広告掲載
MCP.so
ログイン

Text Summarizer MCP Server

@garyedgington

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

garyedgington

投稿者

Gary Edgington

Text Summarizer MCP Server について

Text Summarizer condenses long-form content into structured, actionable summaries so AI agents and applications can work with information faster and at lower cost. Feed it meeting notes, research articles, documentation, JSON payloads, or Markdown files and get back a clean summa

#text-processing#ai#nlp#summarization#content#productivity#markdown#json

Text Summarizer MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "x402-text-summarizer": {
      "url": "https://web-production-78e17.up.railway.app/sse"
    }
  }
}

Text Summarizer MCP Server のツール

2

Compress text, Markdown, or JSON to a structured summary using Claude AI. Supported formats: prose, bullets, headline, tldr. Length presets: brief (~30 words), medium (~80 words), detailed (~200 words). Set target_words (1–500) to override the length preset with an exact word target. Set explain=true to receive a 'notes' field describing what was omitted. Args: input: Text, Markdown, or JSON string to summarize. Max 100KB. input_type: How to interpret the input — text, markdown, or json. format: Output format — prose, bullets, headline, or tldr. length: Length preset — brief, medium, or detailed. Ignored when target_words is set. target_words: Exact target word count (1–500). Overrides length when set. explain: If true, include a notes field describing what was omitted. Returns: summary (str), format (str), word_count (int), compression_ratio (float), notes (str or null), meta (object). On failure: error (str).

Compress text to a prose summary using Claude AI (free trial — prose only, 4KB max). Restrictions: prose format only, brief or medium length only, no target_words, explain always disabled. Use summarize_text for full access to all formats and options. Args: input: Text to summarize. Max 4KB. length: Length preset — brief (~30 words) or medium (~80 words). Returns: summary (str), format (str), word_count (int), compression_ratio (float), notes (null on trial). On failure: error (str).

概要

What is Text Summarizer?

Text Summarizer compresses long-form text to a target length and format using Claude AI. It accepts plain text, Markdown, or JSON input and is part of the x402 micropayment task market. Designed for autonomous agents, document pipelines, and developers needing reliable, cheap per-call text compression without managing prompt engineering or model selection.

How to use Text Summarizer?

Two access modes: via MCP tools over SSE (connect any MCP-compatible client, billing through MCP‑Hive) or via REST with x402 micropayments ($0.005 USDC per call on Base mainnet). A free trial endpoint /v1/summarize/trial is available for prose-only summaries up to 4KB. Add the server URL to your MCP client config or use curl to the paid or trial endpoints with the required request fields.

Key features of Text Summarizer

  • Four output formats: prose, bullets, headline, and TL;DR
  • Three length presets (brief, medium, detailed) or exact word count
  • Free trial endpoint (4KB limit, prose only)
  • Paid endpoint supports 100KB input, all formats
  • Returns compression ratio and optional explain notes
  • x402 v2 USDC micropayment ($0.005/call) on Base mainnet

Use cases of Text Summarizer

  • Compress long documents into concise summaries for AI agents
  • Generate bullet‑point key points from meeting notes or articles
  • Produce short headlines or TL;DRs for content feeds
  • Integrate into document pipelines for automated text reduction

よくある質問

1

What makes Text Summarizer different from using Claude directly?

Text Summarizer handles prompt engineering, length control, and format selection automatically, charges a fixed per‑call fee ($0.005 USDC), and supports both MCP and REST access with no need to manage API keys.

2

What are the runtime requirements and dependencies?

Paid calls require a USDC balance on Base mainnet and an x402‑capable HTTP client. The trial endpoint has no payment requirement. MCP access requires an MCP‑compatible client (billing via MCP‑Hive).

3

Where does my data go during summarization?

Input text is sent to the service, processed by Claude Haiku 4‑5, and the summary is returned in the response. The README does not mention any data storage or retention beyond the single request.

4

What input size limits exist?

The paid endpoint accepts up to 100KB of input; the trial endpoint is limited to 4KB. The trial endpoint only supports the `prose` format.

5

What transports and authentication are supported?

MCP over SSE (no payment signature needed; billing handled by MCP‑Hive) and REST with x402 v2 (requires a `PAYMENT‑SIGNATURE` header after a 402 response). The free trial endpoint requires no authentication.

コメント

「メモリとナレッジ」の他のコンテンツ

Snipara

alopez3006

MCP connector for Snipara, the Project Brain for AI coding agents

1

AOCI-CODE

aoci-spec

Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

1.7K

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

Stele

Stele-Dev

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

The Cloud

Teka

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your

広告掲載