- 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.
zzallirog/weighted-compact
enforced).
ContextTax
Measure the context-window tax an MCP server charges your AI agent — the real token cost of its tool schemas + responses. Ground truth (Anthropic count_tokens) or keyless estimate…
Memory Indexer
.NET SDK and MCP server implementing a cognitive science-based 3-axis memory system (type x scope x tier) for LLM context management beyond finite context windows.
Fastmcp Endpoint Toolsets
One FastMCP server, one port — expose each tool group at its own native MCP URL, so every agent sees only the tools it needs. No proxy, no gateway.
nomadop/session-watcher
no metric ever enters the model's context.
TokenKeeper
Local RAG memory for Claude Code -- reduce prompt tokens by ~80% with hybrid semantic + keyword search
GearCore
One skill to rule them all — a unified MCP & skill hub for Claude Code, Codex, Kimi, and OpenCode. Register once, sync everywhere.
Cortex Agents Infra
The High-Performance, Hardware-Adaptive Knowledge Engine for MCP Agents: Hybrid Graph-RAG & Atomic Concurrency Control.
Belifoa
⚡ High-performance, compact Linear client & MCP server for AI agents. Reduces prompt context payload by 70–80% with persistent auth, CLI, skills & git hooks.
Confluence File Based
MCP server for Confluence: returns storage XHTML files to LLMs, reducing token usage and preserving macros/tables on updates.
Agent Context Optimizer MCP
MCP Server that solves context window overload — smart tool pruning, relevance scoring, budget tracking for AI agents
Claude Rework
Local memory for Claude. Indexes your past sessions so Claude can answer questions about them for ~2.5k tokens instead of ~211k, and carries that memory to a new machine or accoun…
Salc
Symbolic Context Virtualization Protocol — a local-first, deterministic tool that lets an LLM navigate and edit a repository through a compressed, lazily-expandable symbol graph i…
Claude Code Dig
Never lose context to compaction. Archive pre-compaction transcripts, restore working state, and let the model dig back into what it forgot — MCP tools for Claude Code.
Capsule
Codex plugin MCP server (codex-plugin-mcp) for token efficiency, token reduction, context compression: exact-recoverable terminal, file, project, web, memory.
Vibecode Project
VibeCode creates cryptographically verified Digital Twin snapshots—immutable PDFs that serialize entire codebases with full restoration. Powered by large-context LLMs, it combines…
Linkforge MCP
An AI-native MCP server that replaces raw SaaS CRUD calls with token-optimized semantic queries — pre-filtered, compressed insights for Todoist, Linear, Spotify, and Strava instea…
Compression Proxy
A MCP proxy that compresses and optimizes tool description context consumption.
Context Optimizer
Reduce Claude AI token consumption. Zero install to start. Python 3.7+ for auto-manifest generation.
My Tiny Local AI Agent
Local-first chat agent that runs comfortably with small-context local LLMs (from 2B) without losing the original goal of a long conversation. Multi-window context with rollovers,…
Umb
MCP gateway: one Rust binary fronts every MCP server, cutting tool context ~99% via a 3-tool API. Source-available.
Neoxider MCP Hub
One MCP tool instead of every schema you own — a lazy capability broker that cuts resident tool context by a measured 94.4%. Search, inspect, enable and call MCP servers and skill…
Logica Context
MCP server that protects your AI context window via sandboxed execution and smart indexing. 97% token savings.
Context Compress
MCP server and hook toolkit that compresses tool output to save context window tokens.
Shihwesley Plugins
Claude Code plugin marketplace by shihwesley — codebase mapping, documentation, research sandboxes, and developer productivity tools
Vraksha
Vraksha remembers so you can focus on creating.
HyperSABMemory
Git native context harness and memory engine for AI coding agents. Local first, no telemetry.
Claude Rlm
🧠 Enable Claude to handle long inputs using Recursive Language Models that recursively analyze data beyond standard context limits.
Ast Rag Support MCP
A local-first, high-performance MCP server for semantic code retrieval. Features AST-based functional chunking, reactive filesystem indexing, and Gemini-powered query expansion fo…
Plateau
Bounded context for long-horizon LLM agents: carry a small re-grounded signal instead of replaying the transcript, so a parent agent's footprint stays flat as the task grows. Reco…
Session Migrator
A cross-agent session memory migration layer: migrate or compress a conversation based on the target model's context window. MCP server + Python library.
Origin Memorycore
LLM Agent 记忆治理层 —— 热层/冷层双层,自动溢流 + 自适应召回阈值 | Memory governance layer for LLM agents — hot/cold tiers, automatic overflow + adaptive recall threshold
Contextclean
Local-first context cleaner for AI agents.
MASE Agent Memory
Governed white-box memory for LLM agents: every fact carries a mechanically-verified evidence span, every rejected hypothesis is documented. Local-first (SQLite+FTS5), 1000+ tests…
Claude Contextlens
See where your coding agent's tokens actually go. Local usage analytics and setup audit for Claude Code: cost, prompt-cache economics, context growth, 5-hour billing windows, and…
SynapseCode
Ultra-fast Code Graph & AST Pruning MCP Server for LLMs. Reduces context token consumption by 75%-90% in Claude, Cursor & AI Coding Agents.
Reposnap MCP
Free MCP server to ingest any public GitHub repository directly into your AI context. Works with Claude, Cursor, Windsurf, and any MCP client.
Pager
Token-aware response paging for MCP servers. One line of code — large tool responses chunked and delivered page by page.
Kotro Proxy Engine
Local coding-agent control plane — MCP action governance + LLM-path protection + cost control. One Rust binary, no SaaS.
Token Smithers
Your Smithers (butler) for MCP token efficiency. Compression proxy that saves tokens on tool results, tool schemas, and server instructions — sits between any AI coding tool (Clau…
Ctxlens
ESLint for MCP servers — a read-only CLI that audits MCP tool definitions for token cost, description quality, and schema hygiene before your agent burns its context window.
Token Benchmark
Token-cost benchmark for MCP tool definitions: 9 servers measured, a 25x efficiency spread, and a 95% lighter redesign of the worst offender
Context Io
Resume any coding session in a new AI agent for <500 tokens, not 20k+ - automatic capture via git hooks, zero LLM calls, works with any MCP-capable agent.
Lithium Kb
🧠 Fast, zero-dependency structured knowledge base (.agent-kb/) with 2D neural graph visualizer │ & MCP server for Claude, Codex, PI, Cursor, Windsurf, Zed & Other AI coding agent…
Skillassay
Static analyzer for AI coding-agent context — and an Agent Skill your agent can run. Measures always-on context cost of CLAUDE.md, AGENTS.md and Agent Skills; finds skills that wo…
Weigh
Weigh your MCP servers — one command to see how many context-window tokens every MCP server costs you, across Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, and Gemini CL…
Ctxbudget
Measure the fixed token cost of coding-agent instructions, skills, and MCP tool schemas.
Clines
Measure your codebase from the terminal — lines per language, duplicate code, complexity, token cost for AI agents, comment drift, change coupling, a refactor verdict per file, an…
Claude Certified Architect Prep Cohort
Cohort work for Claude Certified Architect Prep (DevCompass) — notes, labs, and solutions.
Lean
A lazy-loading MCP proxy that keeps your agent's context window small — it exposes upstream tool schemas only when they're actually needed.