Declaw AI runs on your own machine — the client starts it, so there is no endpoint to ping. 37 installs a week from npm. Last commit 13 Aug 2026.
Secure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails.
Today is the operative word: we check Declaw AI every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 mcp-server -- npx -y @declaw/mcp-server
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@declaw/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@declaw/mcp-server"]
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@declaw/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@declaw/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
DECLAW_API_KEY (Declaw API key (create one at https://declaw.ai).), DECLAW_DOMAIN (Optional override for the Declaw API domain (for self-hosted deployments).).
The author declared them in the registry entry; get the values from the project itself.
Security guardrails for AI agent payments
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Secure Linux sandboxes for AI agents, as MCP tools.
Credential isolation for AI agents. Inject secrets at the network boundary.
Pay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust.
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Ephemeral data sandbox for AI workflows with guardrails and security
SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.
Answers built from our own checks of this server.