根据当前项目门禁和意图返回是否适合编码、下一步动作和建议 MCP 工具。
AI agents call vguard_development_guidance to retrieve information from Vibe Guard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads project state and intent, then returns advisory information (whether coding is appropriate, next steps, recommended tools). It retrieves and surfaces guidance without modifying data, executing code, or causing side effects. Severity is low as misuse would only result in misleading guidance rather than data loss or system changes.
From the tool's definition '返回是否适合编码、下一步动作和建议 MCP 工具' — the tool returns guidance, next actions, and recommendations based on current project gates and intent
Attacks that exploit this kind of access
根据当前项目门禁和意图返回是否适合编码、下一步动作和建议 MCP 工具。. It is categorised as a Read tool in the Vibe Guard MCP Server, which means it retrieves data without modifying state.
Register the Vibe Guard MCP server in PolicyLayer and add a rule for vguard_development_guidance: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Vibe Guard. Nothing to install.
vguard_development_guidance is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the vguard_development_guidance rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for vguard_development_guidance. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
vguard_development_guidance is provided by the Vibe Guard MCP server (sikuai2333/vibe-guard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →