Agent Knowledge MCP
# Agent Knowledge MCP 🔍
**Complete knowledge management for AI assistants**
MCP server with Elasticsearch search and document management.
<a href="https://glama.ai/mcp/servers/@itshare4u/AgentKnowledgeMCP">
<img width="380" height="200" src="https://glama.ai/mcp/servers/@itshare4u/AgentKnowledgeMCP/badge" alt="Agent Knowledge MCP server" />
</a>
[](https://python.org)
[](https://modelcontextprotocol.io)
[](LICENSE)
## 🚀 Features
**🔑 All-in-One Solution:**
- 🔍 **Elasticsearch**: Search, index, and manage documents
- 📊 **Document Validation**: Schema-enforced structure
- ⚙️ **Configuration**: Complete config management
- 🛡️ **Security**: Sandboxed operations
**✨ Benefits:**
- 🎯 **20 Tools** for knowledge management
- 🤖 **Works with any MCP-compatible AI** (Claude, ChatGPT, VS Code, etc.)
- 📚 **Smart document management** with validation
- ⚡ **Elasticsearch integration** for powerful search
## ⚡ Quick Start
### Installation
```bash
# Install with uvx (recommended)
uvx agent-knowledge-mcp
```
### Setup for Claude Desktop
Add to `claude_desktop_config.json`:
```json
{
"mcpServers": {
"agent-knowledge": {
"command": "uvx",
"args": ["agent-knowledge-mcp"]
}
}
}
```
### Setup for VS Code
[](https://insiders.vscode.dev/redirect/mcp/install?name=agent-knowledge&inputs=%5B%5D&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22agent-knowledge-mcp%22%5D%7D)
## 🛠️ What You Can Do
**Try these with your AI assistant:**
- *"Search documents for API authentication info"*
- *"Index this document with proper tags"*
- *"Create API documentation template"*
- *"Find related documents on specific topics"*
- *"Update configuration settings"*
- *"Validate document structure"*
## 🔧 Tools Overview
**Tools for knowledge management:**
| Category | Tools | Description |
|----------|-------|-------------|
| **🔍 Elasticsearch** | 9 | Search, index, manage documents |
| **⚙️ Administration** | 11 | Config, security, monitoring |
## 🔒 Security & Configuration
**Enterprise-grade security:**
- ✅ **Sandboxed operations** - Configurable access controls
- ✅ **Strict schema validation** - Enforce document structure
- ✅ **Audit trails** - Full operation logging
- ✅ **No cloud dependencies** - Everything runs locally
**Configuration example:**
```json
{
"security": {
"log_all_operations": true
},
"document_validation": {
"strict_schema_validation": true,
"allow_extra_fields": false
}
}
```
## 🤝 Contributing & Support
### Development
```bash
git clone https://github.com/itshare4u/AgentKnowledgeMCP.git
cd AgentKnowledgeMCP
pip install -r requirements.txt
python3 src/main_server.py
```
### Support the Project
[](https://coff.ee/itshare4u)
[](https://github.com/sponsors/itshare4u)
---
**Transform your AI into a powerful knowledge management system! 🚀**
*MIT License - Complete knowledge management solution for AI assistants*TDQS
Scored across 27 tools
Most tools have distinct purposes, but some overlap exists. For example, 'ask_mcp_advice' and 'ask_user_advice' both involve seeking guidance, which could cause confusion. However, their descriptions clarify that one uses AI-filtered knowledge and the other involves human input, helping to differentiate them. Overall, the tools are well-defined with minimal ambiguity.
Tool names follow a consistent snake_case pattern with clear verb_noun structures, such as 'create_document_template', 'delete_index', and 'validate_config'. There are no deviations in naming conventions, making the set predictable and easy to understand. This consistency aids in agent selection and reduces confusion.
With 27 tools, the count is borderline high for an MCP server focused on Elasticsearch and knowledge management. While it covers many operations, it may feel heavy and could overwhelm agents. A more streamlined set of 15-20 tools might be more appropriate, but the current scope is still manageable given the domain's complexity.
The tool surface provides comprehensive coverage for Elasticsearch operations and knowledge base management, including CRUD for documents and indices, configuration handling, backup/restore, and validation. There are no obvious gaps; agents can perform full lifecycle management, from setup to maintenance, without encountering dead ends.