# mcp-pdf-tokensaver

> mcp-pdf-tokensaver — xiongxingzhe-mcp-pdf-tokensaver. Use this tool when you need to optimize token usage for large language models (LLMs) like Cursor and Claude Desktop, as it analyzes PDF structures to save up to 90% context tokens. The mcp-pdf-tokensaver tool takes PDF files as input and outputs optimized tokenized content, making it ideal for applications with limited token budgets. It is particularly useful for processing complex PDFs with multi-columns, tables, and LaTeX equations.

Canonical page: https://skillsregistry.net/skills/xiongxingzhe-mcp-pdf-tokensaver  
JSON: https://api.skillsregistry.net/v1/skills/xiongxingzhe-mcp-pdf-tokensaver

## Description

A layout-aware local MCP server that analyzes PDF structures (multi-columns, tables, LaTeX equations) to save up to 90% context tokens for LLMs in Cursor and Claude Desktop. Powered by https://golocalpdf.com

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/vdumel1i6y)
- **Repository:** <https://github.com/xiongxingzhe/mcp-pdf-tokensaver>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "xiongxingzhe-mcp-pdf-tokensaver"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/xiongxingzhe-mcp-pdf-tokensaver` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/xiongxingzhe-mcp-pdf-tokensaver/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt