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

An event-driven MCP server that enables agents to share context streams, publish and subscribe to events, manage tasks, and follow protocols, keeping a fleet of agents mutually context-aware in real time.

Lets Claude look up your own Claude subscription usage limits — the same 5-hour and weekly percentages shown by /usage — mid-conversation, so it can pace long tasks and warn you before you hit a wall. It reads the local OAuth login, serves a throttled read-only snapshot (cached with graceful fallback), and exposes it as a single get_usage tool.

An MCP server that exposes Claude Code's real-time rate limit usage so that an orchestrator can check remaining capacity before launching subtasks.

MCP server that pings 130+ free coding LLM models across 17 providers in real-time, ranks them by latency, and helps AI agents pick the fastest available model.

Enables AI coding agents to offload large file reads and boilerplate code generation to cheaper or local worker models through MCP, reducing token consumption and keeping context clean.

Enables AI agents to monitor live token consumption and rate-limit windows across providers and assess whether expensive actions are justified before exhausting quotas, with optional budget guardrails.

An MCP server that enables managing multiple lines of thought with features like branch navigation, cross-references between related thoughts, and insight generation from key points.

Discovers LLM models in real time from cloud providers and local Ollama instances, returning compatibility profiles and live pricing so AI agents can route tasks to the cheapest viable model without breaking tool calls or context clipping.

Enables AI agents to achieve production-ready solutions through iterative refinement and recursive thinking processes. It features token optimization via context compression and session-based tracking to improve problem-solving depth while minimizing cost.

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.

Enables Claude Code users to inventory the MCP servers, skills, commands, agents and plugins installed on their machine, estimate how many tokens each one adds to every request, and switch them off per project or globally, including across other AI coding tools. It also monitors live sessions to report real token usage and the savings achieved from disabled items.

Gives the model visibility into the same 5-hour session, weekly, and per-model usage percentages shown in Claude Code, along with reset times. It also lets a project cap how much of the weekly limit may be spent via start/check/end budget tools that report OK, LOW, or OVER_BUDGET.

Provides a standardized protocol for tool invocation, enabling an AI system to search the web, retrieve information, and provide relevant answers through integration with LangChain, RAG, and Ollama.

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 agents to cut token usage by locally pruning, encoding, and summarizing MCP tool responses, with lossless recovery of original data when needed.

An MCP server that seats multiple LLMs as a council, letting your assistant query them in parallel or in sequence, relay answers for cross-critique, and merge conclusions within one conversation.

Enables a Codex orchestrator to obtain a deterministic, local recommendation for a model and reasoning effort for a delegated coding task, without inference calls or API keys.

Enables selecting the best AI model and reasoning effort for any task by analyzing task requirements and live pricing, balancing intelligence, speed, and cost. Provides model recommendations, comparisons, and routing status through MCP tools.

Cost-aware multi-LLM routing MCP server that automatically routes tasks to free models first with fallback to paid, using task difficulty classification.

MCP proxy that reduces context usage through semantic tool routing, enabling on-demand discovery and routing of relevant tools.

Provides MCP tools to profile and optimize LLM conversation context, identifying token waste and applying deterministic fixes to reduce context window usage.

Enables AI coding agents to retrieve the exact original tool-output slices omitted during lossless context compression, via on-demand expansion of hashed references stored in a shared cross-process SQLite vault. Tracks expansion overhead so agents and users can measure true net token savings across debugging sessions.

Enables agents to plan premium-model tasks with estimated credit budgets, require explicit approval before execution, and inspect itemized usage receipts afterward.

Automatically captures project state on git commits, detects context drift, and delivers structured token-budgeted briefings to AI agents, ensuring project continuity without manual effort.

Enables local-first management of OpenCode model routing, letting users discover, enable, and assign orchestrator/specialist roles to models while safely connecting the chosen policy to OpenCode via a local MCP bridge.

Routes subagent tasks across Claude and OpenAI lanes by task kind and quota state, deciding whether to spawn a single model, run a duel of both vendors, or run both and ship the merge. It records duels with attested proof-of-run session ids, grades sides blind with one judge per vendor, and tracks per-kind standings and lane pacing.

Enables autonomous context window management, prompt caching, token optimization, and real-time observability for AI coding agents across multiple IDEs, reducing token costs and improving performance.

One MCP server that routes to 12+ AI providers for text, image, and video generation, with smart task delegation, web search, and model comparison—all from the terminal.

Enables AI agents to route chat completion requests to task-appropriate models via LiteLLM/OpenRouter, track usage and budgets, and run side-by-side eval comparisons of models based on cost, latency, and response quality.

Provides context-aware skill selection for AI agents, reducing token usage by 85-98% and improving accuracy through semantic retrieval, session memory, and feedback learning.