Skip to main content
Glama
ai-zen

pdf-parse-mcp

by ai-zen
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
pdf_infoA

读取 PDF 的文档级信息：页数、每页尺寸与旋转角、元数据（标题/作者/生成器等）。用于在抽取前了解文档结构、确定要处理哪些页。坐标：左上原点、y 向下、单位 pt（1pt=1/72 英寸）。

pdf_extractA

抽取 PDF 某一页的全部内容，用于从 PDF 精确还原设计稿：

  • text：文本片段（字符串、基线坐标 x/y、宽高、字号、旋转角、颜色、外框 bbox）

  • shapes：矢量图形（填充/描边色、透明度、线宽、外框 bbox、以及子路径几何：M/L/C/Q/Z 线段；paint="clip" 是不可见的裁剪区）

  • images：位图贴图（外框 bbox、原始像素尺寸、对象名） 坐标：左上原点、y 向下、单位 pt（1pt=1/72 英寸）。 注意：Chrome/Skia 导出的 PDF 常把可见文字画成矢量轮廓，另垫一层不可见的文本对象；这类文本会被标 "covered":true，颜色则由同位置的轮廓反推并标 "colorFrom":"outline"。 建议先整体抽取一次看清结构，图形很多时用 detail="box" 只取外框与样式，再对重点区域用 pdf_extract + pdf_render 局部细看。

pdf_renderA

把 PDF 某一页栅格化成图片（PNG/JPEG）。可用于：整体查看版面、放大局部核对细节、验证还原结果。

  • 默认返回图片本身（base64），Agent 可直接查看；给 save 则写入文件并只返回路径信息。

  • region 可只渲染局部（[x0,y0,x1,y1]，pt，左上原点），配合较大 scale 相当于「放大镜」。 坐标：左上原点、y 向下、单位 pt（1pt=1/72 英寸）。

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: pdf_info inspects document-level metadata, pdf_extract pulls structured content from a page, and pdf_render rasterizes a page or region to an image. There is no overlap in their primary functions.

Naming Consistency5/5

All three tools follow a consistent pdf_<verb> pattern: pdf_info, pdf_extract, pdf_render. The naming clearly communicates the action and is uniform across the set.

Tool Count5/5

Three tools is well-scoped for a PDF parsing server: inspect, extract structured content, and render. Each tool covers a distinct need without redundancy or bloat.

Completeness4/5

The set covers the core PDF inspection workflow: document info, page content extraction, and rasterization. Minor gaps exist such as no direct text search or page-range extraction, but the described workflow is complete for design-reconstruction use cases.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources