Skip to main content
Glama

@dailui/omega-api-mcp

An MCP server that gives an AI agent one tool to reach the Omega-API judge.

Give agents access to the judge without moving the judge into the agent.

The agent calls the tool with a turn; the judge — which stays on the server — returns a decision and a gate action. Zero judge logic runs in the agent. Apache-2.0. Node 18+.

The tool

omega_judge_turn — judge one agent turn: does the conversational process move? Returns a decision and a gate action. It measures process shape, not whether the goal was reached.

Input:

field

type

notes

input

string (optional)

the user / incoming message

output

string (optional)

the agent's drafted reply (at least one of these)

session_id

string (required)

one id per conversation · the same on every turn · a new id for a new conversation

turn_id

string (optional)

omit for a single agent · Hive member: {agent}_{run_token}_{nnn}

privacy_mode

FULL | REDACTED

optional

Result:

{
  "turn_id": "t_…",
  "decision": "PROCEED | CLARIFY | STOP",
  "reason_family": "…",
  "side": "…",
  "gate": { "action": "release | clarify | suppress | none", "release_original": true }
}

Act on the gate before showing the reply: release → show · clarify → regenerate then call again · suppress → stop or escalate · none → observe only, show.

Related MCP server: Sentinel

Reading agents together (Hive)

A Hive draws the relation of two agents only from a shared token in turn_id, set before the run. Timing can only suggest an association; it never certifies one. Without the token each agent is still judged normally.

turn_id = {agent}_{run_token}_{nnn}
agent      your label · [a-z0-9-]
run_token  10 lowercase hex · one per PAIR of agents, per run · new run = new token
nnn        3 digits shared by both agents for the same exchange (agents counting on their own: s001 · declared, not aligned · no relation graph)

Rules: one session_id per agent for the whole token (a restart needs a new token) · three agents on one token are not certified · a re-used turn_id for a different turn returns 409 TURN_CONFLICT and the turn is not recorded. Full rules: omega.dailui.com/integrations.php and your account's Integration page.

In this server session_id is required on every call (no implicit session: two conversations are never fused); 409 TURN_CONFLICT comes back as a visible tool error.

Before you start: register → key → judge → meter

Register a project and get an API key (oapi_live_…) at https://omega.dailui.com/signup.php. Your first 100 judgments are free; after that, billing applies.

Add it to your MCP host

Most hosts (Claude Desktop, IDE agents) launch MCP servers from a config file. Add:

{
  "mcpServers": {
    "omega-api": {
      "command": "npx",
      "args": ["-y", "@dailui/omega-api-mcp"],
      "env": { "OMEGA_API_KEY": "oapi_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" }
    }
  }
}

The host starts the server over stdio and the omega_judge_turn tool becomes available to the agent.

What it does not claim

It measures whether the process moved. It does not promise the agent achieved the user's goal — the two are independent. It returns no scores or internal measures, only the decision and the gate.

License

Apache-2.0.

Available Tools

1 tool
omega_judge_turnJudge one agent turnA

Judge one agent turn: does the conversational process move? Returns a decision and a gate action. Measures process shape, not whether the goal was reached. Act on the gate before showing the reply: release -> show; clarify -> regenerate then call again; suppress -> stop or escalate; none -> observe only, show.

Inputs: input, output, session_id, privacy_mode. Returns: gate, side, turn_id, decision, +1 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of overlap or confusion. The tool's purpose is clearly specified and distinct by default.

    Naming Consistency5/5

    The single tool name 'omega_judge_turn' follows a clear verb-object pattern and is internally consistent. There is no other tool to conflict with.

    Tool Count3/5

    The server has only one tool, which feels thin for a general-purpose API server. While the tool is well-scoped, the count is borderline per the calibration guidelines.

    Completeness5/5

    Within the narrow domain of judging agent turns, the tool provides a complete lifecycle: it evaluates a turn and returns a decision with the necessary gate action. No obvious dead ends or missing operations are apparent.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      A pre-action authorization server for AI agents that classifies tool calls into 14 intent categories, scores risk 0-100, and produces deterministic allow/deny/ask decisions with full audit trail.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to score their outgoing responses against groundedness and prompt-injection risks mid-turn, returning allow, warn, or block verdicts before the response reaches the user.
      ISC
    • A
      license
      Not graded
      quality
      B
      maintenance
      A local gate that lets agents submit risky tool actions for policy evaluation and receive ALLOW, DENY, or REQUIRE_APPROVE decisions before executing irreversible side effects. It can also open human approval holds and record an activity trail without executing the side effect itself.
      1,614 npm
      3
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables coding agents to send natural language and JSON application state to a judge tool that returns typed judgments (yes/no probability, choice, or score) with model and usage metadata, and fails gracefully without blocking workflows.
      251 npm
      5
      Apache 2.0