Review and analyze formula fields in a SmartSuite application. Without fieldSlug: returns every formula field with its return type, validity (valid:false = broken formula), native complexity score + tier, and structural metrics (function count, nesting depth, reference counts) — sortable by name ...
AI agents call smartsuite_analyze_formulas to retrieve information from SmartSuite MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only analysis and inspection of existing formula field configurations. It retrieves metadata, complexity metrics, and dependency information without creating, modifying, deleting, or executing any formulas or records. The deep:true option computes additional analytics (Impact Index) but remains a read operation. No side effects are possible from its use.
From the tool's definition Tool name 'analyze_formulas' and description 'Review and analyze formula fields' with no mention of modification, deletion, or execution.
Attacks that exploit this kind of access
Review and analyze formula fields in a SmartSuite application. Without fieldSlug: returns every formula field with its return type, validity (valid:false = broken formula), native complexity score + tier, and structural metrics (function count, nesting depth, reference counts) — sortable by name or score. With fieldSlug: returns full detail for one formula plus its dependency graph (resolved [field].[field] reference chains across linked tables) as both an ASCII tree and a Mermaid flowchart. Set deep:true to also compute the cross-table Impact Index (samples record counts and link fan-out — several extra API calls). It is categorised as a Read tool in the SmartSuite MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SmartSuite MCP Server MCP server in PolicyLayer and add a rule for smartsuite_analyze_formulas: 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 SmartSuite MCP Server. Nothing to install.
smartsuite_analyze_formulas 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 smartsuite_analyze_formulas 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 smartsuite_analyze_formulas. 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.
smartsuite_analyze_formulas is provided by the SmartSuite MCP Server MCP server (smartsuitefoundry/smartsuite-mcp-server). 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 →