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

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.

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.

AI coding usage analytics — track spend, model usage, and costs across Cursor and Claude Code sessions.

MCP server that wraps Cursor Enterprise API to enable AI agents to answer questions about team spending, usage, and model adoption.

Persistent sequential thinking for MCP clients, stored durably on Cloudflare Workers with support for branching, revision, and history retrieval.

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.

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 and scripts to rug-check any token on Base, Ethereum, Arbitrum, Optimism, Polygon, or Solana, returning a 0-100 risk score with plain-language reasons and a fingerprint for detecting changes on later checks. It also reports market data and supports automatic $0.01 USDC payments via x402.

Enables MCP hosts and AI agents to request pay-per-call token risk assessments for contract addresses across Base, Ethereum, and Solana, returning a verdict, 0–100 risk score, six market-structure signals, and an analyst summary, with payment handled via x402 USDC on Base.

Read-only XRPL token and wallet checks with issuer-aware explanations, impersonation checks and spoken summaries. Built for Zach Riehn's XRP Ledger Trading Lab by AI coding agents under Zach's direction. Never signs or sends transactions; findings describe observed ledger evidence, not a guarantee of safety or investment advice. Try it: https://cocoeatsai.com/trading-lab/token-guard/

This server assists with A/B testing by calculating required sample sizes and necessary test durations. It provides a suite of significance tests, including z-test, chi-square, and Fisher exact methods, while evaluating the risks of premature peeking.

The Token Metrics Model Context Protocol (MCP) server provides comprehensive cryptocurrency data, analytics, and insights through function calling. This server enables AI assistants and agents to access Token Metrics' powerful API for real-time crypto market data, trading signals, price predictions, and advanced analytics.

MCP server for structured reasoning with cognitive trap detection, verification, and context compression

Enables AI agents to fetch a one-call read-only ERC-20 snapshot — USD price, FDV, DEX liquidity, top pools, holder-concentration hints and bytecode risk flags — across Base, Ethereum, Arbitrum, Optimism, Polygon, Avalanche and BNB Chain, with a free basics tool plus an optional paid full snapshot settled in USDC via x402.

Provides read-only $dasha Solana token market data to AI agents, including price, liquidity, market stats, and Jupiter swap quotes, with no transaction signing or wallet access.

Manages token budgets for AI agents, enabling tracking and enforcement of usage limits with built-in EU AI Act compliance.

Classifies company sites as B2B or B2C and as SaaS, online store, agency, manufacturer, wholesaler, distributor, or marketplace, while matching your own buyer phrases and returning the quoted text and page as evidence. Runs deterministically on Apify, giving one row per domain with grace-free status rows for unreachable, blocked, or empty sites.

Proxy for OpenAI-compatible backends that compacts conversation history before the context window fills, with read-only MCP tools to search and read back the archived originals.

Provides an external context buffer so a local model can maintain session memory across long tasks and search and page through large documents without loading them whole into its limited context window.

MCP server providing lossless file reads with deduplication, per-repo token metering, and HMAC-signed context receipts. Enables auditable, vendor-neutral measurement of what an AI agent saw.

Enables AI coding agents to reduce token usage by condensing source code into AST skeletons, extracting specific symbols, compressing logs, and estimating token budgets.

Aggregator MCP proxy that collapses N downstream MCP servers into 4 meta-tools with progressive tool discovery, and compresses large tool outputs (HTML→Markdown, JSON summarization) with full-output retrieval via read_more and a per-session token-savings report.

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions

A high-performance MCP server providing up-to-date documentation for Go, npm, Python, Rust, Docker, Kubernetes, Terraform, and more — fetched from official sources, not training data.

Translates design tokens across platforms — extracts from Tailwind/CSS/Figma and generates native themes for Material 3, SwiftUI, and CSS variables with WCAG contrast validation.

Local-first memory for AI agents about the people in your life. MCP server + CLI on SQLite. Never phones home.

Ask, check and change live Revit models from Claude, Cursor or any MCP client. One undo per change, read-only switch. Revit 2022-2027.

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.

Temporal knowledge graph for codebases that captures decision traces, links test failures to code changes, learns co-edit patterns, predicts regression risk, and enforces learned constraints at the edit boundary via a PreToolUse hook.