sequential-thinking
Sequential Thinking
Structured problem-solving through iterative reasoning with revision and branching.
When to Use
Use mcp__reasoning__sequentialthinking when:
- Problem requires multiple interconnected reasoning steps
- Initial scope or approach is uncertain
- Need to filter through complexity to find core issues
- May need to backtrack or revise earlier conclusions
- Want to explore alternative solution paths
Do not use for simple queries, direct facts, or single-step tasks.
Core Capabilities
- Iterative reasoning: break complex problems into sequential thought steps
- Dynamic scope: adjust total thought count as understanding evolves
- Revision tracking: reconsider and modify previous conclusions
- Branch exploration: explore alternative reasoning paths from any point
Parameters
<required_parameters>
thought(string): current reasoning stepnextThoughtNeeded(boolean): whether more reasoning is neededthoughtNumber(integer): current step number (starts at 1)totalThoughts(integer): estimated total steps needed </required_parameters>
<optional_parameters>
isRevision(boolean): indicates this revises previous thinkingrevisesThought(integer): which thought number is being reconsideredbranchFromThought(integer): thought number to branch frombranchId(string): identifier for this reasoning branch </optional_parameters>
Workflow
Tips
- Start with rough estimate for
totalThoughts, refine as you progress - Use revision when assumptions prove incorrect
- Branch when multiple approaches seem viable
- Express uncertainty explicitly in thoughts
- Accuracy of scope estimate matters less than progress visibility
For revision patterns and branching strategies: references/advanced.md
More from ven0m0/claude-config
llm-boost
|
20uv
|
11substituting-modern-tools
Substitutes modern performant tools for legacy equivalents in generated code (npm→bun, find→fd, pip→uv, grep→rg, jq→jaq, eslint→biome, black→ruff, git→gix). Use when generating shell commands or scripts.
9linter autofix patterns
Cross-language linter autofix commands and common fix patterns for biome, ruff, clippy, shellcheck, and more.
9moai-tool-svg
>
5building-mcp-servers
Creates high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP servers to integrate APIs, designing tool schemas, or implementing Python (FastMCP) or TypeScript (MCP SDK) servers. Triggers include "MCP server", "tool schema", "model context protocol", or "FastMCP".
5