AI agents call get_node_context 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 queries existing data structures (architecture nodes, their annotations, linked items, and dependency analysis) without modifying, deleting, or executing anything. It is a classic Read operation with minimal blast radius if misused by an AI agent—worst case being disclosure of internal project context.
From the tool's definition Tool name 'get_node_context' and description 'Get full context for an architecture node' indicate a retrieval operation.
Attacks that exploit this kind of access
Get full context for an architecture node: annotations, links to tasks/decisions/memory, and impacted-by analysis. 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 get_node_context: 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.
get_node_context 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 get_node_context 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 get_node_context. 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.
get_node_context 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 →