Clawvault MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 63 installs a week from npm. Last commit 6 Mar 2026.
AI agent payment security - spending limits, whitelists, and human approval.
What the code does
We read the source, 6 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
пакет clawvault-mcp-server ссылается на clawvault/mcp-server
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
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 clawvault-mcp-server -e 'CLAWVAULT_API_KEY=<CLAWVAULT_API_KEY>' -- npx -y clawvault-mcp-server{
"mcpServers": {
"clawvault-mcp-server": {
"command": "npx",
"args": [
"-y",
"clawvault-mcp-server"
],
"env": {
"CLAWVAULT_API_KEY": "<CLAWVAULT_API_KEY>"
}
}
}
}[mcp_servers.clawvault-mcp-server]
command = "npx"
args = ["-y", "clawvault-mcp-server"]
env = { CLAWVAULT_API_KEY = "<CLAWVAULT_API_KEY>" }{
"mcpServers": {
"clawvault-mcp-server": {
"command": "npx",
"args": [
"-y",
"clawvault-mcp-server"
],
"env": {
"CLAWVAULT_API_KEY": "<CLAWVAULT_API_KEY>"
}
}
}
}{
"servers": {
"clawvault-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"clawvault-mcp-server"
],
"env": {
"CLAWVAULT_API_KEY": "<CLAWVAULT_API_KEY>"
}
}
}
}Put your own value in place of
<CLAWVAULT_API_KEY> (Your ClawVault API key from the dashboard).
The author’s registry entry marks it as required.
Alternatives to Clawvault MCP Server
same job, measured the same waySecurity guardrails for AI agent payments
Process management and monitoring for AI agents with strict security boundaries
AI agent governance — security scanning, BYOK routing, audit logging, and Council approvals.
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
x402 payment security and pre-execution transaction risk screening for autonomous AI agents.
Real-time semantic security for AI coding agents and MCP tools
Secure agent purchasing with human-approved virtual cards, receipts, and audit trails.
Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend
Clawvault MCP Server — questions
Answers built from our own checks of this server.