MCP Servers by reasoning.services

Every MCP server published by reasoning.services that Pod indexes.

7 servers, ordered by adoption — npm downloads where a package exists, then reported issue volume. None have been dialled by Pod yet, so every tool list here is publisher-reported and unverified.

Formal Logic

Formal Logic MCP is a Model Context Protocol server that provides deterministic reasoning capabilities without any LLM dependencies. It offers:

Propositional Logic: SAT solving, CNF conversion, consistency checking, and entailment.
First-Order Logic: Theorem proving using the Z3 SMT solver.
Temporal Logic: Trace-based LTL model checking.
100% Deterministic: Identical input always produces identical output — fully cacheable and auditable.
High Performance: Fast execution taking under 5 seconds for typical queries.

Ideal for API contract verification, state machine validation, detecting contradictions in business rules, and system requirements analysis.

9 tools reported — Publisher-reported; not verified by Pod.

Exposes Graph of Thought operations as MCP tools for compatible clients like Claude Desktop, Cursor, and Windsurf. Unlike linear sequential thinking, Graph of Thought enables non-linear reasoning by allowing you to:

Branch (1->N): Explore multiple approaches to a problem simultaneously.
Score (N->N): Evaluate the quality of each approach and prune bad ideas early.
Aggregate (N->1): Synthesize the best aspects of multiple thoughts into a single, cohesive solution.
Refine (1->1): Continuously improve a promising thought.

It is ideal for complex decision-making where you need to explore multiple paths and combine partial solutions using a "Diamond Pattern" of reasoning (seed → generate → score → aggregate).

9 tools reported — Publisher-reported; not verified by Pod.

Structured Reflection

Structured Reflection is an MCP connector that gives Claude a structured workflow for reflecting on problems out loud. Instead of jumping straight to an answer, Structured Reflection guides Claude to restate the problem, list assumptions, explore alternative approaches, and highlight risks or unknowns before converging on a recommendation. Teams use it to debug prompts and workflows, think through product and architecture decisions, and coach themselves through tradeoffs before committing to a plan. By making the reasoning process explicit and iterative, Structured Reflection helps catch hidden assumptions early and produces decision logs that are easier to review and share. Structured Reflection is maintained by Reasoning.Services and complements other MCP servers that provide decision matrices, workflows, and structured reasoning tools.

9 tools reported — Publisher-reported; not verified by Pod.

Context Switcher

Context Switcher is an MCP connector that helps Claude manage and navigate different “contexts” in a structured way, instead of treating every conversation as a blank slate. Teams can define reusable contexts—such as “RFP evaluation,” “customer support triage,” “product discovery,” or “risk review”—and use Context Switcher to move between them without losing the underlying reasoning. When invoked, the connector can load the right criteria, constraints, and reference materials for the chosen context, then guide Claude to apply the appropriate decision lens to the current problem. This makes it easier for product, operations, and proposal teams to keep their work organized, avoid mixing use cases, and ensure that each workflow runs with the right assumptions. Context Switcher is maintained by Reasoning.Services and designed to work alongside other MCP servers that provide structured reasoning, document access, or workflow automation.

8 tools reported — Publisher-reported; not verified by Pod.

Devil's Advocate

The Devil's Advocate MCP transforms defensive thinking into proactive vulnerability discovery using proven red team and devil's advocate methodologies. This tool helps you:

Challenge assumptions before they become blind spots.
Run premortems to prevent failures before they happen.
Build attack trees to map systematic vulnerabilities.
Think adversarially from multiple perspectives simultaneously.

6 Built-in Adversarial Perspectives:

Attacker: Finds ways to exploit weaknesses.
Competitor: Identifies competitive threats.
Skeptic: Questions assumptions and value propositions.
Pessimist: Expects worst-case scenarios.
Contrarian: Challenges conventional wisdom.
Auditor: Finds process gaps and compliance issues.

Additionally, the connector includes transformer-based argument analysis to detect logical fallacies, contradictions, overgeneralizations, and hidden assumptions.

8 tools reported — Publisher-reported; not verified by Pod.

Decision Matrix

Decision Matrix is an MCP connector that lets Claude evaluate choices using explicit criteria, weights, and scoring rules instead of ad‑hoc opinions. Teams can define matrices for vendor selection, feature prioritization, RFP evaluation, risk assessment, or any decision that needs a structured, defensible process. Given a set of options and criteria, Decision Matrix guides Claude to score each option, explain the rationale behind every score, and highlight tradeoffs and sensitivity to changing weights. This makes it easier for product, operations, procurement, and proposal teams to move from “gut feel” to documented, auditable decisions that stand up to stakeholder scrutiny. Decision Matrix is maintained by Reasoning.Services and is designed to work alongside other MCP servers that provide document access, workflows, or additional reasoning tools.

7 tools reported — Publisher-reported; not verified by Pod.

Iterative Refinement

The Iterative Refinement MCP server allows you to systematically improve text, ideas, or algorithms through continuous self-evaluation. It avoids standard LLM timeouts by breaking the refinement process into discrete, trackable steps.

Key Features:

Iterative Refinement: Follows a structured Draft → Critique → Revise → Converge workflow.
Mathematical Convergence: Uses cosine similarity to measure when refinement is complete, ensuring optimal results without endless loops.
Domain-Specific Optimization: Auto-detects and optimizes for technical, marketing, strategy, legal, and financial domains.
Progress Visibility: Each step returns immediately, allowing for real-time UI updates and transparent progress tracking.
Parallel Processing: Supports multiple concurrent refinement sessions and parallel critiques per iteration.
AI-Friendly Error Handling: Provides actionable diagnostics and recovery hints directly to your AI assistant.

5 tools reported — Publisher-reported; not verified by Pod.

For agents

This page has a Markdown and a JSON twin. Pod is also queryable over MCP at https://api.askpod.ai/mcp/read.