AI agents use build_chart 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.
This tool creates/constructs a chart by adding nodes and edges, which is a reversible write operation. It creates new data structures (diagrams) without executing code or deleting anything. Severity is medium because an AI agent could misuse it to create large or malformed diagrams, but the blast radius is limited to the diagramming application.
From the tool's definition Build a chart with nodes and edges. Nodes use temp_ids that edges reference.
Attacks that exploit this kind of access
Build a chart with nodes and edges. Nodes use temp_ids that edges reference. 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 build_chart: 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.
build_chart 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 build_chart 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 build_chart. 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.
build_chart 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 →