Sequential Story
An MCP server for problem-solving using Sequential Thinking and Sequential Story mnemonic techniques.
Sequential Story MCP Server
A Model Context Protocol (MCP) server for Sequential Thinking and Sequential Story as mnemonic techniques for problem-solving.
Overview
This project offers two complementary MCP tools for structuring complex problems:
-
Sequential Story - A narrative-based approach to sequential thinking. Instead of tracking abstract thoughts, it structures problems as story elements with characters, settings, and plot developments to make them more memorable and engaging.
-
Sequential Thinking - A pure Python port of the JavaScript implementation, eliminating Node.js dependencies
Both approaches leverage the power of sequencing and structure to enhance memory retention and problem understanding.
Features
Sequential Story
- Build problem solutions as narrative sequences
- Revise and branch story elements as needed
- Track characters, settings, tones, and plot points
- Formatted, color-coded display of story elements
Sequential Thinking
- Structure problems as a sequence of thoughts
- Revise or branch thinking paths as needed
- Generate and verify solution hypotheses
- Track thinking process completion
- Pure Python implementation (no Node.js required)
Common Features
- Formatted, color-coded display of elements
- Full MCP protocol support for integration with AI systems
- Support for branching and revision
Installation
During Development
When working with the package locally before publishing:
# Clone the repository
git clone https://github.com/dhkts1/sequentialStory
cd sequentialStory
# Install dependencies using uv
uv venv
source .venv/bin/activate
uv sync
# Install with development dependencies
uv sync --group dev
Installing with MCP
# Install in the Claude desktop app
mcp install -e . src/cli.py -n "Sequential Story"
# Install with only the Sequential Thinking tool
mcp install -e . src/cli.py -n "Sequential Thinking" --env-var "TOOLS='[\"thinking\"]'"
# Install with only the Sequential Story tool explicitly
mcp install -e . src/cli.py -n "Sequential Story" --env-var "TOOLS='[\"story\"]'"
# Install with both tools
mcp install -e . src/cli.py -n "Sequential Tools" --env-var "TOOLS='[\"thinking\",\"story\"]'"
For development:
# For development with the MCP Inspector
mcp dev src/__main__.py:main
You can also configure Claude desktop to use the tool with uvx by adding this to your Claude mcpServers.json:
"mcpServers": {
"Sequential Story": {
"command": "uvx",
"args": [
"sequential-story"
]
}
}
The environment variable TOOLS controls which tools are enabled. By default, only the Sequential Story tool is enabled, but the Sequential Thinking tool can be added as needed.
This is useful when you want to focus on a specific problem-solving approach or when integrating with other MCP tools. You can also update the environment variables directly in the Claude desktop app after installation.
Example story element
{
"element": "Our protagonist, a data scientist named Alex, encounters a mysterious pattern in the customer behavior data.",
"elementNumber": 1,
"totalElements": 5,
"nextElementNeeded": true,
"character": "Alex (data scientist)",
"setting": "Data analysis lab",
"tone": "Mysterious",
"plotPoint": "Discovery of pattern"
}
Example thought element
{
"thought": "The problem requires analyzing multiple data sources to identify correlations between customer behavior and sales patterns.",
"thoughtNumber": 1,
"totalThoughts": 5,
"nextThoughtNeeded": true
}
Development
# Install pre-commit hooks
uv run pre-commit install
# Run all pre-commit checks
poe pre
Credits
This project builds on the concepts of sequential thinking and structured problem-solving, adapting these approaches to both analytical and narrative frameworks for enhanced memory and problem-solving.
The Sequential Thinking implementation is a pure Python port inspired by the JavaScript implementation from the Model Context Protocol repositories: https://github.com/modelcontextprotocol/servers/tree/main/src/sequentialthinking
相關伺服器
Kone.vc
贊助Monetize your AI agent with contextual product recommendations
ChartPane
Renders interactive Chart.js charts and dashboards inline in AI conversations.
flomo
flomo 官方 MCP 服务
Basecamp
Interact with Basecamp 3 to manage projects, to-dos, and messages.
Home Assistant
Interact with Home Assistant to control smart home devices, query states, manage automations, and troubleshoot your smart home setup.
PaKi Curator
MCP server for César Yagüe's Visual Medicine art catalog — 300 contemplative moving art works, 13 collections. Search, browse, get recommendations for spaces.
Video Editor
Add, analyze, search, and edit videos using the Video Jungle API. Also supports local video search on macOS.
Mcptix
A simple and powerful ticket tracking system with AI assistant integration.
Nextcloud Calendar
CalDAV Nectcloud calendar integration. Manage calendars, events, attendees, etc.
Memory Graph
A graph-based Model Context Protocol (MCP) server that gives AI coding agents persistent memory. Originally built for Claude Code, MemoryGraph works with any MCP-enabled coding agent. Store development patterns, track relationships, and retrieve contextual knowledge across sessions and projects.
DalexorMI
Dalexor MI is an advanced project memory system designed to provide AI coding assistants with **Contextual Persistence**. Unlike standard RAG (Retrieval-Augmented Generation) systems that perform surface-level keyword searches, Dalexor MI maps the **logical evolution** of a codebase, tracking how symbols, dependencies, and architectural decisions shift over time.