- 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.
LRO
Large Result Offloading (LRO) -- a token-aware strategy for managing large tool outputs in LLM context windows. Includes empirical evaluation and formal specification.
Ctx Budget
See what's eating your LLM context window — analyze prompts and MCP tool manifests for token cost, per-tool breakdown, and what to lazy-load. Zero dependencies.
X Coder
Agentic Workflow Based Coder System
Contextlint
Audit what your AI coding assistant loads before you type: token cost, dead weight, and MCP security risk — across Claude Code, Codex, Cursor and Copilot.
Nexus Thinking Os
A context management protocol and thinking OS for stable, multi-layered AI interactions.
Benchmark Article Resources
An Investigation Across Two MCP Servers, Two Frontier Models, and 20 Controlled Benchmark Runs
Leptin
Personal, local-first memory infrastructure for your coding agent. No account, no subscription; the agent can install it itself. Keeps long-term memory correct when decisions chan…
Ctxdiet
Detect, fix, and measure AI coding-agent context-token waste across Claude Code, Codex, Cursor, Gemini & Copilot.
Token Save MCP
Stop your coding agent burning context on file reads. Delegates big reads to a cheap worker model and returns only the answer — 87-99% saved, measured per call. A hook enforces it…
Agentic Context Compression Framework
Rust MCP server for lossless agent-context compression, reducing token usage while preserving retrieval accuracy.
Mcpaxe
🪓 Weigh your MCP config. Chop the context tax — audit the token cost of every MCP server & tool, find the ones you never use, and generate a slim config. Works with Claude Code, C…
Skill Gateway
Local skill intelligence layer — index, audit, relate & orchestrate the skills your coding agent already has. Zero deps, CJK-first, offline dashboard.
Context Loss Audit
Audit what your output compressor silently deleted: how much of the reduction was real noise, how much was signal. Turns a compressor's 'cuts 90%' claim into two honest numbers.
Agentfit
Fit your messages into the LLM context window. Token-aware truncation with multiple strategies, pluggable tokenizers, zero deps.
AI Codebase Vectorizer
RepoMap AI 2026: Map Codebases for AI Assistants Beyond Window Limits
Dsh MCP Adapter
Context-cheap, crash-resistant MCP access for the DeepSeek Harness: one lazy proxy tool instead of dumping every server's schema into context. Zero dependencies.
MemoryAI
Remember everything. Send only what matters. Universal, local-first long-term memory for Claude Code, Cursor, Codex, and MCP.
Claude MCP Check
Every MCP server Claude Code would load, from which file, whether it starts and answers the handshake, and what its tools cost in context. Approve, switch off, lint, explain a fai…
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…
Agent Toolbox
Download every AI skill, agent, plugin and MCP server you find without breaking your coding agent. Tools stay parked on a shelf, and each task borrows a small loadout for one sess…
Lens
Semantic MCP router/proxy: front a fleet of MCP servers, cut tool-definition context ~98%. Lazy tool discovery for Claude, Cursor & AI agents.
Ctxtax
No description published.
Chronicle
No description published.