"Optimizing AI Model Thinking, Token Usage, and Context Size" matching MCP servers:

Simple sequential thinking MCP in python

Enables AI coding agents to conserve tokens by enforcing rules like delegating heavy work to subagents, checkpointing before token limits, and grepping before reading files.

A Model Context Protocol (MCP) server implementation for the Google Gemini language model. This server allows Claude Desktop users to access the powerful reasoning capabilities of Gemini-2.0-flash-thinking-exp-01-21 model.

Enables AI assistants to work through complex problems step-by-step with dynamic thought processes, allowing for revision of previous steps, exploration of alternative approaches, and flexible planning as understanding deepens.

Sovereign, deterministic, local-first context and DAG lifecycle engine with native stdio MCP server for autonomous AI coding agents.

Enables bounded, local coding tasks to be delegated to OpenAI-compatible models with explicit working directory and read/write paths, pre-application unified-diff validation, and optional verification commands. It routes tasks by complexity and risk, while blocking sensitive changes such as auth, payment, secrets, migrations, database, deployment, or production environments.

Enables coding agents to check human-stated assumptions against authoritative sources like AWS AppConfig, Sentry, and the repository, detecting when beliefs have drifted from reality. It provides tools to inspect belief history, list verifiable properties, review open drifts, and record verified understanding.

Share context, detect file conflicts, and send messages across parallel Claude Code sessions

Reduces token consumption for AI coding agents by 50-70% through intelligent code context filtering, Git delta tracking, and local SQLite/Tree-sitter indexing.

A token-efficient, codebase-aware AI agent runtime that provides MCP tools for starting runs, getting run states, explaining code, and finding files.

A local-first bridge for moving useful context between coding agents, indexing sessions and creating handoff packets for seamless agent switching.

MCP server to provide Jira Tickets information to AI coding agents like Cursor

Enables IDE integration with a multi-agent AI pipeline for solving, reviewing, and optimizing code through adversarial peer review and security filtering.

Enables structured, step-by-step problem-solving through dynamic thinking processes that can be revised, branched, and adjusted as understanding deepens. Supports breaking down complex problems into manageable steps with the ability to revise previous thoughts and explore alternative reasoning paths.

Enables primary AI orchestrators to delegate token-heavy coding tasks to economical models via OpenRouter, running sandboxed autonomous ReAct loops with filesystem operations and git audit tools while reducing token costs.

Forecast time series in CSV files: deterministic skforecast workflows and the script that ran.

A Model Context Protocol server that enables LLMs to read, search, and analyze code files with advanced caching and real-time file watching capabilities.

Provides AI-powered development tools including code generation, refactoring, debugging, performance optimization, and test generation, along with smart prompts for code analysis and documentation, and a built-in knowledge base of coding best practices.

Delegates large file reads to a cheap worker model so coding agents avoid consuming context, with optional hook enforcement and per-call token savings.

Enables managing Linux hosts and local coding agents from an MCP client through shell commands, files, background jobs, system information, instruction and skill discovery, and optional Claude Code, Codex, or Cursor CLI conversations. It provides privileged remote access with token authentication and can run longer work in the background.

Enables AI-powered coding assistance including file editing, code generation, explanation, review, and shell command execution, using multiple free AI providers with automatic fallback.

Enables MCP clients like Claude Code to delegate coding tasks to a local model through a configurable coding-agent CLI backed by any OpenAI-compatible endpoint, with tools for health checks, task execution, and context-aware file modifications.

Enables AI agents to delegate complex coding tasks, refactorings, and automated code reviews to OpenAI Codex and Google Antigravity CLIs, running them autonomously in YOLO mode with process supervision.

Enables running multiple AI CLI tools (Claude, Codex, Gemini, Forge, OpenCode) as background processes with automatic permission handling, allowing LLMs to execute async multitasking and combine different AI models.

Enables developers to delegate asynchronous coding tasks to a cloud-based autonomous agent, creating tasks, reviewing and approving execution plans, sending feedback, monitoring sessions, and retrieving diffs and Pull Requests directly from an MCP-compatible IDE. It also supports configurable mock mode for local testing without consuming API credits.

Enables coding agents to incrementally index project text and code, persist decisions and constraints with clear sources, and assemble focused project context across sessions via MCP.

Enables acceptance gates for AI coding-agent runs by recording evidence, running deterministic validation, applying a quality gate, and rendering auditable outcomes.

MCP server wrapping OpenAI Codex SDK to run Codex agents for code generation, debugging, and more, authenticating via ChatGPT OAuth.

Enables AI agents to build games with the Cocos4 engine by providing high-level scaffolding tools and transparently proxying native MCP tools.

An MCP server that wraps the Claude Agent SDK, enabling Claude-powered queries, coding tasks, web search, and customizable agent execution using OAuth without an API key.