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

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

Enables any MCP-compatible LLM to perform AI-powered web research using Google's AI Mode, returning synthesized and cited answers instead of raw search results.

A read-only MCP server for querying AI provider administration APIs, providing normalized usage, cost, and dashboard data for OpenAI and Anthropic.

Enables an MCP client to read Telegram through your own account — searching and reading chats, folders, forum topics, threads, albums, reactions, and polls, plus discovering public channels — without sending messages or marking anything read. It also supports durable change checkpoints, named watch subscriptions, and source-linked JSONL/Markdown history exports.

Unified MCP server for managing local model runtimes (Ollama, LM Studio, etc.), enabling provider-agnostic discovery, lifecycle management, hardware-fit checks, and delegated inference.

Unified MCP orchestration layer that consolidates multiple MCPs into a single interface with semantic tool discovery, code-mode execution, scheduling, and intelligent caching to reduce token usage by 97% and eliminate choice paralysis.

An MCP server that enables running commands against a ServiceNow instance via its REST APIs, including Table, Aggregate, Attachment, Import Set, Batch, CMDB, Service Catalog, Change Management, and Knowledge APIs.

AI agents that automate bookkeeping, bank reconciliation, and month-end financial close for SMBs and CA firms.

Enables Claude and any other MCP client to place and control voice calls, run conferences, stream call audio to AI agents, build IVRs, read call records and recordings, manage phone numbers, SIP trunks, applications, sub-accounts and billing, and send SMS/MMS/RCS on a Vobiz account. Calling, messaging and account changes stay off until explicitly enabled, with every write confirmed, rate-limited and idempotent.

Enables AI agents to access and utilize GovBR Design System documentation, including component details, accessibility guidance, and search functionality via Model Context Protocol.

A bridge between AI assistants and the Paradex perpetual futures trading platform for managing accounts, vaults, and orders. It enables users to retrieve real-time market data, monitor positions, and execute trading strategies through the Model Context Protocol.

MCP server enabling AI agents to perform cross-chain token swaps through NEAR's intent-based architecture using the Defuse Protocol, with token discovery, quote retrieval, swap execution, and status tracking.

Cite-able, content-addressed, signed memory of every place on Earth

This is an MCP (Model Context Protocol) server that provides tools for interacting with the NOAA Tides and Currents API.

A production-grade TypeScript starter for building Model Context Protocol servers, supporting stdio and Streamable HTTP transports with modular tools, resources, and prompts.

Enables casting I Ching hexagrams with the traditional three-coin method and retrieving James Legge's public-domain translation of judgments, images, and line texts, returning auditable cast records with changing and transformed hexagrams while leaving interpretation to the host model. It also exposes hexagram and trigram resources plus reflection prompts for use in study, creative thinking, and decision exploration.

A Model Context Protocol server that exposes a MeshCore node and the mesh reachable through it as a clean, high-signal interface for AI agents or tools.

Enables encoding JSON into compact TOON format and decoding TOON back to JSON, reducing token usage for LLM prompts.

Enables AI agents to discover and analyze prediction markets, execute trades, and manage positions on Polymarket via the Model Context Protocol.

AI job search and job application tracker. Search live jobs by title, location, salary, date posted, and remote or on-site, and see each one checked on real data: pay against market rates, ghost-job signals, visa sponsorship history, and how well it matches your resume. Check how hiring software reads your resume, track applications, set follow-up reminders, and get email alerts.

A comprehensive MCP server for Dokploy that provides 14 action-based tools covering the full DevOps lifecycle with minimal token usage. It enables AI assistants to manage projects, applications, databases, domains, servers, and more through a unified interface.

A Model Context Protocol (MCP) server for validating Mermaid diagram syntax and providing comprehensive grammar checking capabilities

A Model Context Protocol server that provides real-time access to Effect ecosystem documentation, enabling AI assistants to retrieve accurate and up-to-date docs for Effect packages.

A Model Context Protocol server for Discourse forums, extended with review queue tools to list and act on pending or flagged items, enabling AI agents to moderate content.

Provides access to Deutsche Bahn train timetables, station information, and schedule changes through Model Context Protocol tools and resources.

Provides institutional research data retrieval, extraction, validation, and citation generation for AI assistants via the Model Context Protocol.

Connect QGIS to Claude AI through the Model Context Protocol (MCP), enabling Claude to directly control QGIS — manage layers, edit features, run processing algorithms, render maps, and more.

A Model Context Protocol server for interacting with MongoDB Databases and MongoDB Atlas. It enables AI assistants to query, manage, and operate on MongoDB data and Atlas resources through natural language.

A Model Context Protocol server for the Quire project management platform, enabling AI assistants to securely interact with Quire projects, tasks, and data.

A Model Context Protocol server that allows AI assistants and applications to access IQ.wiki data, enabling retrieval of specific wikis, user-created wikis, user-edited wikis, and detailed wiki activities.