// SCAN REPORT

Omnibase

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

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

Last updated: 29 Jun 2026

1 can modify or destroy data

13 read-only

14 tools total

Community server · catalogue entry verified 29/06/2026

How to control Omnibase ↓

TOOL MAP

What Omnibase exposes to your agents

Read (13) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Omnibase tools

Execute · Critical execute_sql This tool executes arbitrary SQL queries, which is a classic Execute category operation.

1 of Omnibase's 14 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Omnibase

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

Cap read operations

{
  "explain_query": {
    "limits": [
      {
        "counter": "explain_query_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 Omnibase — 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 OMNIBASE →

Instant setup, no code required.

FULL CATALOGUE

All 14 Omnibase tools

EXECUTE 1 tools

Execute execute_sql Execute a SQL query. Permission level of the connection determines what

READ 13 tools

Read explain_query Show the query execution plan without executing the query. Set analyze=true to actually run the query and get Read get_distinct_values Show distinct values and their counts for a column. Useful for understanding enums, statuses, categories, and Read get_indexes List indexes across the database or for a specific table. Shows index name, columns, uniqueness, index type (b Read get_relationships Map foreign key relationships across the database. Returns a list of relationships and a graph showing what ea Read get_sample Preview rows from a table. Table name is validated against schema to prevent injection. Supports optional WHER Read get_schema Get database schema. Without tables param: returns summary (table names, column counts, PKs). With tables para Read get_table_stats Column-level statistics for a table: null counts/percentages, distinct values, min/max. Uses a sample (default Read list_connections List all configured database connections Read list_tables List all tables with row counts. Faster than get_schema for a quick overview of what Read query_history View recent query execution history. Shows tool name, connection, SQL, duration, row count, and status. Useful Read search_schema Search for tables and columns by keyword. Searches names and comments. Returns up to 20 results ranked by rele Read test_connection Test a specific database connection. Returns status, latency, and the actual driver error on failure. Use this Read validate_query Check if a SQL query is syntactically valid and would be allowed by the connection

EXPLORE

Related servers

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

FAQ

Questions about Omnibase

Is the Omnibase MCP server safe to use without restrictions? +

The Omnibase server is primarily read-only with 13 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Omnibase MCP server expose? +

14 tools across 2 categories: Execute, Read. 13 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Omnibase? +

Register the Omnibase 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 Omnibase tool call.

Deterministic rules across all 14 Omnibase tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OMNIBASE →

Instant setup, no code required.

14 Omnibase tools catalogued and risk-classified — across an index of 43,000+ MCP servers.