Security / mnki-mcp

mnki-mcp

io.github.MNKIAgentOS/mnki-mcp · v0.3.0

MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.

Description supplied by the publisher in the MCP Registry. We have not tested this server.

GitHub repositoryWebsite

Install

npx -y mnki-mcp --agent '<invoice-agent>'

Assembled from the package metadata in the official MCP Registry (including any subcommand or flag the publisher lists). Some publishers do not list the subcommand that starts MCP mode, so confirm the command in the README, along with any required configuration and credentials, before connecting it to real data.

Signals

GitHub stars1
npm weekly downloads55
Last push26d ago
LicenceApache-2.0
Open issues0
SECURITY.mdYes
LanguageTypeScript
Latest version published2026-09-20

Signals captured from GitHub, npm and the official MCP Registry on October 15, 2026. See the scoring method.

Similar servers

AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks

Score 70

Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.

★ 0MITpushed 4d ago
SecurityRemote

mcpcut

Score 78

Journals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval

★ 1↓ 592/wkApache-2.0pushed 7d ago
Security

continuity-evidence

Score 70

A bounded local evidence tool with current agent permission checks and durable retry handling.

★ 0Apache-2.0pushed 5d ago
Security