Systemonomic
Model work domains using Cognitive Work Analysis, score tasks for AI suitability, and design organisations.
README
Systemonomic MCP Servers
<!-- mcp-name: io.github.TonyC23/systemonomic-mcp -->
MCP (Model Context Protocol) servers that expose Systemonomic's Work Domain Analysis, ATSS assessment, and organizational design capabilities to AI agents (Claude Desktop, Cursor, Claude Code, etc.).
Quick Start
1. Install
pip install systemonomic-mcp
2. Get an API Key
- Log in to Systemonomic
- Go to Profile → API Keys
- Click Generate API Key
- Copy the key (starts with
sk_sys_) — it's shown only once
3. Configure
Set the environment variable:
export SYSTEMONOMIC_API_KEY="sk_sys_your_key_here"
Optionally, point to a different API endpoint (defaults to production):
export SYSTEMONOMIC_API_URL="https://your-dev-backend.up.railway.app"
4. Add to Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"systemonomic-wda": {
"command": "python",
"args": ["-m", "systemonomic_mcp.wda_server"],
"env": {
"SYSTEMONOMIC_API_KEY": "sk_sys_your_key_here"
}
},
"systemonomic-atss": {
"command": "python",
"args": ["-m", "systemonomic_mcp.atss_server"],
"env": {
"SYSTEMONOMIC_API_KEY": "sk_sys_your_key_here"
}
},
"systemonomic-org": {
"command": "python",
"args": ["-m", "systemonomic_mcp.org_server"],
"env": {
"SYSTEMONOMIC_API_KEY": "sk_sys_your_key_here"
}
}
}
}
5. Add to Cursor
In Cursor Settings → MCP Servers, add each server:
- Name:
systemonomic-wda - Command:
python -m systemonomic_mcp.wda_server - Environment:
SYSTEMONOMIC_API_KEY=sk_sys_...
Repeat for atss_server and org_server.
Available Servers
systemonomic-wda — Work Domain Analysis
| Tool | Description |
|---|---|
list_projects |
List all projects |
get_project_state |
Get complete project state |
create_project |
Create a new project |
get_project_stats |
Get project statistics |
list_wda_nodes |
List WDA nodes |
create_wda_node |
Create a node at a WDA level |
update_wda_node |
Update a node's label/level/description |
delete_wda_node |
Delete a node |
list_wda_links |
List means-ends links |
create_wda_link |
Link two nodes |
delete_wda_link |
Remove a link |
generate_wda |
AI-generate a full WDA from a text description |
export_project |
Export project as JSON |
import_wda |
Import nodes and links |
systemonomic-atss — Assessment & Tasks
| Tool | Description |
|---|---|
list_tasks |
List project tasks |
create_task |
Create a task |
generate_tasks_from_wda |
Auto-generate tasks from WDA Objects |
derive_task_suggestions |
AI-derived task suggestions |
list_suggestions |
List pending suggestions |
accept_suggestions |
Promote suggestions to tasks |
run_atss_batch |
Run ATSS assessment on all tasks |
get_atss_results |
Get stored assessment results |
persist_atss_results |
Save assessment results |
list_atss_runs |
List assessment run history |
systemonomic-org — Organizational Design
| Tool | Description |
|---|---|
get_org_design |
Get current roles, org units, allocations |
persist_org_design |
Save org design |
propose_restructure |
AI-generated restructure proposal |
apply_proposal |
Apply a restructure proposal |
validate_raci |
Validate RACI matrix |
create_org_snapshot |
Create version snapshot |
list_org_snapshots |
List snapshots |
export_org_design_json |
Export as JSON |
generate_pdf_report |
Generate comprehensive PDF report |
get_report_status |
Check report readiness |
Example Conversations
"Help me model our procurement process"
You: Generate a WDA for our university procurement department. They handle purchase requests, vendor management, contract negotiation, and compliance with government regulations.
Claude: Uses
create_project→generate_wda→ returns the generated hierarchy
"Assess which tasks can be automated"
You: For the procurement project, derive tasks from the WDA and run an automation assessment.
Claude: Uses
generate_tasks_from_wda→run_atss_batch→ summarizes automation candidates
"Generate the full report"
You: Create a PDF report for the procurement project.
Claude: Uses
generate_pdf_report→ saves the PDF
Development
# Run a server locally for testing
cd mcp
pip install -e .
SYSTEMONOMIC_API_KEY=sk_sys_... python -m systemonomic_mcp.wda_server
# Use the MCP inspector
SYSTEMONOMIC_API_KEY=sk_sys_... mcp dev src/systemonomic_mcp/wda_server.py
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。