analyze_charts
AI agents call analyze_charts to retrieve information from Insight Digger MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server context indicate a read-only analysis operation on chart data. Although the description is empty (reducing confidence), the naming convention and sibling tools strongly suggest this retrieves or inspects chart metrics/properties rather than creating, modifying, or executing arbitrary code.
From the tool's definition Tool name 'analyze_charts' suggests data analysis/inspection without modification. Server context emphasizes 'discover data sources' and 'execute workflows' (read-oriented). No description provided, limiting precision.
Attacks that exploit this kind of access
analyze_charts. It is categorised as a Read tool in the Insight Digger MCP MCP Server, which means it retrieves data without modifying state.
Register the Insight Digger MCP server in PolicyLayer and add a rule for analyze_charts: 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 Insight Digger MCP. Nothing to install.
analyze_charts 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 analyze_charts 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 analyze_charts. 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.
analyze_charts is provided by the Insight Digger MCP server (sandsiv/data_narrator_mcp). 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 →