Skip to main content
Glama
Sign In
pdf-knowledge-mcp

pdf-knowledge-mcp

by tycket033-tech
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

pdf-knowledge-mcp

pdf-knowledge-mcp 是一个面向 PDF 开发经验沉淀的本地 RAG MCP Server。它可以导入 PDF 解析、生成、渲染、文本提取、表格识别、版式分析、字体处理、OCR、PDF/A、签名、加密、性能优化等经验文档，并通过 MCP 工具提供检索和问答能力。

当前实现不依赖远程模型或外部向量数据库。文档会被切分为 chunk，使用本地 TF-IDF 向量和余弦相似度检索，并把索引持久化为 JSON 文件。后续可以在 src/knowledge-store.ts 中替换或扩展 embedding/provider。

安装与构建

cd C:\src\pdf-knowledge-mcp
npm install
npm run build

Related MCP server: MyDocsMCP

启动

npm start

该进程通过 stdio 提供 MCP 服务。

默认知识库索引路径为项目内的 data/pdf-knowledge-index.json。如需指定其他位置：

$env:PDF_KNOWLEDGE_STORE_PATH = "C:\src\pdf-knowledge-mcp\data\pdf-knowledge-index.json"
npm start

MCP 配置

推荐先链接成本地命令：

cd C:\src\pdf-knowledge-mcp
npm link

然后添加到 Codex：

codex mcp add pdf-knowledge -- pdf-knowledge-mcp

通用 MCP 客户端配置示例：

{
  "mcpServers": {
    "pdf-knowledge": {
      "command": "node",
      "args": ["C:/src/pdf-knowledge-mcp/dist/index.js"],
      "env": {
        "PDF_KNOWLEDGE_STORE_PATH": "C:/src/pdf-knowledge-mcp/data/pdf-knowledge-index.json"
      }
    }
  }
}

工具

ingest_document

导入 PDF 开发经验文档。支持直接传入 content，也支持传入 UTF-8 文本、Markdown、JSON、HTML 文件路径。

{
  "title": "PDF text extraction notes",
  "source": "notes/text-extraction.md",
  "tags": ["parsing", "text", "font"],
  "content": "When extracting text from PDF content streams, ToUnicode CMaps are essential...",
  "chunkSize": 1800,
  "chunkOverlap": 200,
  "replaceExisting": true
}

也可以从文件导入：

{
  "filePath": "C:/docs/pdf-rendering-notes.md",
  "tags": ["rendering", "performance"]
}

search_knowledge

基于本地向量索引检索相关经验片段。

{
  "query": "ToUnicode font extraction",
  "limit": 5,
  "tags": ["text"]
}

返回内容包括分数、文档标题、来源、标签、chunk id、命中词和 excerpt。

ask_pdf_expert

先检索知识库，再基于检索结果生成带来源的 PDF 开发回答。

{
  "question": "How should I handle fonts when extracting PDF text?",
  "limit": 5,
  "maxContextChars": 8000
}

如果没有匹配内容，工具会明确提示需要先导入相关经验文档。

验证

npm test

Smoke test 会验证：

  • 文档导入、分块和索引持久化；

  • 本地向量检索和标签过滤；

  • ask_pdf_expert 返回带来源的 RAG 回答；

  • MCP Server 可以通过 stdio 响应 initialize 请求。

说明

这个服务适合作为 PDF 开发经验知识库的基础版本：它先保证本地、可追溯、可运行。未来可以扩展的方向包括真实 embedding 模型、SQLite/向量数据库、PDF/Docx 文档解析器、自动目录同步、以及与 pdf-debug-mcp、pdf-specification-mcp 的联合查询。

Available Tools

3 tools
ask_pdf_expertB

Answer a PDF development question by retrieving relevant local knowledge first and returning an answer with citations.

Inputs: question (required), tags, limit, maxContextChars.

ingest_documentA

Ingest a PDF development experience document into the local RAG knowledge base. The server chunks, vectorizes, indexes, and persists the content locally.

Inputs: tags, title, source, content, +4 more.

search_knowledgeA

Search the local PDF development knowledge base with semantic-style TF-IDF vector retrieval and return ranked chunks with source references.

Inputs: query (required), tags, limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

    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

    A3.9/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool serves a distinct purpose: ingest for adding documents, search for retrieval, and ask for QA with citations. No overlapping functionality.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern in snake_case (ask_pdf_expert, ingest_document, search_knowledge), making their roles clear.

    Tool Count4/5

    Three tools is a minimal but reasonable set for a knowledge base server, covering the core operations of ingestion, retrieval, and question answering.

    Completeness4/5

    The server covers the essential CRUD-like operations for a RAG system (ingest, search, QA). Missing delete or update, but these are less critical for the domain.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers