astra-knowledge-base-mcp
MCP server for managing and searching multi-tenant knowledge bases backed by SQLite with FTS5, enabling AI agents to persist and retrieve content via full-text search.
README
astra-knowledge-base-mcp
MCP (Model Context Protocol) server for managing and searching multi-tenant knowledge bases.
Part of Astra AI Agent Infrastructure
Overview
Astra Knowledge Base MCP provides AI agents with persistent, searchable knowledge bases backed by SQLite + FTS5 — zero external dependencies, one file per deployment.
Each knowledge base is an isolated namespace with full-text search. Content is auto-chunked on ingestion using recursive text splitting.
Prerequisites
- Python 3.11+
- uv — Python package manager (
pip install uv)
Setup
1. Install dependencies
uv sync
2. Start
uv run server.py
The database file is created at ~/.astra/knowledge-base.db by default. Override with the ASTRA_KB_PATH environment variable.
Configuration
| Variable | Default | Description |
|---|---|---|
ASTRA_KB_PATH |
~/.astra/knowledge-base.db |
Path to the SQLite database file |
Usage
MCP Tools
| Tool | Description |
|---|---|
kb_list |
List all knowledge bases with enable/disable status |
kb_create |
Create a new empty knowledge base |
kb_delete |
Permanently delete a knowledge base and all its content |
kb_enable |
Enable a knowledge base (include in search results) |
kb_disable |
Disable a knowledge base (exclude from search) |
kb_add |
Add text content to a knowledge base (auto-chunked) |
kb_search |
Search across enabled (or specified) knowledge bases |
Registering in Hermes Agent
Add to your Hermes config.yaml:
mcp_servers:
astra-knowledge-base:
command: /path/to/astra-knowledge-base-mcp/run.sh
enabled: true
Then restart Hermes Agent. The tools (kb_list, kb_search, etc.) become available automatically.
Architecture
AI Agent (Hermes)
│ MCP stdio protocol
▼
astra-knowledge-base-mcp (Python, uv run)
│ sqlite3 (stdlib)
▼
SQLite (.db file — ~/.astra/knowledge-base.db)
├── kb_registry ← KB metadata & status
├── chunks ← Content storage
└── chunks_fts ← FTS5 virtual table (auto-synced)
Agent Guide
See AGENTS.md for AI-agent-oriented documentation (entry points, workflows, Hermes integration).
Related
- astra-aiagent-infra — ecosystem portal
- Hermes Agent — AI agent framework
- MCP — Model Context Protocol
License
MIT — see LICENSE.
CI/CD: coming soon — see astra-aiagent-infra for ecosystem-wide pipeline plans.
<p align="center"> <a href="https://star-history.com/#alrcatraz/astra-knowledge-base-mcp&Date"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=alrcatraz/astra-knowledge-base-mcp&type=Date&theme=dark" /> <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=alrcatraz/astra-knowledge-base-mcp&type=Date" /> <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=alrcatraz/astra-knowledge-base-mcp&type=Date" width="600" /> </picture> </a> </p>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。