MCP Action Firewall
Acts as a security proxy for GitHub MCP servers, intercepting high-risk repository management actions and requiring explicit human authorization via a one-time password (OTP) before execution.
Provides a circuit breaker for PostgreSQL MCP servers, blocking destructive database operations such as dropping or truncating tables until they are confirmed by a user through an OTP flow.
Intercepts potentially dangerous Stripe tool calls, such as refunds or charges, and requires human approval via a 4-digit code before the firewall allows the action to proceed to the target Stripe server.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Action Firewallauthorize the pending action with code 9942"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π₯ MCP Action Firewall
Works with any MCP-compatible agent
A transparent MCP proxy that intercepts dangerous tool calls and requires OTP-based human approval before execution. Acts as a circuit breaker between your AI agent and any MCP server.
How It Works
ββββββββββββ stdin/stdout ββββββββββββββββββββ stdin/stdout ββββββββββββββββββββ
β AI Agent β ββββββββββββββββββΊ β MCP Action β ββββββββββββββββββΊ β Target MCP Serverβ
β (Claude) β β Firewall β β (e.g. Stripe) β
ββββββββββββ ββββββββββββββββββββ ββββββββββββββββββββ
β
Policy Engine
βββββββββββββββββ
β Allow? Block? β
β Generate OTP β
βββββββββββββββββMCP servers don't run like web servers β there's no background process on a port. Instead, your AI agent (Claude, Cursor, etc.) spawns the MCP server as a subprocess and talks to it over stdin/stdout. When the chat ends, the process dies.
The firewall inserts itself into that chain:
Without firewall:
Claude ββspawnsβββΊ mcp-server-stripe
With firewall:
Claude ββspawnsβββΊ mcp-action-firewall ββspawnsβββΊ mcp-server-stripeSo you just replace the server command in your MCP client config with the firewall, and tell the firewall what the original command was:
Before (direct):
{ "command": "uvx", "args": ["mcp-server-stripe", "--api-key", "sk_test_..."] }After (wrapped with firewall):
{ "command": "uv", "args": ["run", "mcp-action-firewall", "--target", "mcp-server-stripe --api-key sk_test_..."] }Then the firewall applies your security policy:
β Safe calls (e.g.
get_balance) β forwarded immediatelyπ Dangerous calls (e.g.
delete_user) β blocked, OTP generatedπ Agent asks user for the code β user replies β agent calls
firewall_confirmβ original action executes
Related MCP server: sovr-mcp-proxy
Installation
pip install mcp-action-firewall
# or
uvx mcp-action-firewall --helpQuick Start β MCP Client Configuration
Add the firewall as a wrapper around any MCP server in your client config:
{
"mcpServers": {
"stripe": {
"command": "uv",
"args": ["run", "mcp-action-firewall", "--target", "mcp-server-stripe --api-key sk_test_abc123"]
}
}
}That's it. Everything after --target is the full shell command to launch the real MCP server β including its own flags like --api-key. The firewall doesn't touch those args, it just spawns the target and sits in front of it.
More Examples
{
"mcpServers": {
"stripe": {
"command": "uv",
"args": [
"run", "mcp-action-firewall",
"--target", "uvx mcp-server-stripe --api-key sk_test_...",
"--name", "stripe"
]
},
"database": {
"command": "uv",
"args": [
"run", "mcp-action-firewall",
"--target", "uvx mcp-server-postgres --connection-string postgresql://...",
"--name", "database",
"--config", "/path/to/my/firewall_config.json"
]
}
}
}{
"mcpServers": {
"github": {
"command": "uvx",
"args": [
"mcp-action-firewall",
"--target", "npx @modelcontextprotocol/server-github"
]
}
}
}The OTP Flow
When the agent tries to call a blocked tool, the firewall returns a structured response:
{
"status": "PAUSED_FOR_APPROVAL",
"message": "β οΈ The action 'delete_user' is HIGH RISK and has been locked by the Action Firewall.",
"action": {
"tool": "delete_user",
"arguments": { "id": 42 }
},
"instruction": "To unlock this action, you MUST ask the user for authorization.\n\n1. Show the user the following and ask for approval:\n Tool: **delete_user**\n Arguments:\n{\"id\": 42}\n\n2. Tell the user: 'Please reply with approval code: **9942**' to allow this action, or say no to cancel.\n3. STOP and wait for their reply.\n4. When they reply with '9942', call the 'firewall_confirm' tool with that code.\n5. If they say no or give a different code, do NOT retry."
}Argument visibility guarantee: The arguments shown to the user are frozen at interception time β they are taken from the original blocked call, not from what the agent passes to
firewall_confirm. The agent cannot change the arguments after the OTP is issued.
The firewall_confirm tool is automatically injected into the server's tool list:
{
"name": "firewall_confirm",
"description": "Call this tool ONLY when the user provides the correct 4-digit approval code to confirm a paused action.",
"inputSchema": {
"type": "object",
"properties": {
"otp": {
"type": "string",
"description": "The 4-digit code provided by the user."
}
},
"required": ["otp"]
}
}Configuration
The firewall ships with sensible defaults. Override with --config:
{
"global": {
"allow_prefixes": ["get_", "list_", "read_", "fetch_"],
"block_keywords": ["delete", "update", "create", "pay", "send", "transfer", "drop", "remove", "refund"],
"default_action": "block",
"otp_attempt_count": 1
},
"servers": {
"stripe": {
"allow_prefixes": [],
"block_keywords": ["refund", "charge"],
"default_action": "block"
},
"database": {
"allow_prefixes": ["select_"],
"block_keywords": ["drop", "truncate", "alter"],
"default_action": "block"
}
}
}Rule evaluation order:
Tool name starts with an allow prefix β ALLOW
Tool name contains a block keyword β BLOCK (OTP required)
No match β fallback to
default_action
otp_attempt_count β maximum number of failed OTP attempts before the pending action is permanently locked out. Defaults to 1 (any wrong code cancels the request). Increase for more forgiving UX, keep at 1 for maximum security.
Per-server rules extend (not replace) the global rules. Use --name stripe to activate server-specific overrides.
CLI Reference
--target (required)
The full command to launch the real MCP server. This is the server you want to protect:
mcp-action-firewall --target "mcp-server-stripe --api-key sk_test_abc123"
mcp-action-firewall --target "npx @modelcontextprotocol/server-github"
mcp-action-firewall --target "uvx mcp-server-postgres --connection-string postgresql://localhost/mydb"--name (optional)
Activates per-server rules from your config. Without it, only global rules apply:
mcp-action-firewall --target "mcp-server-stripe" --name stripe--config (optional)
Custom config file path. Without it, uses firewall_config.json in your current directory, or the bundled defaults:
mcp-action-firewall --target "mcp-server-stripe" --config /path/to/my_rules.json-v / --verbose (optional)
Turns on debug logging (written to stderr, won't interfere with MCP traffic):
mcp-action-firewall --target "mcp-server-stripe" -vProject Structure
src/mcp_action_firewall/
βββ __init__.py # Package version
βββ __main__.py # python -m support
βββ server.py # CLI entry point
βββ proxy.py # JSON-RPC stdio proxy
βββ policy.py # Allow/block rule engine
βββ state.py # OTP store with TTL
βββ default_config.json # Bundled default rulesTry It β Interactive Demo
See the firewall in action without any setup:
git clone https://github.com/starskrime/mcp-action-firewall.git
cd mcp-action-firewall
uv sync
uv run python demo.pyThe demo simulates an AI agent and walks you through the full OTP flow:
β Safe call (
get_balance) β passes through instantlyπ Dangerous call (
delete_user) β blocked, OTP generatedπ You enter the code β action executes after approval
Known Limitations
Argument Inspection
The firewall matches on tool names only, not argument values. This means a tool like get_data({"sql": "DROP TABLE users"}) would pass if get_ is in your allow list, because the policy engine only sees get_data.
Workaround: Use explicit tool names in your allow/block lists and set "default_action": "block" so unrecognized tools require approval.
π§ Roadmap: Argument-level inspection (scanning argument values against
block_keywords) is planned for a future release.
Development
# Install dev dependencies
uv sync
# Run tests
uv run pytest tests/ -v
# Run the firewall locally
uv run mcp-action-firewall --target "your-server-command" -vLicense
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceAudits npm package dependencies for security vulnerabilities, providing detailed reports and fix recommendations with MCP integration.Last updated110854MIT
- Flicense-quality-maintenanceA transparent proxy and execution firewall that intercepts and audits AI agent tool calls against configurable security policies before forwarding them to downstream MCP servers. It provides safe execution environments with features like data redaction, anti-loop protection, and unified alert dispatching.Last updated
- Alicense-qualityDmaintenanceHuman-in-the-Loop authorization gateway for AI Agents. Securely pause MCP workflows and route high-risk actions to human approvers via Slack or Email.Last updated511MIT
- AlicenseAqualityCmaintenanceSecurity-enforcing MCP proxy that sits between an AI agent and any number of downstream MCP servers, intercepting every tool call through a capability-token policy gateway that can allow, deny, or escalate to human approval before the call reaches any real tool. It also exposes built-in operator tools for approval workflows, audit trail queries, token management, voice/HUD output, and hierarchicalLast updated2111Apache 2.0
Related MCP Connectors
Security firewall for AI agents β scans MCP calls for injection, secrets, and risks.
Runtime permission, approval, and audit layer for AI agent tool execution.
Crypto transaction firewall and risk tools for MCP agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/starskrime/mcp-action-firewall'
If you have feedback or need assistance with the MCP directory API, please join our Discord server