AI agents call initial_instructions to retrieve information from RoadBoard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns static instructional/configuration content about how to use the platform. It has no side effects — it only reads and returns protocol documentation. The 'Call this tool ONCE at the start of every session' instruction confirms it is an initialization read, not a write or execute action.
From the tool's definition 'Returns the RoadBoard 2.0 MCP operational protocol: available tools, when to use them, recommended workflow, and operating rules'
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Call this tool ONCE at the start of every session. Returns the RoadBoard 2.0 MCP operational protocol: available tools, when to use them, recommended workflow, and operating rules. It is categorised as a Read tool in the RoadBoard MCP Server, which means it retrieves data without modifying state.
Register the RoadBoard MCP server in PolicyLayer and add a rule for initial_instructions: 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 RoadBoard. Nothing to install.
initial_instructions 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 initial_instructions 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 initial_instructions. 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.
initial_instructions is provided by the RoadBoard MCP server (maless88/roadboard). 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 →