"OpenRouter thinking or reasoning capabilities" matching MCP servers:

An MCP server that brings difficulty-adaptive, multi-path reasoning to Claude Code. It implements the Actor-Critic-Planner-Reflexion (ACPR) pipeline for deep research synthesis.

Provides systems thinking models as composable analysis lenses for architecture, infrastructure, DevOps, incident analysis, and technical decision-making.

Provides an MCP server that decomposes complex problems into ordered, isolated reasoning contexts, yielding compressed summaries before discarding intermediate steps. Enables sequential or parallel step execution with optional verification for more reliable LLM reasoning.

A Python MCP server that lets MCP hosts call OpenRouter models for chat, image generation, embeddings, and model search via FastMCP with .env support and retry handling.

Lets a Codex parent delegate bounded work to explicitly approved OpenRouter model/provider routes with strict permission controls, selected-file review, and approval-gated artifact creation.

Strategic BDI cognitive reasoning engine for AI agents. Goal decomposition DAGs, multi-factor utility scoring, risk evaluation, and adaptive replanning over MCP.

A 66-tool reasoning pipeline that intercepts prompts to classify intent, check past mistakes, and generate execution plans, enabling any LLM to think harder and avoid repeating errors.

Provides AI agents with deterministic symbolic math capabilities through 21 tools for algebra, calculus, transforms, and DSP, preventing hallucinations by delegating computations to a SymPy engine.

Enables coding agents to obtain probabilistic decisions from Jev AI via OpenRouter for classification, scoring, and validation, with tools like jev_check, jev_classify, jev_score, and jev_evaluate.

A sophisticated MCP server that provides a multi-dimensional, adaptive reasoning framework for AI assistants, replacing linear reasoning with a graph-based architecture for more nuanced cognitive processes.

A Model Context Protocol server that enhances Claude in Cursor AI with advanced reasoning capabilities including Monte Carlo Tree Search, Beam Search, R1 Transformer, and Hybrid Reasoning methods.

Turns Claude Code into a recursive analysis engine that builds explorable decision trees from IF/THEN chains, enabling thorough problem exploration and structured synthesis of action plans.

An MCP server that enhances sequential thinking with Ultra Think methodology, enabling structured, step-by-step reasoning with quality metrics, bias detection, and resource management.

Enables MCP clients to offload sub-problems to fresh, isolated contexts via sampling, offering plan, think_aside, and run_plan tools for sequential reasoning without cluttering the main conversation with verbose intermediate steps.

Enables Claude Code to generate and edit raster images through OpenRouter, including image-to-image editing with up to 16 ordered references, text-to-image generation, and balance/credit checks.

Provides reasoning budget estimates for AI tasks, making effort and time trade-offs visible through a compact control interface.

A self-hosted MCP server that provides tools for structured reasoning, confidence calibration, and detecting recurring gaps in AI outputs, aiming to reduce workload by improving verification and attention allocation.

Structures debugging processes into a persistent knowledge graph, enabling problem decomposition, hypothesis testing, and reusable solution discovery.

Lets Claude Code delegate tasks to OpenRouter-backed Claude Code sessions in isolated child processes, keeping Anthropic and OpenRouter credentials separate. It adds a model catalog, per-job cost tracking, and API-key management for running tasks on 400+ OpenRouter models.

A structured, persistent reasoning workspace for AI. 20 tools for thought chains, branching, revision, search, tagging, and SQLite session persistence that survives context window resets and server restarts.