Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
SatGate – Economic Firewall for AI Agents
MCP serversBudget, payment and audit controls for AI agent API calls and MCP tool calls.
satgate-mcp-bridge@1.0.5 -
SQLGuard — Execution Certificate Firewall
MCP serversPermission before writes. Gravity→DENYs→Session $0.25. Pilot $100; Gateway $299. Probe free.
-
BarzelVault: AI Action Authorization Firewall
MCP serversAuthorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
-
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
-
Agent Reserve Protocol Authorization Firewall
MCP serversAdvisory policy preflight for AI-agent spend requests; never executes payments or accesses wallets.
-
SHULIAK SIP-1 Zero-Egress AI & MCP Firewall
MCP serversOn-device NIST SP 800-38G FF1 (9/9 CAVP) pseudonymization, OWASP MCP05/06 guard & EU AI Act AIBOM.
@shuliak-corp/sip1-mcp@2.6.3 -
mikrotik-mcp
MCP serversMCP server for MikroTik routers: firewall, NAT, routing, DHCP, DNS, WireGuard and more via SSH.
mcp-server-mikrotik@0.29.4.0 -
swing-skills
SkillsOpen-source Claude Code skills — 6 cognitive firewalls block AI hallucination, bias & sloppy reasoning. npx skills add
git clone https://github.com/TheStack-ai/swing-skills.git -
AWS Network Firewall
Public APIsThis is the API Reference for Network Firewall. This guide is for developers who need detailed information about the Network Firewall API actions, data types, and errors. The REST API requires you to handle connection details, such as calculating signatures, handling request retries, and error handling. For general information about using the Amazon Web Services REST APIs, see Amazon Web…
-
emilia-protocol
MCP serversAuthority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.
git clone https://github.com/emiliaprotocol/emilia-protocol.git -
xops-cli
MCP servers基于 Go 的高性能、跨平台运维 CLI 工具。提供主机管理、SSH 连接、文件传输、批量执行和 Playbook 任务编排,也可通过 Model Context Protocol (MCP) 接入 AI 客户端,配置操作审批和审计。
git clone https://github.com/wentf9/xops-cli.git -
pic-standard
MCP serversOpen standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
git clone https://github.com/pic-standard/pic-standard.git -
FilterLists
Public APIsLists of filters for adblockers and firewalls
-
crowdsec-skill
SkillsOfficial CrowdSec skill for Claude Code & Codex: install, configure, operate and debug the engine, bouncers and WAF/AppSec.
git clone https://github.com/crowdsecurity/crowdsec-skill.git -
WebApplicationFirewallManagement
Public APIsAPIs to manage web application firewall rules.
-
Azure CDN WebApplicationFirewallManagement
Public APIsAPIs to manage web application firewall rules for Azure CDN
-
Seraph
MCP serversCrypto transaction firewall and risk tools for MCP agents.
-
Aegis Policy
MCP serversGovernance firewall and safety guardrails oracle for AI swarms.
-
agentguard
MCP serversNetwork-egress firewall for agent tools: check URLs against a declarative policy.
@mukundakatta/agentguard-mcp@0.1.0 -
assay
MCP serversThe firewall for MCP tool calls. Block, audit, replay with evidence bundles.
https://github.com/Rul1an/assay/releases/download/v3.1.0/assay-mcp-cli-v3.1.0-x86_64-unknown-linux-gnu.tar.gz -
vibecheck-mcp
MCP serversAI Code Firewall — MCP Server for hallucination prevention in AI development
@vibecheckdev/vibecheck-mcp@1.0.0 -
injectshield
MCP serversPrompt-injection firewall for AI agents — scan untrusted text before LLM calls.
@injectshield/mcp@0.1.4 -
contextweaver
MCP serversMCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.
contextweaver@0.18.2 -
mcp
MCP serversPayment firewall for AI agents: a signed, verifiable verdict on every money-moving action.
@fidacy/mcp@0.2.7
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.