Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
YUSA is an MCP integration. Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
The published mcpb package is https://github.com/yusasecurity/yusa/releases/download/v0.3.5/yusa.mcpb. Its declared MCP transport is stdio.
The package declares YUSA_POLICY: Optional path to a policy JSON (allowTools, allowAddresses, allowHosts, maxValueEth) for yusa_check_tool_call..
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository · Project website. This profile uses version 0.3.5 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related other integrations MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| YUSA_POLICY | Optional path to a policy JSON (allowTools, allowAddresses, allowHosts, maxValueEth) for yusa_check_tool_call. | Check documentation |
Run an Actual Budget ledger from your AI agent, with phone approvals for every change on paired machines.
An Odoo module that serves a read-only MCP endpoint at /mcp, scoped to each user's own access rights.
Research-to-report workflow for agents: plan sources, score them for freshness and conflicts, and reject claims without citations.
Agent memory that keeps every correction with its history, plus saved working state so a crashed run can resume.
Five npm MCP servers for Yandex Wordstat, Search, Webmaster, Metrika and Direct, for SEO and ads work in the Russian market.
A desktop downloader and toolbox that coding agents can drive locally: queue media, read files, check ports.