What's Allowed runs on your own machine — the client starts it, so there is no endpoint to ping. 33 installs a week from npm. Last commit 12 Aug 2026.
Merged agent permission rules: which settings file wins, and which rules your client ignores.
We read the source, 21 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
"`devbox run rm -rf .`. These runners are not in Claude Code's built-in wrapper list, so the " +
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch What's Allowed and you get told the day something new turns up.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add whats-allowed-mcp -- npx -y whats-allowed-mcp
{
"mcpServers": {
"whats-allowed-mcp": {
"args": [
"-y",
"whats-allowed-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.whats-allowed-mcp]
command = "npx"
args = ["-y", "whats-allowed-mcp"]
{
"mcpServers": {
"whats-allowed-mcp": {
"args": [
"-y",
"whats-allowed-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"whats-allowed-mcp": {
"args": [
"-y",
"whats-allowed-mcp"
],
"command": "npx"
}
}
}
Secure permission layer between AI agents and your .env files
What fills your agent's context window before a session starts: skill descriptions, memory files.
View client requests, prepare actions and approve work within your firm's permissions.
Shared memory for all your AI agents, your whole team and every MCP client — save, search, recall.
Session memory for AI coding agents. Search past sessions, extract rules, and track what works.
Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.
Search 500+ curated design websites and install DESIGN.md files directly from your AI agent.
Agent memory on your own Postgres that flags superseded facts and abstains instead of guessing.
Answers built from our own checks of this server.