{
  "markdown": "# PublishReady: Professional Writing Control\n\n[![CI](https://github.com/veldica/publishready-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/veldica/publishready-mcp/actions/workflows/ci.yml)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\n**PublishReady** is a deterministic writing analysis system designed to turn AI drafts into publish-ready writing. It serves as the final QA pass for AI-generated prose, providing local-first metrics, target compliance, and specific revision levers without sending text to remote services.\n\n## The PublishReady Packages\n\nThis project is structured as a professional, layered monorepo containing specialized packages:\n\n### Core Packages\n- **[@veldica/publishready-mcp](packages/mcp)**: The Model Context Protocol (MCP) server implementation (`publishready-mcp`).\n- **[@veldica/publishready-cli](packages/cli)**: The command-line tool for local analysis (`publishready`).\n- **[@veldica/publishready-core](packages/core)**: The central orchestration engine.\n- **[@veldica/publishready-schemas](packages/schemas)**: Unified Zod schemas and explicit interfaces.\n\n### Underlying Libraries\n- **[@veldica/prose-analyzer](https://www.npmjs.com/package/@veldica/prose-analyzer)**: Deterministic style signals (variety, density, repetition, narrative texture).\n- **[@veldica/readability](https://www.npmjs.com/package/@veldica/readability)**: Consolidated library of all major readability formulas.\n- **[@veldica/prose-tokenizer](https://www.npmjs.com/package/@veldica/prose-tokenizer)**: Standalone markdown-aware prose tokenization.\n- **[@veldica/prose-linter](https://www.npmjs.com/package/@veldica/prose-linter)**: Target checks, revision levers, content integrity, and deterministic AI-sounding prose markers.\n\n## Installation\n\n### MCP Server (Recommended)\nAdd the server to your MCP client configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"publishready\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@veldica/publishready-mcp\"]\n    }\n  }\n}\n```\n\n### Command Line\n```bash\nnpx @veldica/publishready-cli analyze sample.txt\n```\n\n### Hosted MCP\nFor Smithery, VPS, or gateway deployments, run the server with Streamable HTTP:\n\n```bash\nnpx @veldica/publishready-mcp --transport=http --port=3000\n```\n\nThe MCP endpoint is `/mcp`; the health endpoint is `/health`.\n\n## Key Features\n\n- **Template, Target, and Reference Modes**: Compare writing against built-in templates, explicit numeric targets, reference text, or reusable reference profiles.\n- **Deterministic Metrics**: Structural counts, sentence and paragraph distributions, lexical signals, scannability, fiction proxies, and readability formulas.\n- **Specific Revision Levers**: Ranked, evidence-based suggestions such as `shorten_long_sentences`, `replace_difficult_words`, and `reduce_abstract_wording`.\n- **AI-Sounding Prose Audit**: Deterministic marker inventory for formulaic, generic, or over-polished prose, including exact matches and tracked phrase counts.\n- **Fiction & Non-Fiction Support**: Narrative metrics for dialogue, sensory density, abstract wording, and scene pacing.\n- **Explainable Interpretation**: Target and metric interpretation that explains audience, use cases, style implications, and tradeoffs.\n- **Local-First & Private**: Stdio-first, deterministic, no external API calls, and no LLM wrappers.\n\n## MCP Tool Surface\n\nThe MCP server exposes 16 specialized tools for analysis and control, including `audit_ai_sounding_prose` for deterministic AI-marker analysis. For a full list and documentation, see the [MCP README](packages/mcp/README.md).\n\n## Deterministic Philosophy\n\nThis package explicitly avoids **perplexity** and other model-dependent scores. We believe writing control should be:\n\n1. **Explainable**: You should know exactly why a score changed.\n2. **Reproducible**: The same text should always yield the same metrics.\n3. **Practical**: A metric is only useful if it tells you what to change.\n\n## Development\n\n```bash\nnpm install\nnpm run build\nnpm run lint\nnpm run typecheck\nnpm test\n```\n\n## Publishing Metadata\n\n- npm package: `@veldica/publishready-mcp`\n- MCP Registry name: `io.github.veldica/publishready`\n- Product homepage: `https://veldica.com/publish-ready`\n- Source repository: `https://github.com/veldica/publishready-mcp`\n\n## Registry and Directory Metadata\n\nPublishReady is prepared for MCP directory discovery through:\n- GitHub repository topics\n- npm package keywords\n- Glama metadata via `glama.json`\n- Official MCP Registry metadata via `mcpName`\n\nThis MCP is designed for AI-assisted writing workflows where the model should improve clarity, structure, readability, and publish-readiness while preserving facts, terminology, intent, and author voice.\n\n## License\n\nMIT\n\n[![smithery badge](https://smithery.ai/badge/veldica/publishready)](https://smithery.ai/servers/veldica/publishready)\n",
  "bytes": 4904,
  "sha": "90b1cc33f10f137af0b498ccfa6ebfdf51e26a24a990a75e28d7921151826366",
  "repo_slug": "veldica/publishready-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_veldica_publishready_e65bb1f9/readme"
}