Security / mcpcut

mcpcut

io.github.RostislavMatov/mcpcut · v0.4.1

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

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

GitHub repositoryWebsiteCompare alternatives

Install

npx -y mcpcut wrap --server '<server_name>' -- <server_command>

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 downloads592
Last push6d ago
LicenceApache-2.0
Open issues0
SECURITY.mdYes
LanguageTypeScript
Latest version published2026-10-10

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

Similar servers compare all →

Aegis — AI Agent Governance

Score 74

Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.

★ 18MITpushed 2mo ago
Security

mnki-mcp

Score 72

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

★ 1↓ 55/wkApache-2.0pushed 25d ago
Security

mcpwall

Score 79

iptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.

★ 5↓ 52/wkApache-2.0pushed 27d ago
Security