Agent onboarding. Returns identity, architecture, available tools, skills, guardrails, and quick-start commands. Call this FIRST when connecting to MidOS.
AI agents call midos_bootstrap to retrieve information from MidOS - MCP Community Library without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs agent onboarding by returning read-only metadata: identity, architecture, available tools, skills, guardrails, and quick-start commands. It has no write, execute, or destructive side effects. The worst-case misuse would be information disclosure, which is low severity.
From the tool's definition 'Returns identity, architecture, available tools, skills, guardrails, and quick-start commands' — purely retrieves and returns configuration/onboarding information
Attacks that exploit this kind of access
Agent onboarding. Returns identity, architecture, available tools, skills, guardrails, and quick-start commands. Call this FIRST when connecting to MidOS. It is categorised as a Read tool in the MidOS - MCP Community Library MCP Server, which means it retrieves data without modifying state.
Register the MidOS - MCP Community Library MCP server in PolicyLayer and add a rule for midos_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 MidOS - MCP Community Library. Nothing to install.
midos_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 midos_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 midos_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.
midos_bootstrap is provided by the MidOS - MCP Community Library MCP server (midos-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
midos_bootstrap is one line of MidOS - MCP Community Library's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →