Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NoEdgeAI/doc2x-mcp --skill doc2x-mcpgit clone --depth 1 https://github.com/NoEdgeAI/doc2x-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/noedgeai/doc2x-mcp/doc2x-mcp)<a href="https://agentmods.dev/skills/noedgeai/doc2x-mcp/doc2x-mcp"><img src="https://agentmods.dev/badge/skills/noedgeai/doc2x-mcp/doc2x-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/noedgeai/doc2x-mcp/doc2x-mcp"><img src="https://agentmods.dev/badge/skills/noedgeai/doc2x-mcp/doc2x-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01663 |
| Opus 5 | $0.00000 | $0.00831 |
| Sonnet 5 | $0.00000 | $0.00333 |
| Haiku 4.5 | $0.00000 | $0.00166 |
Grade A, and why
doc2x-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
doc2x-mcp 开发指南
项目概览
@noedgeai-org/doc2x-mcp 是一个 MCP（Model Context Protocol）服务器，通过 stdio 提供 Doc2x PDF/图片解析、格式导出和文件落盘能力。
- 语言：TypeScript（ESM，Node ≥18）
- 包管理：pnpm
- 入口：
src/index.ts→ 构建产物dist/index.js - 发布包名：
@noedgeai-org/doc2x-mcp
目录结构
src/
config/index.ts # 配置：API Key、超时、环境变量解析
doc2x/
client.ts # HTTP 客户端
pdf.ts # PDF 解析 API
convert.ts # 导出 API（md/tex/docx）
image.ts # 图片解析 API
materialize.ts # layout JSON 落盘
download.ts # 文件下载（含 allowlist 校验）
paths.ts # API 路径常量
constants.ts # 通用常量
http.ts # HTTP 工具
mcp/
registerTools.ts # 入口：统一注册所有 tool
registerPdfTools.ts # PDF 相关 tools
registerConvertTools.ts# 导出相关 tools
registerImageTools.ts # 图片相关 tools
registerMiscTools.ts # 杂项 tools（debug config 等）
registerToolsShared.ts # 共享类型、LRU 缓存、Zod schema、工具函数
results.ts # MCP 结果格式化
errors/
error.ts # ToolError
errorCodes.ts # 错误码常量
shared/utils.ts # 通用工具函数
skills/doc2x-mcp/SKILL.md # 用户侧 skill（用于 Claude/Codex 调用指导）
常用命令
just install # pnpm install
just build # tsc 编译
just start # node dist/index.js（stdio MCP 服务器）
just run # build + start
just fmt # prettier 格式化
just fmt-check # 格式检查（CI 用）
just check # fmt-check + build
just clean # 删除 dist/
# 测试
pnpm test # 单元测试 + e2e 测试
pnpm test:unit # 仅单元测试
pnpm test:e2e # 仅 e2e 测试
# skill 安装（开发本地调试用）
just install-skill # 安装到 Codex + Claude
just install-skill-force # 强制覆盖
just install-skill-codex # 仅 Codex
just install-skill-claude # 仅 Claude
环境变量
| 变量 | 说明 | 默认值 |
|---|---|---|
DOC2X_API_KEY |
API Key（也可内嵌在 src/config/index.ts 的 INLINE_DOC2X_API_KEY） |
— |
DOC2X_BASE_URL |
API Base URL | https://v2.doc2x.noedgeai.com |
DOC2X_HTTP_TIMEOUT / DOC2X_HTTP_TIMEOUT_MS |
HTTP 超时（s 或 ms） |
60s |
DOC2X_POLL_INTERVAL_MS |
轮询间隔 | 2000ms |
DOC2X_MAX_WAIT_MS |
最大等待时长 | 600000ms |
DOC2X_PARSE_PDF_MAX_OUTPUT_CHARS |
文本预览最大字符数 | 5000 |
DOC2X_PARSE_PDF_MAX_OUTPUT_PAGES |
文本预览最大页数 | 10 |
DOC2X_DOWNLOAD_URL_ALLOWLIST |
下载域名白名单（逗号分隔，* 表示全放行） |
.amazonaws.com.cn,.aliyuncs.com,.noedgeai.com |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 143 lines · 0 tokens per session scan A 431aea2dc188
doc2x-mcp is a skill published in the GitHub repository NoEdgeAI/doc2x-mcp (3 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,663 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.