Skip to main content
Glama
Sign In
deenesjakoruzh
CURRENT•SEA

CURRENT•SEA

by Bowieboii
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

CURRENT•SEA

Erklärbare Ambiguitätssignale für Text, verfügbar über MCP und REST.

CURRENT•SEA ist ein kleiner, deterministischer Dienst, der KI-Agenten und Software dabei hilft, Formulierungen zu erkennen, die vor einer Reaktion darauf möglicherweise geklärt werden müssen.

Es ist öffentlich als MCP-Server verfügbar:

  • MCP Registry: io.github.Bowieboii/current-sea

  • Aktuelle Registry-Version: 0.0.3

  • Remote-MCP-Endpunkt: https://current-sea.fastapicloud.dev/mcp

  • MCP-Tool: scan_ambiguity

Übermittelter Text wird verarbeitet, aber nicht gespeichert.

Von einem MCP-Client aus verbinden

Für MCP-Clients, die eine mcpServers-Konfiguration akzeptieren, fügen Sie Folgendes hinzu:

{
  "mcpServers": {
    "current-sea": {
      "type": "streamable-http",
      "url": "https://current-sea.fastapicloud.dev/mcp"
    }
  }
}

Diese Konfiguration wurde mit dem offiziellen MCP Inspector verifiziert.

Related MCP server: explain-lint

Was der Dienst erkennt

CURRENT•SEA sucht derzeit nach mehreren häufigen Formen mehrdeutiger Formulierungen, darunter:

  • vage Zeitangaben — soon, later, eventually

  • vage Mengenangaben — some, few, many

  • unsichere Zusagen

  • potenziell unaufgelöste Referenzen — it, them, that

  • subjektive Maßstäbe — reasonable, effective, good, best

Jedes Signal enthält:

  • den Ausdruck, der es ausgelöst hat

  • seine Position im Text

  • die Ambiguitätskategorie

  • eine Erklärung

  • eine vorgeschlagene Klärungsfrage

Beispiel

Eingabe:

Please send it to them soon, include a few examples, and make sure it is good.

Available Tools

1 tool
scan_ambiguityA

Find wording that may need clarification.

Use this when an agent needs an inexpensive, deterministic, explainable check for vague timing, quantities, references, commitments, or standards. The service retains invocation metadata but never the submitted text. Signals are possible issues, not proof of ambiguity.

NameRequiredDescriptionDefault
textYesText to inspect; it is processed but not retained.

Output Schema

NameRequiredDescription

No output parameters

Tool Schema Changelog

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

  1. 1 tool updatev0.0.3
    • First observedscan_ambiguity
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.3/5.0

Scored across 1 tool

Disambiguation5/5

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

Naming Consistency5/5

The single tool name 'scan_ambiguity' follows a clear verb_noun convention, which is consistent and predictable. No conflicting naming styles exist.

Tool Count2/5

A single tool feels too thin for most server purposes. While the scope is narrow, one tool provides minimal utility and may limit agent flexibility, aligning with the 'too few' criterion.

Completeness5/5

For the stated purpose of detecting ambiguous wording, the tool covers the core functionality well. It handles multiple ambiguity types (timing, quantities, references, commitments, standards) with no obvious gaps within that narrow domain.

Maintenance

ActivityStale
ResponsivenessNo recent community issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Prompt Optimizer

    grandinh
    A
    license
    B
    quality
    D
    maintenance
    Automatically analyzes and optimizes AI prompts by calculating clarity scores, detecting risks, asking clarifying questions, and adding domain-specific requirements to improve AI interaction quality.
    1
    MIT

  • jev-mcp

    jkudish
    A
    license
    A
    quality
    A
    maintenance
    Enables agents to verify claims against cited evidence, screen content for prompt injection and relevance before reading it, and rank candidates by meaning, all with calibrated probability verdicts.
    12
    5,273 npm
    574
    MIT

  • Prompt Optimizer MCP

    terngg
    A
    license
    A
    quality
    C
    maintenance
    Enables AI agents to turn rough or ambiguous requests into clearer, context-aware execution guidance through optimization, inspection, adaptation, evaluation, comparison, context compression, and instruction-building tools while preserving original intent and staying local-first.
    9
    27 npm
    MIT