{
  "markdown": "# Twig\n\n> Agents choose you or they don't. Twig makes them choose you.\n\n[![CI](https://github.com/Kind-ling/twig/actions/workflows/ci.yml/badge.svg)](https://github.com/Kind-ling/twig/actions/workflows/ci.yml)\n[![npm](https://img.shields.io/npm/v/@kind-ling/twig)](https://www.npmjs.com/package/@kind-ling/twig)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n\nPart of [Kindling](https://github.com/Kind-ling) — agent SEO for the agent economy.\n\n---\n\n## Free audit. Paid monitoring. Premium intelligence.\n\n| Tier | Features | Price |\n|------|---------|-------|\n| **Free** | `twig analyze` — score your descriptions. `twig optimize` — get better variants. | Always free |\n| **Monitor** | Weekly re-scoring, competitive position, intent trend alerts | $0.50–2.00/report via x402 |\n| **Intelligence** | Category benchmarks, intent corpus, competitive index | $0.50–1.00/query via x402 |\n| **Enterprise** | 15% of measured x402 revenue increase | Performance-based, zero if no improvement |\n\n---\n\n## The Problem\n\nEvery MCP tool has a description. That description is what an LLM reads when deciding whether to call your service. It's the only signal between \"selected\" and \"skipped\".\n\nMost descriptions are garbage.\n\n| Tool | Current Description | Twig Score |\n|------|--------------------|----|\n| `exa/answer` | \"AI-powered answer\" | F (28/100) |\n| `wordspace/invoke` | \"Run wordspace AI agent loop\" | F (31/100) |\n| `exa/find-similar` | \"Find similar pages\" | F (33/100) |\n| `jupiter/portfolio` | \"Wallet portfolio positions\" | D (42/100) |\n\nThese tools are useful. Their descriptions are not. And getting indexed in x402-discovery or MCPay doesn't help if agents skip you because they can't tell what you do.\n\nGetting indexed is table stakes. Twig helps you get **chosen**.\n\n---\n\n## Quick Start\n\n```bash\nnpm install -g @kind-ling/twig\n```\n\n```bash\n# Free — score your descriptions\ntwig analyze https://myservice.com/.well-known/agent.json\n\n# Free — get optimized variants\ntwig optimize https://myservice.com/.well-known/agent.json\n\n# Paid — set up weekly monitoring\ntwig monitor https://myservice.com/.well-known/agent.json\n\n# Paid — see how you rank in your category\ntwig competitive crypto-defi\n\n# Paid — see what agents are actually searching for\ntwig intents crypto-defi\n```\n\n---\n\n## Live API\n\nTwig is available as a hosted API at **https://twig.kind-ling.com**\n\n```bash\n# Health check\ncurl https://twig.kind-ling.com/health\n\n# Analyze any MCP server\ncurl -X POST https://twig.kind-ling.com/analyze \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"url\": \"https://your-mcp-server.com/mcp\"}'\n\n# Optimize descriptions\ncurl -X POST https://twig.kind-ling.com/optimize \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"url\": \"https://your-mcp-server.com/mcp\", \"category\": \"crypto-defi\"}'\n```\n\n**Response format:**\n```json\n{\n  \"ok\": true,\n  \"url\": \"https://your-mcp-server.com/mcp\",\n  \"output\": \"🔍 Analyzing...\\n  Score: 72/100 (C)\\n  ...\"\n}\n```\n\nNo API key required for public endpoints. Rate limits apply.\n\n---\n\n## Scoring Model\n\nThree dimensions, 0–100 each:\n\n| Dimension | Weight | What it measures |\n|-----------|--------|-----------------|\n| **Intent Match** | 40% | Similarity to top agent queries for your category |\n| **Specificity** | 35% | Output format, parameters, constraints, examples present? |\n| **Differentiation** | 25% | Do you stand out from similar services in your category? |\n\n**Grades:** A (85+) · B (70+) · C (55+) · D (40+) · F (<40)\n\nScore below 40 = agents are skipping you.\n\n---\n\n## What Twig Monitors\n\n**Your descriptions** — re-scored weekly against a live intent corpus. Score changes alert you when your positioning drifts.\n\n**Your competitive position** — how you rank vs. similar services in your category. Know when a competitor improves and overtakes you.\n\n**Intent trends** — what agents are searching for this week vs. last. The queries change. Your descriptions need to keep up.\n\n**Volume correlation** — description changes mapped to x402 volume changes. Close the loop between optimization and revenue.\n\n---\n\n## Optimization Variants\n\nTwig generates 3 variants per tool:\n\n**Functional** — Action verb + what + return type:\n> *\"Answers questions with real-time web sources. Returns a cited response with source URLs, confidence score, and supporting quotes. Best for research and fact-checking.\"*\n\n**Structured** — Input → output with constraints:\n> *\"Web Q&A. Input: question string. Returns: answer (string), sources (URL array), confidence (0-1). Supports: factual queries, current events, research synthesis.\"*\n\n**Contextual** — Use case → action → output (highest LLM selectability):\n> *\"Use when you need a factual answer with sourced citations. Queries the web in real-time and synthesizes a response with URLs and supporting quotes. Best for research, fact-checking, and current events.\"*\n\n---\n\n## Before / After\n\n### `exa/answer`\n\n**Before:** `AI-powered answer`  ← F (28/100)\n\n**After (Contextual):** `Use when you need a factual answer with sourced citations. Queries the web in real-time and synthesizes a response with source URLs and supporting quotes. Best for research, fact-checking, and current events.`  ← B (72/100)\n\n### `wordspace/invoke`\n\n**Before:** `Run wordspace AI agent loop`  ← F (31/100)\n\n**After (Structured):** `Executes a Wordspace multi-step agent workflow. Input: task description and optional context. Returns: completed output, intermediate steps, tool calls made. Best for complex tasks requiring multiple tool invocations. $2/call.`  ← B (74/100)\n\n---\n\n## Revenue Model\n\n### Standard (Monitoring)\nWeekly reports are gated via x402 on Base. Set up once, runs automatically.\n\n```bash\ntwig monitor 0xYourWallet --url https://myservice.com/.well-known/agent.json\n```\n\n### Enterprise (Performance-based)\nFor services with existing x402 volume:\n\n1. `twig measure 0xWallet --baseline` — record 7-day baseline\n2. Deploy Twig-optimized descriptions\n3. `twig measure 0xWallet --compare` — measure delta (14–30 days later)\n4. Pay 15% of the revenue increase in USDC on Base\n5. Revenue flat or down? Pay nothing.\n\nEverything measured via on-chain USDC transfer logs. No self-reporting.\n\n---\n\n## Supported Sources\n\n- A2A Agent Cards (`/.well-known/agent.json`)\n- MCP servers (JSON-RPC `tools/list`)\n- OpenAPI specs\n- Local JSON schema files\n- x402-discovery catalog (for competitive analysis)\n\n---\n\n## CLI Reference\n\n```\ntwig analyze <url>              Score descriptions (0-100, free)\ntwig optimize <url>             Generate 3 optimized variants (free)\ntwig monitor <url>              Weekly monitoring (paid via x402)\ntwig competitive <category>     Category ranking (paid via x402)\ntwig intents <category>         Top agent queries (paid via x402)\ntwig measure <wallet>           Measure x402 revenue\ntwig measure <wallet> --baseline   Save baseline\ntwig measure <wallet> --compare    Compare to baseline\ntwig report <wallet>            Revenue report with fee calculation\n\nCategories: crypto-defi, data-feeds, research, computation, media, communication, general\n```\n\n---\n\n*Twig v0.1.0 · [Kind-ling](https://github.com/Kind-ling) · [Permanent Upper Class](https://permanentupperclass.com) · MIT*\n",
  "bytes": 7197,
  "sha": "0429bd0060741dea6c7d5e3d35ee361f4a1b14fbd30bf535ca57a7dd28674e6c",
  "repo_slug": "kind-ling/twig",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_kind_ling_twig_de7e4fe5/readme"
}