Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
esp32_nat_router
MCP serversAn AI-enabled NAT Router/Firewall for the ESP32
git clone https://github.com/martin-ger/esp32_nat_router.git -
kavach
Agents & frameworksTactical AI Workspace Monitor & EDR
git clone https://github.com/LucidAkshay/kavach.git -
pipelock
Agents & frameworksOpen-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
git clone https://github.com/pipelab-org/pipelock.git -
Chainsaw package firewall
MCP serversPackage firewall for agents: route npm, pip and docker installs through Chainsaw.
-
OPNsense / pfSense Firewall Operations
MCP serversGoverned OPNsense + pfSense firewall ops: rules, NAT, VPN, DHCP, RCA. 35 tools.
firewall-aiops@0.16.1 -
Yagami AI Context Firewall
MCP serversOpen-source AI context firewall for governed model, retrieval, memory, and tool access.
yagami@0.8.6 -
MCP Output Firewall
MCP serversThree-layer firewall for MCP: content, egress and action policy. Proxy or server.
mcp-output-firewall@0.3.0 -
WARDEN by AIMarket — MCP tool firewall
MCP serversMCP security firewall: stdio wrap proxy or inspection tools; zero runtime dependencies.
@aimarket/warden@0.27.0 -
Firewall rules audit — Atom
MCP serversFirewall rules audit, delivered per API call as an atom service on Conduit Atoms.
-
unifi-skills
SkillsAgent skills for administering a real UniFi network over its local API: auth, zone firewall, Wi-Fi, clients, and the site map.
git clone https://github.com/t3chnaztea/unifi-skills.git -
Firewall Management Service
Public APIsThis is the Firewall Manager API Reference . This guide is for developers who need detailed information about the Firewall Manager API actions, data types, and errors. For detailed information about Firewall Manager features, see the Firewall Manager Developer Guide . Some API actions require explicit resource permissions. For information, see the developer guide topic Service roles for Firewall…
-
agent-prompt-injection-firewall-mcp
MCP serversThe WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
agent-prompt-injection-firewall-mcp@1.0.13 -
sipi.bot — Spend Firewall for AI Agents
MCP serversPre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
-
AI Firewall MCP
MCP serversMulti-agent LLM security layer detecting prompt injection and jailbreaks.
ai-firewall-mcp@1.0.1 -
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
-
ai-agent-firewall
MCP serversEvery agent action watched, every money-moving one gated, every verdict independently verifiable.
@fidacy/mcp@0.7.1 -
code-firewall-mcp
MCP serversStructural similarity-based code filter. Stops malicious code pattern reaching execution tools.
code-firewall-mcp@0.7.0 -
Agent Trust Firewall
MCP serversFree pre-action policy checks and data cleaning for autonomous AI agents.
-
SML Risk Firewall
MCP serversPre-trade risk checks for agent trades: orders vs your limits, signed receipts.
-
context-firewall
MCP serversLocal MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.
context-firewall@0.1.1 -
agent-firewall-mcp
MCP serversInput/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
agent-firewall-mcp@1.3.0 -
IntentFence Agent Action Firewall
MCP serversFail-closed action authorization, MCP risk scanning, x402 checks, and signed receipts.
-
values-firewall
MCP serversEU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.
-
AI API Cost Firewall & Rate Limiter
MCP serversToken guard and rate limiter preventing runaway API cost spikes for OpenAI and Anthropic.
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.