axomind-mcp
MCP server for Axomind — enables AI assistants to manage activities, mindmaps, and messages through a harmless proxy to the Bot API.
README
<div align="center"> <img src="image/logo_axomind.png" alt="Axomind Logo" width="150"/> <h1>axomind-mcp</h1> <p><strong>MCP server (Model Context Protocol) for Axomind — a harmless proxy to the Bot API.</strong></p> </div>
Principle
The MCP lives on the consumer side, not on the Axomind server. It contains no business logic — it makes an HTTP POST to bot_api.php with id_bot + key_access and returns the JSON. All security (auth, rate limiting, IP bans, bots @> checks) stays on the PHP side.
AI (Hermes/Atlas)
→ stdio → MCP server Python (FastMCP)
→ HTTP POST → bot_api.php (lib_api_access/*)
→ PHP does the work (auth, DB, WS notify)
← JSON response
← MCP tool result → AI
Installation
uv pip install -e .
Dependencies: mcp (official SDK), httpx (HTTP client).
Configuration
Copy .env.example to .env and fill in the bot credentials:
cp .env.example .env
Variables:
AXOMIND_BASE_URL— URL tobot_api.php(e.g.http://xx.xx.xx.xx/app/bot_api.php)AXOMIND_BOT_ID— Bot ID (from Axomind UI → bot management)AXOMIND_BOT_KEY— Bot access keyAXOMIND_TIMEOUT— HTTP timeout in seconds (default: 30)
Available tools (14)
Activity / Planning (5)
| Tool | Description |
|---|---|
list_activities |
List activities where the bot is assigned |
get_activity |
Read a specific activity |
add_assignment |
Assign time slots to an activity |
update_assignment |
Update an assignment group |
delete_assignment |
Delete an assignment group |
Mindmap (5)
| Tool | Description |
|---|---|
list_mindmaps |
List mindmaps where the bot is assigned |
get_mindmap |
Read a mindmap (metadata + nodes) |
replace_mindmap |
Replace all nodes (simplified format) — the AI only needs {title, parent, color?, size_box?} |
add_nodes |
Append nodes to an existing mindmap (simplified format) |
sync_nodes |
Raw sync (full node JSON, for advanced use) |
Simplified format for replace_mindmap / add_nodes
The AI provides a compact JSON — the MCP auto-expands ~25 default fields:
[
{"title": "Root", "parent": 0, "color": "0xFFF0BA6D", "size_box": 2, "bold": true},
{"title": "Category A", "parent": 1, "color": "0xFF7A8FF5", "size_box": 1, "line_style": 1},
{"title": "Item 1", "parent": 2},
{"title": "Item 2", "parent": 2, "color": "0xFFFF6F91", "free_links": [3]}
]
Fields:
title(required) — node titleparent(required) — order_index of the parent node (0 = root, 1 = first node)color(optional) — hex color (default:0xFF7A8FF5)pos_x,pos_y(optional) — canvas position (default: 0)size_box(optional) — 0=normal, 1=category, 2=root (default: 0)bold,italic,underline(optional) — text styleline_type(optional) — 0=curve, 1=rounded, 2=squareline_style(optional) — 0=solid, 1=dashedstroke_width,dot_radius,radius,border_size,label_size(optional)icon_id(optional) — icon IDactive_bg_colors(optional) — active background colorsdescriptions(optional) — descriptive textfree_links(optional) — list of order_index for free links between nodes
UID and order_index are assigned automatically. add_nodes reads the existing mindmap and appends after existing nodes.
Messenger (4)
| Tool | Description |
|---|---|
send_message |
Send a message (targeted or broadcast) |
get_messages |
Read bot messages in a conversation |
update_message |
Update a bot message |
delete_message |
Delete a bot message |
Tests
PYTHONPATH=src python -m pytest tests/ -v
31 tests — mock httpx, no network calls to the Axomind server.
Hermes configuration
In ~/.hermes/config.yaml:
mcp_servers:
axomind:
command: "python3"
args: ["-m", "axomind_mcp.server"]
env:
AXOMIND_BASE_URL: "http://xx.xx.xx.xx/app/bot_api.php"
AXOMIND_BOT_ID: "72"
AXOMIND_BOT_KEY: "your_key_access"
PYTHONPATH: "/path/to/axomind-mcp/src"
workdir: "/path/to/axomind-mcp"
⚠️ All env values must be strings (YAML parses 72 as int → pydantic rejects it).
⚠️ PYTHONPATH is required — workdir sets the cwd but not the Python import path.
Restart Hermes → tools are discovered automatically with the mcp_axomind_ prefix.
Security
- The MCP does not touch the database, read files, or contain any business logic
- Credentials come from environment variables
- The Axomind server cannot tell it's a MCP — it sees normal bot_api requests
- The MCP does not run on production — zero additional attack surface
License
Proprietary — see LICENSE. Copyright © 2025 VEZZANI Sébastien. All rights reserved.
<div align="center"> <a href="https://sebastien-vezzani.xyz/" target="_blank"><img src="https://img.shields.io/badge/Portfolio-3423A6?style=for-the-badge&logo=firefox-browser&logoColor=white" alt="Link to Portfolio"/></a> </div>
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。