mcpwall

mcpwall

iptables for MCP. Blocks dangerous tool calls, scans for secret leakage, logs everything. No AI, no cloud, pure rules.

Sits between your AI coding tool (Claude Code, Cursor, Windsurf) and MCP servers, intercepting every JSON-RPC message and enforcing YAML-defined policies.

Why

MCP servers have full access to your filesystem, shell, databases, and APIs. When an AI agent calls tools/call, the server executes whatever the agent asks — reading SSH keys, running rm -rf, exfiltrating secrets. There's no built-in policy layer.

mcpwall adds one. It's a transparent stdio proxy that:

• Blocks sensitive file access — .ssh/, .env, credentials, browser data
• Blocks dangerous commands — rm -rf, pipe-to-shell, reverse shells
• Scans for secret leakage — API keys, tokens, private keys (regex + entropy)
• Scans server responses — redacts leaked secrets, blocks prompt injection patterns, flags suspicious content
• Logs everything — JSON Lines audit trail of every tool call and response
• Uses zero AI — deterministic rules, no LLM decisions, no cloud calls

Install

npm install -g mcpwall

Or use directly with npx:

npx mcpwall -- npx -y @modelcontextprotocol/server-filesystem /path/to/dir

Quick Start

Option 1: Docker MCP Toolkit

If you use Docker MCP Toolkit (the most common setup), change your MCP config from:

{
  "mcpServers": {
    "MCP_DOCKER": {
      "command": "docker",
      "args": ["mcp", "gateway", "run"]
    }
  }
}

To:

{
  "mcpServers": {
    "MCP_DOCKER": {
      "command": "npx",
      "args": ["-y", "mcpwall", "--", "docker", "mcp", "gateway", "run"]
    }
  }
}

That's it. mcpwall now sits in front of all your Docker MCP servers, logging every tool call and blocking dangerous ones. No config file needed — sensible defaults apply automatically.

Option 2: Interactive setup

npx mcpwall init

This finds your existing MCP servers in Claude Code, Cursor, Windsurf, and VS Code configs and wraps them.

Option 3: Manual wrapping (any MCP server)

Change your MCP config from:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/me/projects"]
    }
  }
}

To:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y", "mcpwall", "--",
        "npx", "-y", "@modelcontextprotocol/server-filesystem", "/Users/me/projects"
      ]
    }
  }
}

Option 4: Wrap a specific server

npx mcpwall wrap filesystem

How It Works

┌──────────────┐    stdio     ┌──────────────┐    stdio     ┌──────────────┐
│  Claude Code │ ──────────▶  │   mcpwall    │ ──────────▶  │  Real MCP    │
│  (MCP Host)  │ ◀──────────  │   (proxy)    │ ◀──────────  │   Server     │
└──────────────┘              └──────────────┘              └──────────────┘
                               ▲ Inbound rules               │
                               │ (block dangerous requests)   │
                               │                              │
                               └── Outbound rules ◀───────────┘
                                   (redact secrets, block injection)

Inbound (requests):

1. Intercepts every JSON-RPC request on stdin
2. Parses tools/call requests — extracts tool name and arguments
3. Walks rules top-to-bottom, first match wins
4. Allow: forward to real server
5. Deny: return JSON-RPC error to host, log, do not forward

Outbound (responses):

1. Parses every response from the server before forwarding
2. Evaluates against outbound_rules (same first-match-wins semantics)
3. Allow: forward unchanged
4. Deny: replace response with blocked message
5. Redact: surgically replace secrets with [REDACTED BY MCPWALL], forward modified response
6. Log only: forward unchanged, log the match

Configuration

Config is YAML. mcpwall looks for:

1. ~/.mcpwall/config.yml (global)
2. .mcpwall.yml (project, overrides global)

If neither exists, built-in default rules apply.

Example config

version: 1

settings:
  log_dir: ~/.mcpwall/logs
  log_level: info         # debug | info | warn | error
  default_action: allow   # allow | deny | ask

rules:
  # Block reading SSH keys
  - name: block-ssh-keys
    match:
      method: tools/call
      tool: "*"
      arguments:
        _any_value:
          regex: "(\\.ssh/|id_rsa|id_ed25519)"
    action: deny
    message: "Blocked: access to SSH keys"

  # Block dangerous shell commands
  - name: block-dangerous-commands
    match:
      method: tools/call
      tool: "*"
      arguments:
        _any_value:
          regex: "(rm\\s+-rf|curl.*\\|.*bash)"
    action: deny
    message: "Blocked: dangerous command"

  # Block writes outside project directory
  - name: block-external-writes
    match:
      method: tools/call
      tool: write_file
      arguments:
        path:
          not_under: "${PROJECT_DIR}"
    action: deny

  # Scan all tool calls for leaked secrets
  - name: block-secret-leakage
    match:
      method: tools/call
      tool: "*"
      arguments:
        _any_value:
          secrets: true
    action: deny
    message: "Blocked: detected secret in arguments"

secrets:
  patterns:
    - name: aws-access-key
      regex: "AKIA[0-9A-Z]{16}"
    - name: github-token
      regex: "(gh[ps]_[A-Za-z0-9_]{36,}|github_pat_[A-Za-z0-9_]{22,})"
    - name: private-key
      regex: "-----BEGIN (RSA |EC |DSA |OPENSSH )?PRIVATE KEY-----"
    - name: generic-high-entropy
      regex: "[A-Za-z0-9/+=]{40}"
      entropy_threshold: 4.5

Rule matchers

The special key _any_value applies the matcher to ALL argument values.

Outbound rules (response inspection)

Outbound rules scan server responses before they reach your AI client. Add them to the same config file:

outbound_rules:
  # Redact secrets leaked in responses
  - name: redact-secrets-in-responses
    match:
      secrets: true
    action: redact
    message: "Secret detected in server response"

  # Block prompt injection patterns
  - name: block-prompt-injection
    match:
      response_contains:
        - "ignore previous instructions"
        - "provide contents of ~/.ssh"
    action: deny
    message: "Prompt injection detected"

  # Flag suspiciously large responses
  - name: flag-large-responses
    match:
      response_size_exceeds: 102400
    action: log_only

Outbound matchers

Outbound actions

Built-in rule packs

• rules/default.yml — sensible defaults (blocks SSH, .env, credentials, dangerous commands, secrets)
• rules/strict.yml — deny-by-default paranoid mode (whitelist only project reads/writes)

Use strict mode:

mcpwall -c /path/to/strict.yml -- npx -y @some/server

CLI

mcpwall [options] -- <command> [args...]   # Proxy mode
mcpwall init                               # Interactive setup
mcpwall wrap <server-name>                 # Wrap specific server

Options:

• -c, --config <path> — path to config file
• --log-level <level> — override log level (debug/info/warn/error)

Audit Logs

All tool calls are logged by default — both allowed and denied. Logs are written as JSON Lines to ~/.mcpwall/logs/YYYY-MM-DD.jsonl:

{"ts":"2026-02-16T14:30:00Z","method":"tools/call","tool":"read_file","action":"allow","rule":null}
{"ts":"2026-02-16T14:30:05Z","method":"tools/call","tool":"read_file","args":"[REDACTED]","action":"deny","rule":"block-ssh-keys","message":"Blocked: access to SSH keys"}

Denied entries have args redacted to prevent secrets from leaking into logs.

mcpwall also prints color-coded output to stderr so you can see decisions in real time.

Security Design

• Bidirectional scanning: Both inbound requests and outbound responses are evaluated against rules
• Fail closed on invalid config: Bad regex in a rule crashes at startup, never silently passes traffic
• Fail open on outbound errors: If response parsing fails, the raw response is forwarded (never blocks legitimate traffic)
• Args redacted on deny: Blocked tool call arguments are never written to logs
• Surgical redaction: Secrets in responses are replaced in-place, preserving the JSON-RPC response structure
• Path traversal defense: not_under matcher uses path.resolve() to prevent ../ bypass
• Pre-compiled regexes: All patterns compiled once at startup for consistent performance
• No network: Zero cloud calls, zero telemetry, runs entirely local
• Deterministic: Same input + same rules = same output, every time

License

Apache-2.0

mcpwall is not affiliated with or endorsed by Anthropic or the Model Context Protocol project. MCP is an open protocol maintained by the Agentic AI Foundation under the Linux Foundation.