// SCAN REPORT

Ai Analyst

26 tools. 12 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 30 Jun 2026

12 can modify or destroy data

14 read-only

26 tools total

Community server · catalogue entry verified 30/06/2026

How to control Ai Analyst ↓

TOOL MAP

What Ai Analyst exposes to your agents

Read (14) Write / Execute (9) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ai Analyst tools

Destructive · Medium clear_query_cache The name suggests purging a query cache, which is typically an irreversible action (cached data is discarded). Destructive · High delete_custom_metric The delete_ prefix signals a destructive operation that cannot be undone. Destructive · High cancel_workflow Cancel an active workflow execution. Execute · High execute_workflow This tool executes workflows containing multiple queries whose outcomes are not predetermined and depend on external inputs (the workflow definition, parameters, and underlying data state).

12 of Ai Analyst's 26 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ai Analyst

PolicyLayer is an MCP gateway — it sits between your AI agents and Ai Analyst, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "cancel_workflow": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_workflow": {
    "limits": [
      {
        "counter": "create_workflow_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "discover_models_for_question": {
    "limits": [
      {
        "counter": "discover_models_for_question_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Ai Analyst — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AI ANALYST →

Instant setup, no code required.

FULL CATALOGUE

All 26 Ai Analyst tools

DESTRUCTIVE 3 tools

Destructive cancel_workflow Cancel an active workflow execution. Destructive clear_query_cache clear_query_cache Destructive delete_custom_metric delete_custom_metric

EXECUTE 6 tools

Execute execute_workflow Execute a multi-query workflow with dependency resolution and optimization. Execute optimize_query optimize_query Execute query_model query_model Execute run_conversion_analysis run_conversion_analysis Execute run_feature_usage_analysis run_feature_usage_analysis Execute test_significance test_significance

WRITE 3 tools

Write create_workflow Create a new multi-query workflow execution from template. Write define_custom_metric define_custom_metric Write export_conversation_summary Export a comprehensive summary of the current conversation and analysis.

READ 14 tools

Read discover_models_for_question discover_models_for_question Read get_contextual_suggestions Get contextual analysis suggestions based on conversation history. Read get_conversation_context Get current conversation context and analysis history. Read get_model Get detailed information about a specific semantic model. Read get_optimization_dashboard Get comprehensive optimization dashboard with performance metrics. Read get_query_performance get_query_performance Read get_sample_queries Get sample queries for a specific model to help users get started. Read get_workflow_status Get current status of a workflow execution. Read health_check Check health of semantic layer and database connections. Read list_custom_metrics list_custom_metrics Read list_models List available semantic models with their descriptions and key metrics. Read list_workflow_templates List available workflow templates for multi-query analysis. Read suggest_analysis suggest_analysis Read suggest_batch_queries suggest_batch_queries

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Ai Analyst

Can an AI agent delete data through the Ai Analyst MCP server? +

Yes. The Ai Analyst server exposes 3 destructive tools including cancel_workflow, clear_query_cache, delete_custom_metric. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Ai Analyst? +

The Ai Analyst server has 3 write tools including create_workflow, define_custom_metric, export_conversation_summary. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ai Analyst.

How many tools does the Ai Analyst MCP server expose? +

26 tools across 4 categories: Destructive, Execute, Read, Write. 14 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on Ai Analyst? +

Register the Ai Analyst MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ai Analyst tool call.

Deterministic rules across all 26 Ai Analyst tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AI ANALYST →

Instant setup, no code required.

26 Ai Analyst tools catalogued and risk-classified — across an index of 43,000+ MCP servers.