mineru-mcp: Instructions file for Claude Code

CLAUDE.md

mineru-mcp CLAUDE.md is an instructions file for Claude Code from linxule/mineru-mcp. It costs 1,532 tokens per session, scanned A, original, MIT.

Project instructions for MinerU MCP, a server that sends PDFs, Word files, presentations, or images to the MinerU document-parsing service and receives Markdown text. It also explains how to manage the required API key.

In plain words
What is it for?
Use it when developing, configuring, or debugging the MinerU MCP server, its TypeScript build, or its API-key setup.
Why use it?
It helps developers build and troubleshoot the document-parsing integration, especially when authentication tokens expire.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is linxule/mineru-mcp's own configuration. It tells Claude Code how to work on mineru-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mineru-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to linxule/mineru-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/linxule/mineru-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/linxule/mineru-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for mineru-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/linxule/mineru-mcp/claude-md.svg)](https://agentmods.dev/instructions/linxule/mineru-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/linxule/mineru-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/linxule/mineru-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,532 This file is loaded in full into every session.
When invoked 1,532 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01532 $0.01532
Opus 5 $0.00766 $0.00766
Sonnet 5 $0.00306 $0.00306
Haiku 4.5 $0.00153 $0.00153

Measured 8d ago against content hash b859e2d23e52, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mineru-mcp CLAUDE.md 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 8d 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.

CLAUDE.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mineru-mcp

MCP server for MinerU document parsing API — PDF/DOC/PPT/images to markdown.

Quick Reference

  • Language: TypeScript/Node
  • Package manager: bun
  • Build: bun run build (outputs to dist/)
  • Dev: bun run dev (tsx, stdio mode)
  • Entry: src/index.ts (stdio) / src/server.ts (HTTP)

API Key Management

  • Provider: MinerU (OpenXLab) — https://mineru.net
  • Format: JWT token (Bearer auth)
  • Expiry: Tokens auto-expire after ~90 days from issuance
  • Don't hard-code the expiry date here — a stale one is worse than none. (This line used to read "Current key expires: 2026-05-19" and sat ~2 months past that, presenting an expired key as current.) Read the real expiry from the token itself:
    # decode the JWT payload -> exp (unix seconds)
    python3 -c "import base64,json,os,sys;t=os.environ['MINERU_API_KEY'].split('.')[1];print(json.loads(base64.urlsafe_b64decode(t+'='*(-len(t)%4)))['exp'])"
    
  • Config location: ~/.claude.json under mcpServers.mineru.env.MINERU_API_KEY (appears in both global and project-level entries)
  • Env var: MINERU_API_KEY
  • Troubleshooting 401: almost always an expired token. Decode exp (above); tokens are not refreshable — generate a new one at mineru.net and update both the global and project-level entries in ~/.claude.json.

Architecture

Single-file server (src/index.ts, ~695 lines) with 6 tools:

Tool Purpose Flow
mineru_parse Parse single URL Returns task_id
mineru_status Check task progress Poll with task_id
mineru_batch Parse multiple URLs (preferred) Returns batch_id
mineru_batch_status Check batch progress Poll with batch_id
mineru_upload_batch Upload local files (slow, use URLs when possible) Returns batch_id
mineru_download_results Download named paper folders Uses batch_id, saves to output_dir

URL workflow (preferred)

mineru_batch (array of public URLs — arXiv, SSRN, publisher sites)
  → mineru_batch_status (poll until all done)
  → mineru_download_results (extracts named paper folders)

Read the full file on GitHub · 115 lines

Changes

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.

  1. 8d ago First seen · 115 lines · 1,532 tokens per session scan A b859e2d23e52

Subscribe to this mod's changes

mineru-mcp CLAUDE.md is an instructions file published in the GitHub repository linxule/mineru-mcp (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,532 tokens to every session, about $0.0077 per session on Opus 5. 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens