AI agents use add_node to create or update resources in AI Charts — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AI Charts environment.
Adding a node creates/modifies chart data reversibly. It does not execute code, destroy data, or move money. It is clearly Write rather than Execute because it manipulates a known data structure (a diagram) with predictable, bounded effects. The severity is low because misuse would only affect the target chart's structure, causing no damage beyond visual/informational consequence.
From the tool's definition Tool name 'add_node' and description 'Add a single node to a chart' — creates a new diagram element reversibly. This is a data creation operation without side effects beyond the chart structure itself.
Attacks that exploit this kind of access
Add a single node to a chart. Width/height optional — omit for auto-size. It is categorised as a Write tool in the AI Charts MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AI Charts MCP server in PolicyLayer and add a rule for add_node: 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 AI Charts. Nothing to install.
add_node is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_node 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 add_node. 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.
add_node is provided by the AI Charts MCP server (tjameswilliams/ai-charts). 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 →