// SCAN REPORT

Mcp-Omega-Brain

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

12 write tools that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

12 can modify or destroy data

30 read-only

42 tools total

Community server · catalogue entry verified 29/06/2026

How to control Mcp-Omega-Brain ↓

TOOL MAP

What Mcp-Omega-Brain exposes to your agents

Read (30) Write / Execute (12) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Mcp-Omega-Brain tools

Execute · Medium omega_execute Cortex-governed execution wrapper that checks alignment, steers if needed, executes, and auto-logs to the SEAL chain. Execute · Medium omega_seal_run Appends a tamper-proof entry to the SEAL (Secure Evidence Audit Ledger) SHA-256 hash chain. Execute · Medium veritas_run_pipeline Runs the full 10-gate VERITAS pipeline: INTAKE → TYPE → DEPENDENCY → EVIDENCE → MATH → COST → INCENTIVE → SECURITY → ADVERSARY → TRACE/SEAL. Write · Medium omega_complete_task Mark a task you claimed as done, with a result summary. The result is ingested into the vault.

12 of Mcp-Omega-Brain's 42 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp-Omega-Brain

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

Rate limit write operations

{
  "omega_complete_task": {
    "limits": [
      {
        "counter": "omega_complete_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "omega_agents": {
    "limits": [
      {
        "counter": "omega_agents_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 Mcp-Omega-Brain — 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 MCP-OMEGA-BRAIN →

Instant setup, no code required.

FULL CATALOGUE

All 42 Mcp-Omega-Brain tools

EXECUTE 3 tools

Execute omega_execute Cortex-governed execution wrapper that checks alignment, steers if needed, executes, and auto-logs to the SEAL Execute omega_seal_run Appends a tamper-proof entry to the SEAL (Secure Evidence Audit Ledger) SHA-256 hash chain. Execute veritas_run_pipeline Runs the full 10-gate VERITAS pipeline: INTAKE → TYPE → DEPENDENCY → EVIDENCE → MATH → COST → INCENTIVE → SECU

WRITE 9 tools

Write omega_complete_task Mark a task you claimed as done, with a result summary. The result is ingested into the vault. Write omega_handoff Write a handoff note so another agent (or you on another machine) can continue the work. Write omega_post_task Post a task to the shared queue for any agent to claim. Write omega_remember Save a memory, insight, decision, or context fragment to the unified OmegaBrain vault. Write omega_send Send a message to another agent on the network. Use to_agent= Write omega_write_handoff Creates a SHA-256 sealed handoff document that auto-loads on the next server restart via omega://session/prelo Write veritas_claeg_resolve Maps a VERITAS verdict to a CLAEG terminal state: PASS→STABLE_CONTINUATION, MODEL_BOUND/INCONCLUSIVE→ISOLATED_ Write veritas_mis_greedy Runs the MIS_GREEDY algorithm to find the maximum independent set of evidence items with no shared source, cha Write veritas_type_gate Gate 2/10: Enforces type-level correctness — unique primitives, non-empty domains, operator arity, symbol reso

READ 30 tools

Read omega_agents List all registered agents on the network with presence info (online = active in last 15 min). Read omega_brain_report Generates a human-readable audit report showing SEAL chain entries, Cortex verdicts, and vault statistics. Read omega_brain_status Returns a quick health summary of all Omega Brain subsystems as structured JSON. Read omega_claim_task Atomically claim an open task from the shared queue. Returns claimed=false if another agent got it first. Read omega_context Load relevant context from the unified vault for a given task. Returns the most relevant fragments, Read omega_cortex_check Read-only alignment gate that measures semantic similarity between a proposed action and the task baseline. Read omega_cortex_steer Alignment gate with automatic argument correction for drifting tool calls. Read omega_ecosystem_status Returns a unified health snapshot of ALL THREE VERITAS MCP systems: Read omega_inbox Fetch your messages (directed + broadcasts). By default returns unread only and marks them read. Read omega_ingest Stores a new knowledge fragment in the provenance RAG store with source and evidence tier metadata. Read omega_log_session Writes a complete session record to the vault for cross-session persistence. Read omega_preload_context Loads episodic context for a new task by querying the RAG store, vault history, and any sealed handoff. Read omega_rag_query Searches the provenance RAG store using semantic similarity and returns ranked text fragments. Read omega_read_handoff Read the latest open handoff addressed to you (or to anyone). Read omega_recall Search the unified OmegaBrain vault across all agents. Returns semantically similar fragments Read omega_status Check OmegaBrain vault health: row counts per table, embedding engine, vec cache, recent agents. Read omega_subscribe Live inbox peek for active sessions. Returns unread messages with id > since_id, Read omega_tasks List tasks in the shared queue. Filter by status: open (default), claimed, done, cancelled, all. Read omega_vault_search Searches the vault database using exact keyword matching via SQLite FTS5. Read veritas_adversary_gate Gate 9/10: Stress-tests the claim against attack transforms (bound inflation, evidence removal, parameter/evid Read veritas_claeg_transition Validates whether a CLAEG state transition is permitted under closed-world rules (absence of explicit permissi Read veritas_compute_quality Computes the VERITAS Quality(e) score for a single evidence item using: clamp01(0.50provenance + 0.30uncertain Read veritas_cost_gate Gate 6/10: Computes resource utilization as max(cost_i / bound_i) and checks against redline thresholds. Read veritas_dependency_gate Gate 3/10: Analyzes supply-chain security via SBOM scan, CVE check, integrity verification, license compatibil Read veritas_evidence_gate Gate 4/10: Evaluates evidence sufficiency for critical variables by computing independence (MIS_GREEDY), agree Read veritas_incentive_gate Gate 7/10: Detects evidence monoculture by measuring source dominance (max_count_from_single_source / independ Read veritas_intake_gate Gate 1/10: Parses, canonicalizes, and validates a BuildClaim Read veritas_math_gate Gate 5/10: Translates boundary constraints into interval arithmetic or SMT formulas and checks satisfiability Read veritas_nafe_scan Scans text for NAFE failure signatures: Narrative Rescue, Moral Override, Authority Drift, and Intent Inferenc Read veritas_security_gate Gate 8/10: Evaluates security posture from SAST, secret detection, injection surfaces, auth boundaries, and TL

EXPLORE

Related servers

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

FAQ

Questions about Mcp-Omega-Brain

How do I prevent bulk modifications through Mcp-Omega-Brain? +

The Mcp-Omega-Brain server has 9 write tools including omega_complete_task, omega_handoff, omega_post_task. 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 Mcp-Omega-Brain.

How many tools does the Mcp-Omega-Brain MCP server expose? +

42 tools across 3 categories: Execute, Read, Write. 30 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on Mcp-Omega-Brain? +

Register the Mcp-Omega-Brain 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 Mcp-Omega-Brain tool call.

Deterministic rules across all 42 Mcp-Omega-Brain tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP-OMEGA-BRAIN →

Instant setup, no code required.

42 Mcp-Omega-Brain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.