mcp-agent-template runs on your own machine — the client starts it, so there is no endpoint to ping. 382 installs a week from pypi. Last commit 4 Nov 2026.
Enterprise MCP guard: roles, allowlist policy, human confirmation, JSONL audit log, example tools.
Today is the operative word: we check mcp-agent-template 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-agent-template -- uvx mcp-agent-template
{
"mcpServers": {
"mcp-agent-template": {
"command": "uvx",
"args": [
"mcp-agent-template"
]
}
}
}
[mcp_servers.mcp-agent-template]
command = "uvx"
args = ["mcp-agent-template"]
{
"mcpServers": {
"mcp-agent-template": {
"command": "uvx",
"args": [
"mcp-agent-template"
]
}
}
}
{
"servers": {
"mcp-agent-template": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-agent-template"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
MCP_AGENT_TEMPLATE_ROLE (Caller role: lecteur (read-only), operateur, admin. Defaults to lecteur), MCP_AGENT_TEMPLATE_CONFIRM (elicit: the server asks the human; client: the client confirms itself from destructiveHint), MCP_AGENT_TEMPLATE_AUDIT_DIR (Directory of the JSONL audit log).
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
Remote MCP security gateway for auth, redaction, policy enforcement, and audit logging.
Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.
Security gate for agent-driven WhatsApp: allowlist, secret scan, rate limit, audit log.
Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
AI agent governance: content scanning, audit logs, policy evaluation, session management.
MCP gateway: one connection for your AI apps, with tool policies, PII redaction and audit logs.
Governed read-only warehouse access for agents: SQL guard, row policies, PII pseudonyms, audit log.
Answers built from our own checks of this server.