mcp-sequentialthinking-tools
Verified Safeby dscv103
Overview
Recommends tools for step-by-step reasoning, tracks agent thought processes, and learns tool-chain patterns.
Installation
npx -y mcp-sequentialthinking-toolsEnvironment Variables
- MAX_HISTORY_SIZE
- ENABLE_PERSISTENCE
- DB_PATH
- ENABLE_BACKTRACKING
- MIN_CONFIDENCE
- MAX_BACKTRACK_DEPTH
- BASE_CONFIDENCE
- TOOL_CONFIDENCE_WEIGHT
- REVISION_PENALTY
- BRANCH_BONUS
- PROGRESS_BONUS
- PROGRESS_THRESHOLD
- DECLINING_CONFIDENCE_THRESHOLD
- ENABLE_DAG
- ENABLE_TOOL_CHAINS
- TOOL_CHAIN_PREFIX_MATCH_WEIGHT
- TOOL_CHAIN_KEYWORD_MATCH_WEIGHT
- TOOL_CHAIN_HIGH_SUCCESS_BONUS
- TOOL_CHAIN_RECENT_USE_BONUS
- TOOL_CHAIN_RECENT_USE_DAYS_THRESHOLD
- TOOL_CHAIN_HIGH_SUCCESS_RATE_THRESHOLD
- TOOL_CHAIN_CONFIDENCE_WEIGHT
- LOG_LEVEL
- STRUCTURED_LOGS
- LOG_FORMATS
Security Notes
The server primarily operates locally, using SQLite for persistence and standard I/O for MCP communication, which minimizes external network attack surfaces. Input validation (Valibot) is used for incoming MCP requests, and SQLite queries are prepared, preventing SQL injection. No 'eval' or direct execution of user-supplied commands found. The main potential risk would be if the configured DB_PATH points to a sensitive system location, but this is a configuration rather than a code vulnerability.
Similar Servers
mcp-sequentialthinking-tools
Guides LLM-driven sequential problem-solving by breaking down complex problems into manageable steps and providing confidence-scored recommendations for MCP tool usage at each stage.
conductor-tasks
Conductor Tasks acts as an intelligent AI-powered assistant for developers, streamlining the entire development lifecycle from task generation and planning (parsing PRDs, expanding tasks, generating implementation steps) to execution and code modification (generating diffs). It provides visual task management, integrates with various IDEs, and leverages multiple LLM providers for optimal results and cost efficiency.
knowns
A CLI-first knowledge layer and task/documentation management tool that provides AI agents with persistent project context.
Matryoshka
Processes large documents beyond LLM context windows using a Recursive Language Model (RLM) that executes symbolic commands for iterative document analysis.