lakehouse_fix

THE RISK

High Risk

Why lakehouse_fix needs a policy

This tool executes Spark SQL statements against a Lakehouse through the Livy API. Running arbitrary Spark SQL can modify, overwrite, or delete data in the Lakehouse depending on the fixes applied. It spans Write and potentially Destructive, but since it executes code/queries via an external API (Livy), Execute is the most appropriate category.

From the tool's definition AUTO-FIX: Applies Spark SQL fixes to a Lakehouse via Livy API (no notebooks needed)

Documented attack patterns abuse exactly the kind of access lakehouse_fix gives an agent:

POLICY

How to control lakehouse_fix

PolicyLayer is an MCP gateway — it sits between your AI agents and Force Fabric MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for lakehouse_fix:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "lakehouse_fix": {
      "limits": [
        {
          "counter": "lakehouse_fix_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

lakehouse_fix stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Force Fabric MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Force Fabric MCP Server tools

Destructive auth_logout Logout from Microsoft Fabric and clear cached credentials. Execute lakehouse_run_table_maintenance Run table maintenance (OPTIMIZE with V-Order, Z-ORDER, VACUUM) on a Fabric Lakehouse. Execute eventhouse_auto_optimize AUTO-OPTIMIZE: Scans a Fabric Eventhouse for all fixable issues across all KQL databases a Execute eventhouse_fix AUTO-FIX: Applies fixes to a Fabric Eventhouse. Execute eventhouse_fix_materialized_views AUTO-FIX: Diagnoses and repairs broken materialized views in a Fabric Eventhouse. Execute gateway_fix AUTO-FIX: Applies fixes to gateway and connection issues. Execute lakehouse_auto_optimize AUTO-OPTIMIZE: Discovers ALL Delta tables in a Lakehouse and applies fixes to every table Execute semantic_model_fix AUTO-FIX: Uses XMLA/TMSL commands for atomic per-object fixes (measures, columns, tables).

All 33 Force Fabric MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Force Fabric MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about lakehouse_fix

What does the lakehouse_fix tool do? +

AUTO-FIX: Applies Spark SQL fixes to a Lakehouse via Livy API (no notebooks needed). It is categorised as a Execute tool in the Force Fabric MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on lakehouse_fix? +

Register the Force Fabric MCP Server MCP server in PolicyLayer and add a rule for lakehouse_fix: 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 Force Fabric MCP Server. Nothing to install.

What risk level is lakehouse_fix? +

lakehouse_fix is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit lakehouse_fix? +

Yes. Add a rate_limit block to the lakehouse_fix 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.

How do I block lakehouse_fix completely? +

Set action: deny in the PolicyLayer policy for lakehouse_fix. 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.

What MCP server provides lakehouse_fix? +

lakehouse_fix is provided by the Force Fabric MCP Server MCP server (tmdaidevs/force-fabric-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Force Fabric MCP Server tool call.

Start from Force Fabric MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →