Skip to main content
Glama
deenesjakoruzh
Enesp4rl4k

enterprise-knowledge-integrator

by Enesp4rl4k
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

🧠 Enterprise Knowledge Integrator

将企业私有数据（PDF、Excel、Word、SQL）连接到 LLM 与 AI 智能体，内置 PII 脱敏、混合搜索与 MCP 服务器。

License: MIT Python 3.9+ FastAPI Model Context Protocol PRs Welcome

实时仪表盘 • 快速上手 • MCP 服务器设置 • 架构 • API 参考

🌟 为什么选择 Enterprise Knowledge Integrator？

企业的知识分散在 PDF 政策文档、Excel/CSV 财务模型、合同和 ERP 笔记中。将这些数据直接输入 LLM 往往会导致 PII 泄露、数字幻觉和上下文丢失。

Enterprise Knowledge Integrator 是一个开源、轻量级、即插即用的中间件，可将您公司的原始文件转换为干净、带引用且安全的上下文，供任何 LLM 或 AI 智能体使用。

Related MCP server: doc-intel MCP server

✨ 核心特性

  • 📄 表格感知 ETL（Excel 与 CSV）：将电子表格行转换为 Markdown 表格和语义行分组，使 LLM 永远不会对行号或公式产生幻觉。

  • 🛡️ 内置 PII 与密钥脱敏器：在嵌入或提示注入之前自动检测并掩码 TCKN、IBAN、信用卡号、税号（VKN）、电话号码和 API 密钥。

  • ⚡ 混合检索（向量 + Okapi BM25 + RRF）：使用倒数排名融合（RRF）将密集嵌入与稀疏关键词匹配相结合，对财务代码和数字实现 100% 准确率。

  • 👥 基于角色的访问控制（RBAC）：强制执行文档密级（Public、Internal、Confidential、Restricted）和部门过滤。

  • 🔍 引用与幻觉验证器：自动将生成的 LLM 答案与源文档进行核对，并计算置信度分数。

  • 🔄 目录自动监视器：监控您的文件夹/云盘挂载，并自动重新索引新增或修改的文件。

  • 🔌 通用网关：

    • Model Context Protocol（MCP），适用于 Cursor、Claude Desktop、Antigravity。

    • FastAPI REST API，带 Swagger UI。

    • 交互式 Web 仪表盘（零额外依赖）。

    • LangChain / LangGraph 工具适配器。

🏛️ 系统架构

graph TD
    subgraph Ingestion ["1. Multi-Source Ingestion & ETL"]
        F1["📄 Documents (PDF, Word, Markdown)"]
        F2["📊 Tabular (Excel, CSV)"]
        F3["🗄️ Notes & Text Snippets"]
        F1 & F2 & F3 --> PII["🛡️ PII Masker (TCKN, IBAN, Cards)"]
        PII --> Chunk["✂️ Semantic & Parent-Child Chunker"]
    end

    subgraph Storage ["2. Storage & Hybrid Search Engine"]
        Chunk --> V["V-Store: Cosine Dense Embeddings"]
        Chunk --> B["BM25: Sparse Keyword Index"]
        V & B --> RRF["🎯 Reciprocal Rank Fusion (RRF)"]
    end

    subgraph Governance ["3. Security & Governance"]
        RRF --> RBAC["👥 RBAC & Clearance Filter"]
        RBAC --> Val["🔍 Citation & Grounding Validator"]
    end

    subgraph Interfaces ["4. LLM & Agent Gateways"]
        Val --> MCP["⚡ MCP Server (Claude Desktop / Cursor)"]
        Val --> API["🌐 FastAPI REST API (/api/v1/context)"]
        Val --> UI["🖥️ Modern Web Dashboard (/dashboard)"]
        Val --> SDK["💼 LangChain / LangGraph Adapter"]
    end

⚡ 60 秒快速上手

1. 安装

git clone https://github.com/your-username/enterprise-knowledge-integrator.git
cd enterprise-knowledge-integrator
pip install -r requirements.txt

2. 启动 Web 仪表盘与 API

python -m knowledge_integrator.interfaces.api.app

在浏览器中打开 http://localhost:8088/dashboard 以访问可视化控制面板。

💻 CLI 用法

摄取文本/政策说明：

python -m knowledge_integrator.interfaces.cli.main ingest-text \
  --title "2025 Travel Policy" \
  --content "Daily travel allowance is 2,500 TL. Stays above 5,000 TL require CFO approval." \
  --category "policy"

摄取文件或目录（PDF、Excel、CSV、Word、Markdown）：

python -m knowledge_integrator.interfaces.cli.main ingest ./company_docs/ --category "finance"

搜索知识库：

python -m knowledge_integrator.interfaces.cli.main query "What is the travel budget limit?"

列出已索引文档：

python -m knowledge_integrator.interfaces.cli.main list

⚡ Model Context Protocol（MCP）服务器

将您的企业知识直接连接到 Claude Desktop、Cursor IDE 或 Antigravity。

将此添加到您的 claude_desktop_config.json 或 cursor settings：

{
  "mcpServers": {
    "company-knowledge": {
      "command": "python",
      "args": ["-m", "knowledge_integrator.interfaces.cli.main", "serve-mcp"]
    }
  }
}

可用 MCP 工具：

  • search_company_knowledge：对私有公司文档执行混合搜索。

  • get_company_context：返回干净、带引用的上下文，可直接用于提示注入。

  • list_company_documents：列出所有已索引的来源和元数据。

  • ingest_company_note：动态保存新的政策或知识片段。

🌐 REST API 参考

方法

端点

描述

POST

/api/v1/ingest/file

上传并索引文件（PDF、Excel、CSV、Word、MD）

POST

/api/v1/ingest/text

摄取原始企业笔记或规则

POST

/api/v1/context

获取带引用的、可直接用于 LLM 的上下文块

POST

/api/v1/search

搜索排序后的分块（混合）

GET

/api/v1/documents

列出所有已索引文档

DELETE

/api/v1/documents/{id}

删除文档及所有关联的嵌入

交互式 Swagger 文档位于：http://localhost:8088/docs

🤖 Python 与 LangChain / LangGraph 集成

from knowledge_integrator import KnowledgeEngine
from knowledge_integrator.agentic_cfo_adapter import AgenticCFOKnowledgeAdapter

# 1. Initialize engine
engine = KnowledgeEngine()

# 2. Ingest document
engine.ingest_file("budget_2025.xlsx", category="finance")

# 3. Retrieve LLM context
ctx = engine.get_context_for_llm("What was the Q3 software budget?")
print(ctx.context_text)

# 4. Use as a LangChain / LangGraph Tool for AI Agents
adapter = AgenticCFOKnowledgeAdapter(engine)
agent_tool = adapter.as_langchain_tool()

🐳 Docker 部署

docker-compose up -d

🧪 运行测试

python -m pytest knowledge_integrator/tests/ -v

📄 许可证

本项目采用 MIT 许可证授权 — 详情请参阅 LICENSE 文件。

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd
A
license - permissive license
Not graded
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Servers

  • Enterprise Knowledge MCP

    j84077200345-dotcom
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables querying enterprise documents (DOCX, PDF, PPTX) using natural language, with hybrid search and MCP integration for Claude Desktop and other agents.
    MIT

  • doc-intel MCP server

    avinashbadgu
    F
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to extract structured data from PDFs with confidence scores and provenance, and to search, review, and correct documents via MCP tools, resources, and prompts.

  • MCP RAG Server

    amaralphp
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables document ingestion, semantic search, and retrieval-augmented generation via MCP tools and REST API, using vector embeddings and intelligent chunking.
    MIT

  • nacre

    nacre-work
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides a self-hosted knowledge index with document-level permissions, enabling AI agents to retrieve exactly the documents they are authorized to see via MCP. Supports OAuth 2.1, custom embedding models, and runs inside your network.
    41
    Apache 2.0

View all related MCP servers

Related MCP Connectors

  • qsearch

    Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.

  • mcp

    Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.

  • Frenchie

    OCR, transcription, file extraction, and image generation for AI agents via MCP.

View all MCP Connectors

Latest Blog Posts

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/Enesp4rl4k/enterprise-knowledge-integrator'

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