Why this server?
Exact match for the searched repository; blocks destructive tool calls like force-push, rm -rf, and secret exfiltration.
Alicense-qualityAmaintenanceA runtime gate for coding agents. Blocks the tool calls that wreck a repo (force-push main, rm -rf, secret exfiltration, CI wipe) and lets normal build and commit work through. Machine-checked git-branch core (z3); the rest is high-precision heuristics. Tested on 3,790 real CI commands, 0 false blocks.MITWhy this server?
Local guardrail proxy that wraps MCP servers and blocks destructive tool calls before execution, with TOFU catalog pinning and injection scanning.

aperion-shieldofficial
FlicenseAqualityAmaintenanceLocal guardrail proxy for AI coding agents. Wraps any MCP server (stdio or HTTP/SSE) and blocks destructive tool calls before they execute, with TOFU catalog pinning against rug pulls and tool-poisoning/result-injection scanning. Single Rust binary, Apache-2.0.146Why this server?
Guardrail sidecar proxy with policy engine, human approval gates, and rate limiting; fail-closed by default.
Alicense-qualityAmaintenanceGuardrail sidecar proxy between AI agents and their MCP/REST/CLI tools. Policy engine, human approval gates, time-limited grants, rate limiting, and OTEL tracing. One Go binary, one YAML config, fail-closed by default.1Apache 2.0Why this server?
Runtime safety infrastructure adding budget caps, loop detection, retry limits, and incident reports for agents.
AlicenseAqualityAmaintenanceAgentGuard47 is runtime safety infrastructure for AI agents. It adds budget caps, loop detection, retry limits, timeouts, local traces, and incident reports so agents can stop bad runs while they are happening, not just explain them afterward.74MITWhy this server?
Local-first security gateway enforcing cost caps, blocking prompt injections, and requiring approval for dangerous actions.
Flicense-qualityCmaintenanceA local-first security gateway and visual dashboard for AI agents that enforces cost caps, blocks prompt injections, and requires approval for dangerous actions.2Why this server?
Minimal guardrails framework acting as an MCP proxy to enforce policies, approvals, and audit logging.
Alicense-qualityAmaintenanceA minimal guardrails framework for AI agents, acting as an MCP proxy to enforce policies, approvals, and audit logging on tool calls.MITWhy this server?
Guardrails for AI coding agents that enforce rules via compliance receipts and block destructive actions.
AlicenseAqualityBmaintenanceGuardrails for AI coding agents that enforces rules via compliance receipts, blocking destructive actions and syncing rules across all AI tools.24341MITWhy this server?
Runtime safety guardrails for coding agents; checks file access, validates shell commands, and scores repo AI safety.
Alicense-qualityCmaintenanceRuntime safety guardrails for AI coding agents. Checks file access, validates shell commands, and scores your repo's AI safety — all via MCP.78MITWhy this server?
Deterministic policy enforcement for agent tool calls, evaluating against user-defined rules before execution.
Alicense-qualityAmaintenanceDeterministic policy enforcement for AI agent tool calls. It evaluates every tool call against user-defined rules before execution, with no LLM in the authorization path.3MIT