"A guide for reducing token count in AI requests" matching MCP servers:

Manage a fleet of OPNsense firewalls from an AI agent, inside guardrails it can't drive around. MCP server for central management of OPNsense firewall fleets. 129 tools across devices, config sync, tasks, schedules, templates, backups and remote consoles - destructive actions confirmation-gated, MCP-issued tokens lifetime-bounded, backup and storage secrets excluded from the toolset entirely.

Connect to your TTRPG campaign's repository and database. Instead of retrieving prose, its 48 tools (20 read, 28 write) return typed state: 14 entity schemas (NPCs, factions, locations, sessions, lore), relationship and knowledge-graph queries, wiki blocks, and a narrative-state bundle of open threads and canon facts.

Enables governed multi-agent software factory operations through eight typed, audited tools for Sprint planning, submission, decisions, inspection, cancellation, and resumption.

Open source MCP server specializing in easy, fast, and secure tools for Databases.

MCP server for browser debugging, inspection, and verification that streams console logs, network errors, and user actions into AI coding assistants.

Provides persistent, searchable memory across AI coding agent and chat history (Claude Code, Codex, Gemini CLI, ChatGPT, and more) via retrieval-augmented generation, enabling semantic and hybrid search to retain context across sessions.

Enables LLMs to interact with embedded devices by reading and writing Segger RTT data through a J-Link debugger.

MCP server that integrates with VictoriaMetrics vmanomaly API to enable AI-assisted anomaly detection, model management, and configuration generation.

Enables AI agents to communicate with business agents across company boundaries using Google's A2A protocol, with tools for discovery, messaging, and connection management.

Stop runaway agents. One gateway in front of all your agent traffic — MCP tools and LLM models — one budget, one kill switch. Sits between AI clients (Cursor, Claude Desktop, Windsurf) and remote MCP servers / OpenAI-compatible model APIs; hard token budgets; a single static Go binary.

A Bitbucket CLI and MCP server written in Go for managing workspaces, repositories, pull requests, pipelines, issues, and source code. Supports stdio and HTTP transport.

An MCP orchestration layer that aggregates multiple MCP servers while exposing only 8 meta-tools, dramatically reducing context window usage, and provides SLOP scripting, event monitoring, and tool customization.

Enables coding agents to develop on one machine and verify results on another, using branch-bound runbooks, isolated checkpoints, and structured receipts to guide repair iterations.

Content-addressed code graph that produces ranked context for AI agents in one call. 22 MCP tools across indexing, blast radius, test scope, semantic diff, runtime traffic, and feedback-aware context packing. Incremental updates via Merkle DAG (no re-indexing). GCF wire format saves 84% tokens vs JSON

An MCP bridge that lets Codex and Claude Code interact with OpenLinker agents, and allows the host to serve as a callable agent in the OpenLinker network.

Enables AI video dubbing from any MCP-capable agent: upload a video or provide a URL, submit a dubbing job, poll progress, and download the finished MP4.

Enables AI coding assistants to search and retrieve information from a locally ingested knowledge base using hybrid search, grounded in user-curated documentation.

Enables an assistant to work inside gitlab.com projects as the signed-in user: issues, merge requests, code reviews, repositories, CI pipelines and job logs, plus optional gated toolsets for wiki, snippets, releases, planning, deployments and activity. It authenticates through a user-supplied OAuth application with the token kept in the OS keyring, and registers only the tools that are switched on.

Turns any web page into clean, token-budgeted Markdown for AI agents, with no browser installation required.

Enables AI agents to send HTML documents to a local viewer, where they are stored and displayed in a live web UI for browsing and searching.