// SCAN REPORT

Omni Rag

6 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

5 read-only

6 tools total

Community server · catalogue entry verified 02/07/2026

How to control Omni Rag ↓

TOOL MAP

What Omni Rag exposes to your agents

Read (5) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Omni Rag tools

Execute · Medium ingest_current_directory Triggering an indexing process is an Execute-category action: it runs an operation that processes files and writes index data.

1 of Omni Rag's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Omni Rag

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

Cap read operations

{
  "check_index_status": {
    "limits": [
      {
        "counter": "check_index_status_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 Omni Rag — 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 OMNI RAG →

Instant setup, no code required.

FULL CATALOGUE

All 6 Omni Rag tools

EXECUTE 1 tools

Execute ingest_current_directory [Deprecated: use 'ingest'] Manually trigger indexing.

READ 5 tools

Read check_index_status [Deprecated: use 'check_status'] Check index freshness. Read collection_stats [Deprecated: use 'stats'] Get index statistics. Read get_codebase_context [Deprecated: use 'get_context'] Get directory overview. Read search_codebase [Deprecated: use 'search'] Semantic search over indexed files. Read search_codebase_by_file [Deprecated: use 'search_by_file'] Search filtered by file pattern.

EXPLORE

Related servers

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

FAQ

Questions about Omni Rag

Is the Omni Rag MCP server safe to use without restrictions? +

The Omni Rag server is primarily read-only with 5 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 Omni Rag MCP server expose? +

6 tools across 2 categories: Execute, Read. 5 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Omni Rag? +

Register the Omni Rag 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 Omni Rag tool call.

Deterministic rules across all 6 Omni Rag tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OMNI RAG →

Instant setup, no code required.

6 Omni Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.