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

Enables coding agents to retrieve token-budgeted, source-hashed code context from explicitly registered local repositories via read-only MCP tools, reducing broad repository crawling while providing structure, symbols, and impact slices.

Enables local-first tracking of AI token usage and costs from Claude Code and OpenCode, answering queries about tokens, models, sessions, and cost through MCP tools and a CLI, with no network calls.

Read-only MCP server for querying AI usage metrics (exact tokens, cost, latency, errors, productivity) from a local SQLite database, enabling charts and analysis in Claude Code and Cursor.

Enables AI assistants to see which model IDs each provider's API has started listing since the last check, and to list the models a given provider currently serves with optional substring filtering, all without spending tokens.

Claude Code token usage and cost visibility for MCP-capable agents.

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.

Provides Claude plan usage data (session and weekly percentages) as an MCP tool by reading through a logged-in browser, enabling Claude to check its own remaining usage.

Enables Claude Code sessions to check account rate-limit headroom, local token spend, and live session status, with read-only MCP tools for limits, summaries, token usage, and session listing.

An MCP server that cuts AI coding-agent token usage by 60–80% via framework-aware context optimization.

Enables retrieving real Claude subscription usage statistics, including the 5-hour session window, weekly limit, and per-model limits, from the same endpoint Claude Code uses.

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

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

Monitors your Cursor usage and provides a conserve flag to the agent, helping you manage request quota by batching questions, preferring defaults, and cutting unnecessary confirmations.

Reports your Claude subscription usage (5-hour and weekly limits) with a forecast and velocity recommendation, using Claude Code's existing OAuth session without requiring an API key.

MCP server that reduces token consumption in AI coding assistants by up to 90% via structural reads, PreToolUse hooks, and tp-\* subagents.

Real-time Claude.ai subscription awareness for AI coding assistants. Surfaces live utilization, forecasts limits, gates expensive operations, and measures real per-task cost.

MCP plugin that alerts you when AI token usage is wasteful. Fires warnings, errors, and alerts on large outputs, verbose logs, and repetitive history, auto-suppressing noise to keep your context lean.

Enables MCP clients to query Kiro credit usage, including plan, used and remaining credits, reset date, and percentage used, through a read-only tool with optional cache refresh.

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.

Local-first dashboard + MCP server that parses Claude Code and Codex JSONL files into a SQLite cost / token tracker. Per-MCP and per-tool breakdown, session drill-down, dedup by request_id; never talks to vendor APIs

A read-only MCP server that reports token usage by agents and models, and recommends the cheapest safe model and effort level for a given task, helping to reduce token waste.

A local MCP server that exposes Blacksmith.sh's usage and cost data, enabling queries for CI spend through agents, alerts, or dashboards.

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.

This is a MCP server that implements an unreasonable thinking system. It helps generate unconventional solutions: Generating unreasonable thoughts that challenge conventional wisdom. Creating branches of thinking in different directions

Provides owner-bound secure storage and retrieval of tool outputs via MCP tools, enabling trusted persistence for agents like Claude Code, Codex CLI, and OpenCode.

An MCP server that provides structural codebase indexing and surgical query tools to drastically reduce token usage through symbol-level searches and transitive impact analysis. It supports multiple languages and integrates with git to help AI agents understand code dependencies and the impact of changes in sub-millisecond time.

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.

Audits local Claude Code transcripts to show which connected MCP servers are actually used, idle, failing, or awaiting authorization, and recommends which to keep or disconnect.

Exposes compact-context MCP tools that outline large files, cap and summarize repo-wide searches, and run builds or tests while returning only grouped errors and key warnings. Guard hooks block whole-file reads, unbounded recursive greps, and raw build logs so coding sessions keep their context budget intact.

Enables AI agents to obtain a compressed code context where the active file is fully included and dependency files are reduced to type signatures, interfaces, and exports, cutting token usage while preserving code shape.