AI agents call bootstrap to retrieve information from Prompts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The description states the tool automatically reads project context (context.md, todos, module records). This is a data retrieval operation with no explicit side effects mentioned. It is described as the first step when an agent starts, acting as an initialization read.
From the tool's definition 自动读取项目上下文（context.md + todos + 模块记录）— 'reads' project context files
Attacks that exploit this kind of access
【一键启动】自动读取项目上下文（context.md + todos + 模块记录）。智能体启动时第一步调用。. It is categorised as a Read tool in the Prompts MCP Server, which means it retrieves data without modifying state.
Register the Prompts MCP server in PolicyLayer and add a rule for bootstrap: 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 Prompts. Nothing to install.
bootstrap 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 bootstrap 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 bootstrap. 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.
bootstrap is provided by the Prompts MCP server (thana0623/pmcp-server). 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 →