CURRENT•SEA
CURRENT•SEA
面向文本的可解释歧义信号,可通过 MCP 和 REST 使用。
CURRENT•SEA 是一个小型确定性服务,帮助 AI 代理和软件在依据文本采取行动前,检测出可能需要澄清的措辞。
它作为 MCP 服务器公开提供:
MCP 注册表:
io.github.Bowieboii/current-sea当前注册表版本:
0.0.3远程 MCP 端点:
https://current-sea.fastapicloud.dev/mcpMCP 工具:
scan_ambiguity
提交的文本会被处理,但不会被保留。
从 MCP 客户端连接
对于接受 mcpServers 配置的 MCP 客户端,请添加:
{
"mcpServers": {
"current-sea": {
"type": "streamable-http",
"url": "https://current-sea.fastapicloud.dev/mcp"
}
}
}此配置已通过官方 MCP Inspector 验证。
Related MCP server: explain-lint
它检测什么
CURRENT•SEA 目前会查找几种常见的歧义措辞形式,包括:
时间模糊 —
soon,later,eventually数量模糊 —
some,few,many不确定的承诺
可能未解决的指代 —
it,them,that主观标准 —
reasonable,effective,good,best
每个信号包括:
触发该信号的短语
它在文本中的位置
歧义类别
解释
建议的澄清问题
示例
输入:
Please send it to them soon, include a few examples, and make sure it is good.Available Tools
1 toolscan_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.
Inputs: text (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap. The single tool's purpose is clearly defined and distinct by default.
The single tool name 'scan_ambiguity' follows a clear verb_noun convention, which is consistent and predictable. No conflicting naming styles exist.
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.
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
Related MCP Connectors
Explainable ambiguity signals for text. Submitted text is processed but never retained.
Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.
Paid deterministic data-quality and execution-verification tools for AI agents.
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
Related MCP Servers
- AlicenseBqualityDmaintenanceAutomatically analyzes and optimizes AI prompts by calculating clarity scores, detecting risks, asking clarifying questions, and adding domain-specific requirements to improve AI interaction quality.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to identify and judge unexplained terms in prose documents by providing differential linting, term context, and ledger management.MIT
- AlicenseAqualityAmaintenanceEnables 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.124,999 npm586MIT
- AlicenseAqualityCmaintenanceEnables 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.928 npmMIT