Mnki MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 420 installs a week from npm. Last commit 17 Sep 2026.
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
Today is the operative word: we check Mnki MCP 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 mnki-mcp -- npx -y mnki-mcp
{
"mcpServers": {
"mnki-mcp": {
"args": [
"-y",
"mnki-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mnki-mcp]
command = "npx"
args = ["-y", "mnki-mcp"]
{
"mcpServers": {
"mnki-mcp": {
"args": [
"-y",
"mnki-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mnki-mcp": {
"args": [
"-y",
"mnki-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
MNKI_API_KEY (Agent Trust API key with the verify scope (console → Settings → API keys).), MNKI_URL (Console base URL; https://mnki.com unless self-hosted.).
The author declared them in the registry entry; get the values from the project itself.
Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
See, price, and control every tool call your AI agents make: policy checks, cost, and audit tools.
Transparent MCP proxy that independently re-verifies tool-call claims before the Host trusts them.
Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.
MCP security trust-check for agents before installing MCPs, Skills or tools.
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.
Answers built from our own checks of this server.