n8n-fabric

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.

Category
访问服务器

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


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

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选