What are the requirements for AgentWall?

AgentWall requires a compatible MCP client such as Claude Desktop, Claude Code, or Cursor. No additional environment variables are needed for basic setup.

Is AgentWall free to use?

Yes, AgentWall is open source and free to use. You can find the source code on GitHub.

What MCP clients support AgentWall?

AgentWall works with any MCP-compatible client including Claude Desktop (Anthropic's official desktop app), Claude Code (CLI tool), Cursor, and other editors with MCP support.

How do I configure AgentWall?

Configure AgentWall by adding it to your MCP client's config file. The setup block at the top of this page generates a ready-to-paste config for Claude Code, Cursor, Codex, Windsurf, and Claude Desktop.

MCP server/ai-tools

AgentWall MCP Server

Q: How do I install AgentWall?

Install AgentWall by running: npx @agentwall/agentwall setup

Run AI agents safely on your local machine

★ 26 agentwall/agentwall ↗by agentwallupdated Apr 9, 2026

Manual setup required. We don't have a verified install command for this server. Follow the maintainer README and use the raw config below as a starting point.

Prepare the server locally

Run this once before adding it to Claude Code.

npm install -g @agentwall/agentwall
agentwall setup

Add it to Claude Code

Paste the maintainer's config below, then edit any placeholder values.

~/.claude.json

AgentWall automatically wraps your existing MCP servers via the setup command, so manual JSON editing is not required.

See the agentwall README for full setup instructions.

Make your agent remember this setup

agentwall's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.

npx conare@latest

Free · one command · indexes the sessions already on disk. Set up in the browser instead →

What it does

Intercepts and enforces policies on all MCP tool calls
Browser-based approval UI for GUI clients like Cursor and Claude Desktop
YAML-based policy engine with glob matching and SQL content matching
Independent audit log for all tool call activity
Rate limiting to prevent runaway agent loops

Try it

→Check the status of my AgentWall protection to see which servers are currently monitored.

→Open the AgentWall UI to review the latest blocked tool calls.

→Update my policy to deny all shell execution commands by default.

→View the audit log to see what files my AI agent accessed in the last hour.

Original README from agentwall/agentwall

<table> <tr> <td valign="middle"></td> <td valign="middle"><h1>AgentWall</h1></td> </tr> </table>

Run AI agents safely on your local machine

Your AI agent has root access to your filesystem, your database, and your shell. Do you know what it's doing?

AgentWall is a policy-enforcing MCP proxy. It sits between your AI client and every MCP server, intercepts every tool call, and enforces your rules before anything executes. Works with Claude Desktop, Cursor, Windsurf, Claude Code, and OpenClaw — one command to install.

AgentWall demo

The killer feature

AI clients have their own approval flows. AgentWall ignores them.

Claude Desktop approved the call. OpenClaw approved the call. AgentWall blocked both.

18:14:47   mcp        DENY    policy   list_directory   ← BLOCKED despite Claude "Always allow"
18:14:51   openclaw   DENY    policy   exec             ← BLOCKED despite OpenClaw approval

Your YAML policy is the final word. Not the client. Not the model. You.

Features

Works everywhere — Claude Desktop, Cursor, Windsurf, Claude Code, OpenClaw, any MCP client
One command install — npx @agentwall/agentwall setup auto-detects and wraps all your MCP servers
Browser approval UI — approve or deny tool calls from your browser, works in GUI clients with no terminal
YAML policy engine — deny, allow, ask with glob matching, SQL content matching, path rules
Independent audit log — ground truth record of every tool call, regardless of what the model claims
Hot-reload — edit ~/.agentwall/policy.yaml and changes apply instantly, no restart needed
Rate limiting — cap tool calls per minute to catch runaway agent loops
Fully reversible — agentwall undo restores all original configs in one command

Install

npx @agentwall/agentwall setup

AgentWall detects Claude Desktop, Cursor, Windsurf, Claude Code, and OpenClaw. Wraps every MCP server automatically. Backs up your originals. Zero JSON editing.

# Or install globally
npm install -g @agentwall/agentwall
agentwall setup

Requires Node.js >= 22.

To verify protection is active:

agentwall status
# AgentWall v0.8.0
# Protected: Claude Desktop (3 servers) · Cursor (1 server) · OpenClaw
# Policy: ~/.agentwall/policy.yaml
# Decisions today: 47 allowed · 0 blocked · 2 approved

Quick start

# 1. Install and wrap your MCP servers
npx @agentwall/agentwall setup

# 2. Create a default policy (protects credentials, database, shell)
agentwall init

# 3. Start the web UI first — it owns port 7823
agentwall ui
# → http://localhost:7823

# 4. Start OpenClaw gateway (if using OpenClaw)
openclaw gateway
# Detects AgentWall on port 7823 and routes approvals to the browser

# 5. Open your AI client (Claude Desktop, Cursor, etc.)
# MCP proxies spawn automatically and connect to the same UI

Boot order matters. Start agentwall ui before the OpenClaw gateway and before opening AI clients. The gateway and MCP proxies detect the UI on startup and route approval requests to it. If the UI isn't running yet, they fall back to terminal prompts.

Supported clients

Client	Approval method	Integration
Claude Desktop	Browser UI at localhost:7823	MCP proxy
Cursor	Browser UI at localhost:7823	MCP proxy
Windsurf	Browser UI at localhost:7823	MCP proxy
Claude Code	Terminal `y/n/a` prompt	MCP proxy
OpenClaw	Terminal `y/n/a` prompt	Native plugin
Any MCP client	Browser UI or terminal	MCP proxy

GUI clients (Cursor, Claude Desktop, Windsurf) have no terminal — approval requests appear in your browser at http://localhost:7823. Auto-denies after 30 seconds if no response.

Terminal clients (Claude Code, OpenClaw) get an inline y/n/a prompt. Press a to always allow an operation for the rest of the session.

Web UI

agentwall ui    # → http://localhost:7823

Approval / — approve or deny tool calls from your browser in real time. Auto-denies after 30 seconds.

Policy editor /policy — edit rules visually or in raw YAML. Both modes edit the same file. Changes apply instantly.

Log viewer /log — searchable view of everything your agent has done. Filter by runtime, decision, tool name, date.

Clients /clients — see every supported client on your machine, which MCP servers are protected, and wrap

Frequently Asked Questions

What are the key features of AgentWall?

Intercepts and enforces policies on all MCP tool calls. Browser-based approval UI for GUI clients like Cursor and Claude Desktop. YAML-based policy engine with glob matching and SQL content matching. Independent audit log for all tool call activity. Rate limiting to prevent runaway agent loops.

What can I use AgentWall for?

Preventing AI agents from accidentally deleting or modifying sensitive system files. Restricting database access to read-only operations for specific AI sessions. Auditing all tool calls made by an agent to ensure compliance with security policies. Adding a human-in-the-loop approval step for shell commands executed by AI.

How do I install AgentWall?

Install AgentWall by running: npx @agentwall/agentwall setup

What MCP clients work with AgentWall?

AgentWall works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Conare · memory for coding agents

Turn this server into reusable context

Keep AgentWall docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Set up free$npx conare@latest