mcp-flowise
mcp-flowise
mcp-flowise是一个 Python 包,实现了与 Flowise API 集成的模型上下文协议 (MCP) 服务器。它提供了一种标准化且灵活的方式来列出聊天流、创建预测,并为 Flowise 聊天流或助手动态注册工具。
它支持两种操作模式:
低级模式(默认) :动态注册从 Flowise API 检索的所有聊天流的工具。
FastMCP 模式:提供列出聊天流和创建预测的静态工具,适用于更简单的配置。
特征
动态工具暴露:低级模式为每个聊天流或助手动态创建工具。
更简单的配置:FastMCP 模式公开
list_chatflows和create_prediction工具以进行最少设置。灵活过滤:两种模式都支持通过 ID 或名称(正则表达式)通过白名单和黑名单过滤聊天流。
MCP 集成:无缝集成到 MCP 工作流程中。
Related MCP server: n8n-MCP
安装
通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装 mcp-flowise:
npx -y @smithery/cli install @matthewhand/mcp-flowise --client claude先决条件
Python 3.12 或更高版本
uvx包管理器
通过uvx安装并运行
确认您可以使用uvx直接从 GitHub 存储库运行服务器:
uvx --from git+https://github.com/matthewhand/mcp-flowise mcp-flowise添加到 MCP 生态系统( mcpServers配置)
您可以将mcp-flowise添加到mcpServers配置中,从而将其集成到您的 MCP 生态系统中。例如:
{
"mcpServers": {
"mcp-flowise": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/matthewhand/mcp-flowise",
"mcp-flowise"
],
"env": {
"FLOWISE_API_KEY": "${FLOWISE_API_KEY}",
"FLOWISE_API_ENDPOINT": "${FLOWISE_API_ENDPOINT}"
}
}
}
}操作模式
1.FastMCP模式(简单模式)
通过设置FLOWISE_SIMPLE_MODE=true启用。此模式:
公开两个工具:
list_chatflows和create_prediction。允许使用
FLOWISE_CHATFLOW_ID或FLOWISE_ASSISTANT_ID进行静态配置。通过
list_chatflows列出所有可用的聊天流。
2. 低级模式(FLOWISE_SIMPLE_MODE=False)
特征:
将所有聊天流动态注册为单独的工具。
工具以聊天流程名称命名(规范化)。
使用来自
FLOWISE_CHATFLOW_DESCRIPTIONS变量的描述,如果没有提供描述,则返回到聊天流名称。
例子:
my_tool(question: str) -> str。
使用uvx在 Windows 上运行
如果您在 Windows 上使用uvx时遇到--from git+https的问题,建议的解决方案是将仓库克隆到本地,并使用uvx.exe和克隆仓库的完整路径配置mcpServers 。此外,请根据需要添加APPDATA 、 LOGLEVEL和其他环境变量。
MCP 生态系统的示例配置(Windows 上的mcpServers )
{
"mcpServers": {
"flowise": {
"command": "C:\\Users\\matth\\.local\\bin\\uvx.exe",
"args": [
"--from",
"C:\\Users\\matth\\downloads\\mcp-flowise",
"mcp-flowise"
],
"env": {
"LOGLEVEL": "ERROR",
"APPDATA": "C:\\Users\\matth\\AppData\\Roaming",
"FLOWISE_API_KEY": "your-api-key-goes-here",
"FLOWISE_API_ENDPOINT": "http://localhost:3000/"
}
}
}
}笔记
完整路径:对
uvx.exe和克隆的存储库使用完整路径。环境变量:如果需要,将
APPDATA指向您的 Windows 用户配置文件(例如,C:\\Users\\<username>\\AppData\\Roaming)。日志级别:根据需要调整
LOGLEVEL(ERROR、INFO、DEBUG等)。
环境变量
一般的
FLOWISE_API_KEY:您的 Flowise API Bearer 令牌(必需)。FLOWISE_API_ENDPOINT:Flowise 的基本 URL(默认值:http://localhost:3000)。
低级模式(默认)
FLOWISE_CHATFLOW_DESCRIPTIONS:以逗号分隔的chatflow_id:description对列表。例如:FLOWISE_CHATFLOW_DESCRIPTIONS="abc123:Chatflow One,xyz789:Chatflow Two"
FastMCP 模式( FLOWISE_SIMPLE_MODE=true )
FLOWISE_CHATFLOW_ID:单个聊天流 ID(可选)。FLOWISE_ASSISTANT_ID:单个助手 ID(可选)。FLOWISE_CHATFLOW_DESCRIPTION:针对所公开的单个工具的可选描述。
过滤聊天流
可以使用以下环境变量在两种模式下应用过滤器:
按 ID 加入白名单:
FLOWISE_WHITELIST_ID="id1,id2,id3"按 ID 加入黑名单:
FLOWISE_BLACKLIST_ID="id4,id5"按名称列入白名单(正则表达式) :
FLOWISE_WHITELIST_NAME_REGEX=".*important.*"按名称列入黑名单(正则表达式) :
FLOWISE_BLACKLIST_NAME_REGEX=".*deprecated.*"
注意:白名单优先于黑名单。如果同时设置了白名单和黑名单,则采用最严格的规则。
安全
保护您的 API 密钥:确保
FLOWISE_API_KEY的安全,不会在日志或存储库中暴露。环境配置:使用
.env文件或环境变量进行敏感配置。
将.env添加到你的.gitignore中:
# .gitignore
.env故障排除
缺少 API 密钥:确保
FLOWISE_API_KEY设置正确。无效配置:如果同时设置了
FLOWISE_CHATFLOW_ID和FLOWISE_ASSISTANT_ID,服务器将拒绝启动。连接错误:验证
FLOWISE_API_ENDPOINT是否可访问。
执照
本项目遵循 MIT 许可证。详情请参阅LICENSE文件。
待办事项
[x] Fastmcp 模式
[x] 低级模式
[x] 过滤
[x] Claude 桌面集成
[ ] 助理
Available Tools
2 toolscreate_predictionA
Create a prediction by sending a question to a specific chatflow or assistant.
Args:
chatflow_id (str, optional): The ID of the chatflow to use. Defaults to FLOWISE_CHATFLOW_ID.
question (str): The question or prompt to send to the chatflow.
Returns:
str: The raw JSON response from Flowise API or an error message if something goes wrong.
Inputs: question (required), chatflow_id.
list_chatflowsA
List all available chatflows from the Flowise API.
This function respects optional whitelisting or blacklisting if configured
via FLOWISE_CHATFLOW_WHITELIST or FLOWISE_CHATFLOW_BLACKLIST.
Returns:
str: A JSON-encoded string of filtered chatflows.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: one lists available chatflows, and the other creates predictions using a specific chatflow. There is no overlap in functionality or ambiguity between them.
Both tools follow a consistent verb_noun pattern (list_chatflows, create_prediction) with clear, descriptive names that align with their functions. No deviations or mixed conventions are present.
With only 2 tools, the server feels thin for its apparent domain of interacting with Flowise chatflows. While the tools cover basic operations, the lack of tools for updating, deleting, or managing chatflows suggests an incomplete surface that may limit agent workflows.
The toolset is severely incomplete for a chatflow management domain. It provides listing and prediction creation but lacks essential CRUD operations like creating, updating, or deleting chatflows, as well as tools for managing predictions (e.g., retrieving or canceling them), which will likely cause agent failures in complex tasks.
Maintenance
Related MCP Connectors
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Build and run AI workflows, agents, data tables and 1000+ API integrations from any MCP client.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
CheckFlow’s own MCP server. Ask your AI assistant to start checklists, complete tasks, fill in fields, build templates from written procedures and update Data Sets in CheckFlow. Sign in with your CheckFlow account, or use an API key.
Related MCP Servers
FlicenseNot gradedqualityDmaintenanceThe MCP Server for Weaviate facilitates integration with Weaviate using a customizable Python-based server, enabling interaction with Weaviate databases and OpenAI APIs via configurable URL and API keys.162-- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides AI assistants with access to documentation, schemas, and operations for over 535 n8n workflow automation nodes. It enables models to understand, create, and manage n8n workflows through natural language by connecting to the n8n API.MIT
- AlicenseNot gradedqualityDmaintenanceMCP Server for interacting with the Langflow API via a natural language interface. It exposes Langflow functionalities as tools for LLMs.MIT
- AlicenseAqualityBmaintenanceA Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to Langflow workflow automation platform.31,520 npm10MIT