1. Conduid
  2. Marketplace
  3. #context-window
Tag

MCP servers tagged context-window

39 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.

39
live servers
43
avg trust
622
most stars
1

MCPProxy

smart-mcp-proxy

Supercharge AI Agents, Safely

★ 148updated 6 months agoMIT
88
2

varun29ankuS/shodh-memory

varun29ankuS

Cognitive memory for AI agents — learns from use, forgets what's irrelevant, strengthens what matters. Single binary, fully offline.

★ 120updated 6 months agoApache-2.0
88
3

Headroom

chopratejas

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP s…

★ 622updated 6 months agoApache-2.0
87
4

Baml Agents

Elijas

Building Agents with LLM structured generation (BAML), MCP Tools, and 12-Factor Agents principles

★ 60updated a year agoMIT
59
5

Smart Webfetch MCP

mathisto

Context-aware web fetching MCP server that prevents LLM context window flooding

updated 9 months agoMIT
57
6

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…

52
7

Mnemon

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with Claude Code, OpenClaw, and any CLI agent.

52
8

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.

44
9

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…

44
10

Hypa

Local context runtime for coding agents: compress shell output, query code, and proxy MCP tools

42
11

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.

39
12

N2 Arachne

Optimize AI workflows with Arachne. Automatically assembles the perfect code context (Tree, Target, Deps, Semantic) to fit context windows without noise. Built for efficiency and…

39
13

Reshapr

The open source, no-code MCP Server for AI-Native API Access

39
14

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.

39
15

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 -…

39
16

Unclog

Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.

39
17

Skillreaper

Evidence-based pruning for your AI-agent stack — scan, report, and safely prune unused skills/MCP servers/agents using real transcript evidence

39
18

PlayGuard

AI-powered MCP proxy for Playwright and Figma. Optimize Claude Code and AI agents with session recovery, context reduction and intelligent tool routing.

39
19

Contextrot

Find out where your coding agent starts degrading. Personal context-rot analytics from your own sessions - 100% local, zero-config: uvx contextrot

39
20

Slop

MCP orchestrator — connect unlimited Model Context Protocol servers through 8 meta-tools. Progressive tool discovery keeps your AI agent's context window small.

37
21

Lazy

MCP lazy loading proxy for AI agents - reduce context window token usage by 90%+

37
22

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.

37
23

Forget

Convert MCP servers into Skill documents + CLI wrappers. Kill context window overhead.

37
24

Slim

MCP proxy that gives agents their context window back. Schema compression, lazy loading, response caching.

37
25

Demipass

Secrets management for LLM sessions. Keep credentials out of context windows.

37
26

Tooltrim

Tooltrim — an open-source MCP proxy: aggregate N MCP servers, filter and shrink tool descriptions, and trace every call.

37
27

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…

37
28

4q Tokenz

MCP Proxy Gateway - Intelligent proxy that reduces token usage by exposing only mcp_search, mcp_call, and mcp_schema

37
29

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`.

37
30

Tooltax

Token-budget linter and public leaderboard for MCP tool schemas.

37
31

Cortex Ast

A powerful Model Context Protocol (MCP) server and Omni-AST engine. It empowers AI agents to seamlessly parse complex codebases, execute secure cross-project operations, and dynam…

34
32

ShipItAndPray/mcp-memory

based, zero dependencies.

34
33

Reshapr.io

reShapr website

34
34

Cpp Project Indexer

MCP C++ project indexer for fast symbol, module, and source-range navigation in large C++20 codebases.

34
35

zzallirog/weighted-compact

enforced).

34
36

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…

34
37

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.

34
38

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.

34
39

nomadop/session-watcher

no metric ever enters the model's context.

34
← Previous Page 1 of 1 Next →