Kuriflow Mcp

Name: Kuriflow Mcp
Author: sGuNk13

by sGuNk13communityv0.1.1

Kuriflow MCP Server lets an AI agent turn a one-time solution into a repeatable workflow that can rerun on new data from email, Google Drive, schedules, or manual uploads. It supports remote OAuth/API-key access and local uvx installation for managing workflows, approvals, execution results, and regulatory queries.

From the registry: Make AI tasks repeatable. Run with new data automatically — zero AI tokens per run.

GitHub Repository

Install & configure

Prerequisites

optional
Create a Kuriflow account and generate an API key
Required for API-key-based remote access or local stdio usage. Sign up, then generate an API key in Settings → API Keys.
https://kuriflow.com/signup},{

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `kuriflow-mcp` MCP server into my current AI client (that's you).

Optional prerequisites:
- Create a Kuriflow account and generate an API key — Required for API-key-based remote access or local stdio usage. Sign up, then generate an API key in Settings → API Keys. (https://kuriflow.com/signup},{)

Canonical MCP server config (HTTP transport):
- url: `https://mcp.kuriflow.com`
- headers:
  - `Authorization`: `Bearer <your-api-key>`

Note: README provides multiple connection options: remote HTTP with bearer auth, local stdio via `uvx kuriflow-mcp`, and Claude Cowork OAuth. Per instructions, the simplest portable path is the remote HTTP server. Local stdio alternative shown in README: command `uvx`, args `["kuriflow-mcp"]`, env vars `KURIFLOW_API_KEY` (required) and `KURIFLOW_API_URL` (optional, example default in README omitted here). OAuth via Claude Cowork does not require an API key but is client-specific and not extracted as canonical config.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: README provides multiple connection options: remote HTTP with bearer auth, local stdio via `uvx kuriflow-mcp`, and Claude Cowork OAuth. Per instructions, the simplest portable path is the remote HTTP server. Local stdio alternative shown in README: command `uvx`, args `["kuriflow-mcp"]`, env vars `KURIFLOW_API_KEY` (required) and `KURIFLOW_API_URL` (optional, example default in README omitted here). OAuth via Claude Cowork does not require an API key but is client-specific and not extracted as canonical config.

Tools (8)

save_workflow

Save the AI's solution as a repeatable workflow

run_workflow

Run a saved workflow again with new data

list_workflows

List saved workflows

list_kuris

Browse available workflow types

get_execution_result

Check execution results and download outputs

request_approval

Request human approval before proceeding

get_approval_status

Check the status of an approval decision

query_regulation

Look up regulatory rules

Environment variables

KURIFLOW_API_KEYrequiredAPI key for authenticating local or bearer-auth MCP access

KURIFLOW_API_URLrequiredBase URL for the Kuriflow API

Packages

kuriflow-mcp

pypiv0.1.1transport: stdio

Details

Language: Python
License: MIT
Released: May 8, 2026
Last commit: May 8, 2026
Registry name: io.github.sGuNk13/kuriflow-mcp

Related Servers

Claude Flow

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

68.0k

Codebase Memory Mcp

Persistent codebase knowledge graph. Survives session restarts and context compaction.

39.2k

Serena

A powerful toolkit for coding, providing semantic retrieval and editing capabilities.

28.1k