// SCAN REPORT

Oracle Models

3 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

1 can modify or destroy data

2 read-only

3 tools total

Community server · catalogue entry verified 02/07/2026

How to control Oracle Models ↓

TOOL MAP

What Oracle Models exposes to your agents

Read (2) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Oracle Models tools

Write · Low format_plan_block This tool creates or formats data (a plan block) for use in a system protocol.

1 of Oracle Models's 3 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Oracle Models

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

Rate limit write operations

{
  "format_plan_block": {
    "limits": [
      {
        "counter": "format_plan_block_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "classify_task": {
    "limits": [
      {
        "counter": "classify_task_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 Oracle Models — 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 ORACLE MODELS →

Instant setup, no code required.

FULL CATALOGUE

All 3 Oracle Models tools

WRITE 1 tools

Write format_plan_block MANDATORY: Generates the formatted output block to be pasted at the end of every plan as a system protocol.

READ 2 tools

Read classify_task MANDATORY: Classifies the complexity of a dev task. If the user input is not in English, translate the core in Read get_model_suggestions Returns suggested models for a tier. Auto-detects your client environment (Claude Code, Gemini CLI, OpenCode,

FAQ

Questions about Oracle Models

How do I prevent bulk modifications through Oracle Models? +

The Oracle Models server has 1 write tools including format_plan_block. 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 Oracle Models.

How many tools does the Oracle Models MCP server expose? +

3 tools across 2 categories: Read, Write. 2 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Oracle Models? +

Register the Oracle Models 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 Oracle Models tool call.

Deterministic rules across all 3 Oracle Models tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ORACLE MODELS →

Instant setup, no code required.

3 Oracle Models tools catalogued and risk-classified — across an index of 43,000+ MCP servers.