How do I use pdf-knowledge-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pdf-knowledge-mcp How to extract text from PDF content streams?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

pdf-knowledge-mcp

by tycket033-tech

Overview Schema Related Servers Score Discussions

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.

ParametersJSON Schema

Name	Required	Description
`tags`	No	Only use chunks that contain all of these tags.
`limit`	No	Maximum number of retrieved chunks to use.
`question`	Yes	PDF development question to answer with retrieved local knowledge.
`maxContextChars`	No	Maximum retrieved context characters to include in the answer.

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description only says retrieves knowledge and returns answer with citations. Lacks disclosure on side effects, permissions, or dependencies (e.g., prior ingestion).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that is clear, front-loaded, and efficient. No waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema; description lacks details on answer format, citation structure, or prerequisites. The tool is complex (RAG-based) and needs more context for correct selection and use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% so baseline 3. Description adds context about retrieval but does not enhance parameter meaning beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb 'Answer', resource 'PDF development question', and method 'retrieve local knowledge and return with citations'. Distinguishes from sibling tools like search_knowledge.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage for PDF development questions but provides no explicit when-to-use or when-not-to-use guidance, nor alternatives. The context from siblings is not referenced.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

ingest_documentA

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

ParametersJSON Schema

Name	Required	Description
`tags`	No	Optional tags for classifying or filtering knowledge, such as parsing, rendering, font, ocr, pdfa, signature.
`title`	No	Human readable title. Defaults to the file name or source.
`source`	No	Stable source identifier, such as a file path, URL, note id, or repository path.
`content`	No	Raw text or Markdown content to ingest. Use this or filePath.
`filePath`	No	Path to a UTF-8 text, Markdown, JSON, or HTML document. Relative paths are resolved from the MCP server process cwd.
`chunkSize`	No	Approximate maximum characters per chunk.
`chunkOverlap`	No	Approximate overlapping characters between adjacent chunks.
`replaceExisting`	No	Replace existing documents with the same source before ingesting.

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description clearly discloses the tool's behavior: 'The server chunks, vectorizes, indexes, and persists the content locally.' It accurately describes the write operation, though it could further address idempotency or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with verb and resource, and contains no filler. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (8 parameters, no output schema), the description covers the core process but omits details about supported file types (schema allows non-PDF formats) and post-ingestion querying. It is mostly complete but has a minor inconsistency between description ('PDF') and schema (other formats).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with parameter descriptions present. The description does not add per-parameter meaning beyond the schema, which is acceptable. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Ingest a PDF development experience document into the local RAG knowledge base.' It specifies the verb (ingest), resource (PDF document), and destination (RAG knowledge base), and distinguishes from sibling tools like ask_pdf_expert (query) and search_knowledge (search).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for adding documents to the knowledge base but does not explicitly state when to use this tool versus alternatives like ask_pdf_expert or search_knowledge. No when-not or direct comparisons are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_knowledgeA

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

ParametersJSON Schema

Name	Required	Description
`tags`	No	Only search chunks that contain all of these tags.
`limit`	No	Maximum number of chunks to return.
`query`	Yes	PDF development question, keyword, API name, error symptom, or concept to search for.

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description mentions 'semantic-style TF-IDF vector retrieval' and 'ranked chunks' but doesn't detail limitations, required permissions, or behavior for edge cases. No annotations provided to offset this.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single, concise sentence with no extraneous information. Every phrase adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 3 parameters and no output schema, the description covers the core purpose and return format (ranked chunks). Could be improved by noting range of acceptable queries or performance considerations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with good descriptions for each parameter (query, tags, limit). The description doesn't add significant meaning beyond what the schema already provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool searches a local PDF knowledge base using semantic-style TF-IDF vector retrieval and returns ranked chunks with source references, distinguishing it from siblings like ask_pdf_expert or ingest_document.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage for searching PDF development knowledge, but no explicit guidance on when to use this tool versus ask_pdf_expert (which likely handles interactive Q&A) or ingest_document (which ingests documents).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

3 tool updatesv0.1.0Jun 25, 2026
- First observedask_pdf_expert
- First observedingest_document
- First observedsearch_knowledge

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0

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

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

CustomGPT.ai
ai.customgpt.mcp
The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.
RAG Systems Knowledge & Memory Search
2
Mirror Memory MCP Server
io.github.Tr1ckyMag1ca1
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
Knowledge & Memory Search Note Taking
2
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102
Needle
com.needle-ai.mcp
The Needle MCP server enables semantic search on documents stored in files like PDFs, DOCX, and XLSX by connecting AI applications to external data sources. It provides capabilities to create and manage document collections, perform natural language searches on stored content, and retrieve relevant information without requiring exact keyword matches.
RAG Systems Search File Systems
2

Related MCP Servers

RAG-MCP
RAG Systems Vector Databases
alejandro-ao
F
license
Not graded
quality
D
maintenance
A Retrieval Augmented Generation MCP server that ingests documents into a local vector database and enables semantic search queries.
Updated a year ago (2025-09-26 14:24 UTC)
10
-
MyDocsMCP
RAG Systems Vector Databases File Systems
Edwardmaster7
F
license
A
quality
D
maintenance
MCP server that enables semantic search over local PDF collections using local RAG, with automatic indexing of new documents.
Updated 5 months ago (2026-03-27 12:47 UTC)
5
-
corpus-rag
RAG Systems Knowledge & Memory
monahand1023
A
license
Not graded
quality
A
maintenance
MCP server for local RAG over personal notes, PDFs, and documents, enabling plain-English querying and hybrid search with multi-hop context expansion.
Updated 4 days ago (2026-09-02 16:22 UTC)
MIT
MCP RAG Server
RAG Systems Vector Databases Search
Sujith29k
F
license
Not graded
quality
C
maintenance
MCP server for retrieving answers from local PDFs using RAG with FAISS and OpenAI.
Updated 24 days ago (2026-08-13 10:32 UTC)
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tycket033-tech/pdf-knowledge-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server