n8n-fabric
Wraps n8n with an MCP server and vector storage to enable semantic search, management, and execution of automated workflows. It integrates with other tools to make workflows searchable and orchestratable within a larger automation ecosystem.
README
n8n-fabric
Workflow Automation Fabric Layer
n8n-fabric wraps n8n with an MCP server, Qdrant vector storage, and Redis caching—making workflows searchable, memorable, and orchestratable alongside git-steer and aiana.
Architecture
flowchart TB
subgraph FABRIC["n8n-fabric"]
direction TB
mcp["MCP Server"]
embed["Workflow Embedder"]
cache["Cache Layer"]
end
subgraph N8N["n8n Engine"]
api["REST API"]
exec["Execution Engine"]
nodes["500+ Nodes"]
end
subgraph STORAGE["Storage"]
qdrant[("Qdrant\nWorkflow Vectors")]
redis[("Redis\nCache & State")]
postgres[("PostgreSQL\nn8n Data")]
end
subgraph ECOSYSTEM["ry-ops Fabric Ecosystem"]
gitsteer["git-steer\nRepo Lifecycle"]
aiana["aiana\nSemantic Memory"]
end
mcp --> api
mcp --> embed
mcp --> cache
embed --> qdrant
cache --> redis
api --> exec
exec --> nodes
api --> postgres
mcp <-.->|"MCP"| gitsteer
mcp <-.->|"MCP"| aiana
style FABRIC fill:#7C3AED,color:#fff
style N8N fill:#FF6D5A,color:#fff
style qdrant fill:#059669,color:#fff
style redis fill:#DC2626,color:#fff
style postgres fill:#336791,color:#fff
<p align="center"> <img src="./assets/n8n-fabric-architecture.svg" alt="n8n-fabric Architecture" width="100%"> </p>
Features
MCP Server
- Full n8n API access - Workflows, executions, credentials, nodes
- Semantic search - Find workflows by meaning, not just name
- Cross-fabric coordination - Works with git-steer and aiana
Workflow Intelligence
- Vector embeddings - Workflows stored in Qdrant for similarity search
- Pattern recognition - "How did I handle webhook → transform → API?"
- Playbook recall - Find and reuse proven workflow patterns
Infrastructure
- Docker Compose - One command to run full stack
- Redis caching - Fast workflow metadata and execution state
- PostgreSQL - n8n's persistent storage
Quick Start
Docker Compose (Recommended)
# Clone repository
git clone https://github.com/ry-ops/n8n-fabric
cd n8n-fabric
# Start full stack (n8n + Qdrant + Redis + PostgreSQL)
docker compose up -d
# Check status
docker compose ps
# View n8n UI
open http://localhost:5678
Local Development
# Install dependencies
uv sync
# Set environment variables
export N8N_URL=http://localhost:5678
export N8N_API_KEY=your-api-key
# Run MCP server
uv run n8n-fabric-mcp
MCP Tools
Workflow Management
| Tool | Description |
|---|---|
workflow_list |
List all workflows with metadata |
workflow_get |
Get workflow by ID (full JSON) |
workflow_create |
Create new workflow from JSON |
workflow_update |
Update existing workflow |
workflow_delete |
Delete workflow |
workflow_activate |
Activate workflow |
workflow_deactivate |
Deactivate workflow |
workflow_execute |
Execute workflow manually |
workflow_search |
Semantic search across workflows |
Execution Management
| Tool | Description |
|---|---|
execution_list |
List executions with filters |
execution_get |
Get execution details and data |
execution_delete |
Delete execution |
execution_retry |
Retry failed execution |
execution_stop |
Stop running execution |
Credentials & Nodes
| Tool | Description |
|---|---|
credential_list |
List credential names (no secrets) |
credential_create |
Create new credential |
credential_delete |
Delete credential |
node_types |
List available node types |
node_info |
Get node type details |
System & Status
| Tool | Description |
|---|---|
n8n_status |
n8n health and version |
fabric_status |
Full stack health check |
fabric_sync |
Sync workflows to Qdrant |
Configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
N8N_URL |
n8n API URL | http://localhost:5678 |
N8N_API_KEY |
n8n API key | (required) |
QDRANT_URL |
Qdrant URL | http://localhost:6343 |
REDIS_URL |
Redis URL | redis://localhost:6389 |
N8N_ENCRYPTION_KEY |
n8n encryption key | (required for production) |
Note: Ports 6343 and 6389 are used to avoid conflicts with existing Qdrant/Redis instances.
Claude Desktop Integration
{
"mcpServers": {
"n8n-fabric": {
"command": "uv",
"args": ["run", "n8n-fabric-mcp"],
"cwd": "/path/to/n8n-fabric"
}
}
}
Fabric Ecosystem
n8n-fabric is part of the ry-ops fabric ecosystem:
| Fabric | Role | MCP Tools |
|---|---|---|
| n8n-fabric | Workflow execution, playbooks | Workflows, executions, credentials |
| git-steer | Repo lifecycle, version control | Repos, branches, security, PRs |
| aiana | Semantic memory, pattern recall | Memory search, context injection |
Cross-Fabric Examples
"Remember how I built the Slack notification workflow"
→ aiana searches memory
→ n8n-fabric retrieves workflow
→ Returns full workflow JSON
"Create a new webhook-to-Slack workflow and commit it"
→ n8n-fabric creates workflow
→ git-steer commits workflow JSON to repo
→ aiana indexes for future recall
"Run my deployment notification playbook"
→ aiana recalls playbook pattern
→ n8n-fabric executes workflow
→ git-steer logs deployment
Documentation
- CLAUDE.md - AI assistant context
- Architecture - Technical design
- ADR-001 - Fabric design decisions
License
MIT License - see LICENSE file for details.
Repository: github.com/ry-ops/n8n-fabric
Status: Alpha - Initial Development
Version: 0.1.0
Updated: 2026-02-04
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。