MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Agentic-AI-Firewall-Orchestratorgithub.com/irl-jacob/Agentic-AI-Firewall-Orchestratorupdated this year
AFO is an agentic firewall orchestration platform powered by Model Context Protocol (MCP). It combines AI agents, natural language processing, and adaptive learning to manage complex firewall configurations
-
AI-firewallgithub.com/Akhilucky/AI-firewallupdated this year
🛡️ AI Firewall — Multi-agent LLM security MCP server. Protects against prompt injection, jailbreaks, and policy violations.
pypi MIT -
ai-agent-spend-firewallgithub.com/kindrat86/ai-agent-spend-firewallupdated this year
Pre-spend firewall for autonomous AI agents: approve, block, or flag every transaction before money moves. MCP-native.
-
Governed AI-ops for OPNsense + pfSense firewalls — gateway/rule/traffic RCA, guarded rule/alias writes, with audit/budget/undo (preview)
pypi MIT ★ 2 -
The firewall for AI agents (preview): fixed rules, outside the model, check each tool call that reaches them through a coding agent's hooks, the library or the MCP gateway, before it runs.
npm Apache-2.0 -
Agent Firewall for AI and MCP tool calls: deterministic allow, ask, deny permissions with human approval and audit hooks.
npm MIT -
🔌 Exposes AI agent prompt injection firewall over MCP — OWASP LLM Top 10 1 runtime guard. MIT.
pypi MIT -
Open-source firewall for AI agents: centrally managed egress control, full traffic visibility (TLS inspection) and audit for fleets of LLM agents. Rust gateway, Nuxt console, CLI & MCP.
Apache-2.0 -
SHULIAK SIP-1 v2.6.2: Zero-Egress AI & MCP Firewall (9/9 NIST SP 800-38G FF1 CAVP Verified, OWASP MCP05/06 Guard, EU AI Act AIBOM). CERN DOI: 10.5281/zenodo.24159380
npm NOASSERTION ★ 1 -
PayPal AI Hackathon 2026 entry. A payment firewall for AI agents: every payment an agent tries is checked against your rules before it reaches PayPal, and Z3 proves the agent's permission can never exceed them. Stops prompt injection, overspending and lookalike shops. PayPal Agent Toolkit + MCP.
MIT ★ 2 -
rookbotgithub.com/rookbot-io/rookbotupdated this year
A firewall for AI agents — intercept, inspect, and control MCP tool calls
npm (Apache-2.0 OR MIT) -
@idevelopers/agentlockactive
Local permission firewall for AI coding agents and MCP tools.
npm MIT -
MCP tool packages (.mcpb) for AI-driven network device ops — firewall REST API toolkits (NSFOCUS / Hillstone / YAXIN / ASG, 490+ tools) + open package format spec. 灵枢 MCP 扩展包生态:防火墙/网络设备运维工具集
MIT ★ 4 -
pfsense-mcpgithub.com/abl030/pfsense-mcpupdated this year
MCP server for the pfSense REST API v2 — 677 tools for AI-driven firewall management
MIT ★ 1 -
🛡️ APHANIS :: Zero-Trust AI Provenance Firewall, Automatic Humanizer Engine & Stego Defense Platform
pypi MIT ★ 4 -
A local application firewall for coding agents. Little Snitch, but for AI agent tool calls.
MIT ★ 1 -
MCP server for managing Fortinet FortiGate firewalls (FortiOS 7.6 REST API) with AI
MIT ★ 5 -
Runtime firewall for AI coding agents. Gate every tool, MCP and skill call against a least-privilege policy.
Apache-2.0 ★ 3 -
bonanza-mcpgithub.com/c6zks4gssn-droid/bonanza-labs-websiteupdated this year
MCP server for AI agent payments — spending firewall, budget checks, and approval flows via the Model Context Protocol
pypi Apache-2.0 -
@sonnylabs/mcpgithub.com/sonnylabs/sonnylabsupdated this year
Model Context Protocol server for the Sonny Labs AI firewall. Run it inside your agentic client (Claude Desktop, Cursor, Claude Code) to scan prompts and outputs for injection / PII / toxicity, manage API keys, and scaffold the firewall into your codebase
npm Apache-2.0 -
LLM Security Gateway — AI application firewall, prompt injection risk analysis & sovereign audit runtime.
Apache-2.0 -
Arbiter: A capability firewall between AI agents and services
go MIT ★ 3 -
Modular MCP server for OPNsense firewall management - 88 tools providing access to 2000+ methods through AI assistants
MIT ★ 96 -
A local security checkpoint for AI agents. MCP firewall, Linux sandbox, secret inspection and auditable tool execution — built in Rust.
MIT ★ 1 -
MeterGate: Zero-Dependency, Zero-Telemetry Local AI Agent 3-Tier Firewall, Official-Rate Cost Ledger & Standard MCP Middleware (pipx / uvx ready)
pypi MIT License -
AI Agent Firewall for OpenAI-compatible traffic and MCP tool calls: policy enforcement, approvals, execution receipts, and verifiable evidence.
-
Zero-dependency AI Agent sandbox firewall compiler (nftables, macOS pf, Tailscale ACL), Sing-box/Mihomo QUIC mesh router & native MCP server
MIT -
dealgo-mcpgithub.com/dealgo-systems/dealgo-mcp-serverupdated this year
MCP server for DeAlgo CSC — runtime decision firewall for AI agents. Drop into Claude Desktop, Claude Code, or Cursor and your agent must consult csc_check before acting.
pypi Apache-2.0 -
fidacy-mcpgithub.com/lucaslubi/fidacy-mcpupdated this year
Payment firewall for AI agents: a signed, independently-verifiable verdict on every money-moving action. Non-custodial, local-first. npx @fidacy/mcp
pypi Apache-2.0 ★ 1 -
Native Rust AI Slop & Hallucination Firewall + Real-time MCP Observer TUI Console. Intercepts phantom imports, broken APIs, empty stubs, mock data & silent errors before git commit.
MIT ★ 2 -
Policy firewall for AI agents and MCP tools. Intercepts tool calls, enforces allow/deny/ask rules, redacts secrets, validates arguments, and writes auditable logs before agents touch your filesystem, GitHub, browser, or APIs.
Apache-2.0 ★ 6 -
terminusgithub.com/interceptai-tech/terminusupdated this year
The SQL firewall for AI agents: a default-deny sidecar / MCP enforcement point that governs what an AI agent runs against your database. Open core, AGPL-3.0.
AGPL-3.0 -
UniFi Network MCP server for AI-assisted VLAN, Wi-Fi, firewall and AP radio management, with Mermaid topology diagrams and approval-gated changes.
MIT -
A secure MCP server for managing OPNsense firewalls through AI assistants. 62 tools across 10 domains with read-only default, savepoint rollback, and security auditing.
pypi MIT ★ 27 -
Spec-driven development governance for AI coding agents: Gherkin specs as executable contracts, deterministic drift gates, an agent firewall and a least-privilege MCP server, on any repository.
npm MIT -
Open-source firewall for AI agents. Tortoise Gate checks every MCP tool call before it runs, blocks or asks you about risky actions, and keeps a tamper-evident log, so a hidden instruction in an email can't make your agent leak data or send money.
Apache-2.0 -
🛡️ The consent firewall for AI agents. Your agent can use the world's public data — the world can't use yours. Field-level minimization, in-flow consent, LLM tokenization, prompt-injection quarantine & hash-chained privacy receipts. MCP server included.
MIT ★ 1 -
Automate Cisco Secure Firewall (FMC-managed FTD) with Python, Ansible, and Terraform, plus three MCP servers that let an AI agent search policy, trace object usage, and propose changes behind a preview-and-confirm gate. Read-only by default, TLS on by default, CSV-driven, lab-tested.
MIT -
Description: Autonomous pre-trade firewall for Solana AI agents: behavioral baseline, 9 deterministic rules, simulation, and on-chain Token-22 enforcement. Website: https://daniilmilintieiev-ux.github.io/wallet-radar/ Topics: solana, ai-agents, firewall, token-22, zk-compression, mcp, x402
MIT -
MCP server for managing pfSense firewalls through AI assistants
pypi MIT ★ 7 -
checkpoint-mcp-servergithub.com/cheenu1092-oss/checkpoint-mcp-serverupdated this year
MCP server for Check Point Management API — firewall policy, objects, NAT, sessions via AI agents
★ 1 -
opnsense-mcpgithub.com/digitalhen/opnsense-mcpupdated this year
MCP server connecting Claude.ai to OPNsense router API — firewall, diagnostics, VPN, DNS, and 20+ modules with 750+ methods
★ 1 -
Anthropic MCP servers to enable AI agent integration and autonomous defense for Check Point firewalls, endpoint, and more.
MIT ★ 1 -
hostinger-mcpupdated this year
MCP server for Hostinger API — manage VPS, DNS, domains, firewall and snapshots via AI
npm MIT -
Anti-Death-Spiral Firewall & Cryptographic Test-File Locking for Autonomous AI Agents
npm MIT -
Pre-Execution Token Budget Firewall & Cost Telemetry Sentinel for AI Coding Agents
npm MIT -
Ephemeral Copy-on-Write Database Branching & Destructive Migration Firewall for AI Coding Agents
npm MIT -
@vibecheckai/mcp-servergithub.com/vibecheckai/vibecheckupdated this year
VibeCheck — AI Code Firewall | MCP Server for hallucination prevention in AI-assisted development
npm MIT -
🌐 A comprehensive MCP server for Cisco device management via SSH/Telnet. Execute commands and manage Cisco routers, switches, and firewalls through AI assistants.
npm MIT ★ 10 -
unifi-mcpgithub.com/abl030/unifi-mcpupdated this year
AI-generated MCP server for the Ubiquiti UniFi Network Controller API. 283 tools for managing networks, firewall rules, switch ports, WiFi, clients, and devices.
★ 1 -
A local-first permission firewall and approval layer for AI agent tool calls.
Apache-2.0 ★ 4 -
Manage Securepoint UTM firewalls and MikroTik routers with AI assistants through the Model Context Protocol (MCP).
MIT ★ 2 -
Agentix Lite Sentinel read-only MCP gateway (Go, linux/x64) for local AI agents: host security telemetry, no firewall or shell access.
npm Apache-2.0 -
agentoolboxgithub.com/solhammer/agentoolboxupdated this year
The quality layer for AI agents — hallucination firewall, import validator, context distiller. Pay per call in SOL.
npm MIT -
Deterministic context firewall for AI coding agents — AST-skeleton checkouts, three commit gates, DSSE attestations. MCP server + BYOK proxy + Studio.
pypi Apache-2.0 -
@golproductions/check-mcpgithub.com/golproductions/check-mcpupdated this year
Less hallucinations. A command firewall for AI agents: validates every shell command before execution, so fabricated commands are denied before they run.
npm SEE LICENSE IN LICENSE -
A type system, state validator, and safety firewall between AI coding assistants and physical instruments — schema-driven, MCP-native, zero hardware knowledge in the engine.
MIT ★ 1 -
A security proxy and MCP firewall that protects databases from unsafe AI agent queries through real-time SQL inspection, policy enforcement, query blocking, and approval-based execution.
-
Spending firewall for AI agents on NEAR: on-chain policy wallet, shared scam registry, counterparty scout, MCP tools. Try to steal our agent's money. NEAR HACKATHON 2026.
MIT -
MCP server for QuickCloud - manage VMs, dedicated servers, firewalls, load balancers, storage, databases, email relay, websites and DNS from Claude, Cursor or any MCP-capable AI assistant. Zero dependencies, read-only by default.
npm MIT