across seven ecosystems.

io.github.aggrete/aggrete

MCP policy proxy: enforces a code of conduct across connectors before the upstream is called.

io.github.clayseal/clayseal

Authorizes MCP tool calls against a session policy, not one call at a time.

io.github.r33drichards/mcp-js

Run JavaScript and TypeScript in sandboxed V8 isolates with policy-controlled host capabilities.

io.github.agentwares/agentguard

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

io.github.aliengineering-byte/gaugemesh

Route MCP capabilities through deterministic identity, policy, budget, and deadline constraints.

io.github.agentic-hil/agentic-hil

Develop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated.

io.github.Aggrete/aggrete

MCP policy proxy: enforces a code of conduct across connectors before the upstream is called.

io.github.Runestone-Labs/gatekeeper

Run MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit.

io.github.Shrike-Security/shrike-mcp

Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.

io.github.IvanBBaev/x-mcp-ai

Safety-first X (Twitter) API v2 MCP server: 41 typed tools across 12 packages, policy-gated.

io.github.ocm-mcp-server/ocm-mcp-server

Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.

io.github.WYRE-AI/action1-mcp

Action1 MCP server — endpoint inventory, patch visibility, and policy automation via REST API.

io.github.WYRE-AI/spamtitan-mcp

MCP server for SpamTitan email security — quarantine, allow/block lists, and policy management.

io.github.mikhailbovt/contextdb-memory

Local-first durable AI memory with policy-bound recall and a typed project graph.

ai.midplane/midplane

Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.

com.ai-rete-rag/ai-rete-rag-mcp

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

io.github.mattijsmoens/sovereign-mcp-gateway

Gating proxy for MCP servers: policy, verification and one audit trail across upstreams.

com.unlimitedtts/tts

Quote-first, non-custodial x402 text-to-speech with spend policy, MP3 artifacts, and receipts.

io.github.wyre-technology/action1-mcp

Action1 MCP server — endpoint inventory, patch visibility, and policy automation via REST API.

io.github.ezequiellich44-cmd/mandateguard

Deterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.