- Conduid
- Marketplace
- #context-window
MCP servers tagged context-window
173 live MCP servers tagged "context-window", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with context-window.
MCPProxy
Supercharge AI Agents, Safely
varun29ankuS/shodh-memory
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No c…
Community
reShapr Community repo
Baml Agents
Building Agents with LLM structured generation (BAML), MCP Tools, and 12-Factor Agents principles
Claude Mem
A long-term memory storage system for LLMs using the Model Context Protocol (MCP) standard. This system helps LLMs remember the context of work done over the entire history of a p…
Smart Webfetch MCP
Context-aware web fetching MCP server that prevents LLM context window flooding
Context Attachment Manager
Codex and Claude Code plugin (works in Claude Desktop): choose which past images go to the model with your next message. Unchecked images become placeholders, the conversation goe…
Token Saver
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) witho…
Tokenfold
Local, provider-neutral compression for LLM prompts, tool schemas, JSON, logs, and diffs. Lossless, receipt-audited, no ML tax.
Codex Attachment Manager
Codex plugin: choose which past images go to the model with your next message. Unchecked images become placeholders, the task goes on, and requests stay small.
Entroly
The Context Engineering Engine. Your AI sees 5% of your codebase — Entroly shows it everything. 78% fewer tokens. Works with Cursor, Claude Code, Copilot, OpenClaw.
Token Goat
Token burn reducer and focus keeper for Claude Code, Codex, Gemini CLI, Cline, Windsurf, Aider, Cursor, Copilot, and more: surgical read hints, PDF/Office/CSV/markdown file interc…
Chatcli
ChatCLI is a command-line application that utilizes LLMs—such as those from Anthropic, OpenAI, and others—to facilitate interactive conversations within the terminal. At its core,…
Hypa
Local context runtime for coding agents: compress shell output, query code, and proxy MCP tools
OKFy
Knowledge engineering for AI agents: distill corpora too big for any context window into small, verified, git-native knowledge bundles
Okfy
Knowledge engineering for AI agents: distill corpora too big for any context window into small, verified, git-native knowledge bundles
Usagetrim
Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
IHMT MEMORY
Long-term memory for AI coding agents (Claude Code, Codex, opencode) as a tree of plain files
Cpp Project Indexer
MCP C++ project indexer for fast symbol, module, and source-range navigation in large C++20 codebases.
Cpp Project Indexer
MCP C++ project indexer for fast symbol, module, and source-range navigation in large C++20 codebases.
Ctxray
X-ray your AI coding agent's context window — see what CLAUDE.md, rules, skills and MCP tool schemas cost you in tokens, across Claude Code / Cursor / Codex / Copilot / Gemini / W…
Claude Teams Brain
Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.
Reshapr
The open source, no-code MCP Server for AI-Native API Access
Squeez
End-to-end token optimizer for Claude Code, Copilot CLI & OpenCode. Up to 95% bash compression, cross-call redundancy, caveman persona, markdown compressor. Zero new dependencies.
Gortex
High-performance code intelligence engine that indexes repositories into an in-memory knowledge graph and exposes it via CLI, MCP Server, and web UI. Built for AI coding agents -…
Unclog
Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.
Skillreaper
Evidence-based pruning for your AI-agent stack — scan, report, and safely prune unused skills/MCP servers/agents using real transcript evidence
PlayGuard
AI-powered MCP proxy for Playwright and Figma. Optimize Claude Code and AI agents with session recovery, context reduction and intelligent tool routing.
Contextrot
Find out where your coding agent starts degrading. Personal context-rot analytics from your own sessions - 100% local, zero-config: uvx contextrot
Pluck
MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup
Zap Coding Agent
ZAP is a terminal-first, local AI coding agent built in Rust. It uses AST-powered codebase indexing and lazy-loaded skills to completely eliminate prompt bloat and minimize contex…
Contextcore
ContextCore: An MCP server for Claude (or any AI tool) that enables massive token saving through hybrid search (BM25 + Embeddings)
Unity MCP Efficient
Token-efficient facade and Codex skill for MCP for Unity: 96% smaller measured tool-schema surface, compact results, batching, and recovery.
Atlasmemory
Proof-backed, drift-resistant AI memory for your codebase. 11 languages, 28 MCP tools, evidence-linked claims.
Skills Not MCP
80-90% token savings with Skills+ shell vs MCP
Context Engineering Bootcamp
Context Engineering for LLMs: structured notes on RAG, system prompts, MCP, Agents, and Memory Management — compiled from multiple expert sources.
Paper7
arXiv papers as clean Markdown for LLMs. 97% smaller than PDF. Zero dependencies. Bash-only.
Scopeon
AI context observability & optimization for Claude Code, Copilot CLI, Codex, Gemini — TUI dashboard, preset optimization, cost tracking, CI gates
Lazy Load
🫠 MCP tools eating your context window? Lazy-load them on demand across all AI agents with one command.
Multiplexer
One MCP server fronting many: list_servers, list_tools, search_tools, describe_tool, call_tool, refresh_tools, authorize_server. Lazy schema discovery slashes context-token costs.…
Context Cost
Measure what your MCP servers cost in context tokens — audit your own config, or badge the server you publish
Dsh Tool Guardian
Tool Guardian as a native DeepSeek Harness (DSH) bundle: keeps tool definitions out of the context window by fronting your MCP servers behind a small native router. A bridge to th…
Lazy
MCP lazy loading proxy for AI agents - reduce context window token usage by 90%+
Universal Context Mode
Stop losing context to large outputs — MCP server that compresses tool outputs. Works everywhere: Claude Code, Cursor, Windsurf, Copilot, and any MCP-compatible IDE.
Forget
Convert MCP servers into Skill documents + CLI wrappers. Kill context window overhead.
Demipass
Secrets management for LLM sessions. Keep credentials out of context windows.
Tooltrim
Tooltrim — an open-source MCP proxy: aggregate N MCP servers, filter and shrink tool descriptions, and trace every call.
Zerodb Sequential Thinking
Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-con…
4q Tokenz
MCP Proxy Gateway - Intelligent proxy that reduces token usage by exposing only mcp_search, mcp_call, and mcp_schema
Larkx
AI codebase indexer and MCP server for Claude Code, Cursor, and Copilot. Pre-index your project into a compact graph and measure real token savings with `larkx bench`.