context-window
21 servers · 3,099★ total
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.
Code intelligence for agents: find the code that matters and keep your context window and tokens lean.
DAG-based Lossless Context Management for Claude Code. Every message preserved, summaries cascade as a DAG, patterns extracted via Lossless Dream — full recall and reflection across sessions.
AI-powered MCP proxy for Playwright and Figma. Optimize Claude Code and AI agents with session recovery, context reduction and intelligent tool routing.
Proof-backed, drift-resistant AI memory for your codebase. 11 languages, 28 MCP tools, evidence-linked claims.
Your agent can read git log. It can't read the shell commands you tried that failed. NexusMem indexes shell history with exit codes, git commits and diffs, and project docs into a local SQLite database, and serves back a token-budgeted slice on demand. No cloud, no account.
MCP C++ project indexer for fast symbol, module, and source-range navigation in large C++20 codebases.
Context-optimized MCP server for web scraping. Reduces LLM token usage by 70-90% through server-side CSS filtering and HTML-to-markdown conversion.
CLI bridge that wraps MCP servers as bash-invokable commands, recovering ~11K tokens of context window per session
High-performance local SQLite FTS5-based tool output cache and MCP multiplexer for AI agents.
High-performance, low-latency MCP server for local code context. Features AST-aware symbol graphs, semantic reranking, and PageRank-scored search for AI agents (Claude, Cursor, and more).
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.
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. Cross-platform single-file CLI.
Save 60-80% tokens when AI reads code — MCP server for token-efficient code navigation with AST-aware structural reading
Reduce Claude AI token consumption. Zero install to start. Python 3.7+ for auto-manifest generation.
Persistent memory for Claude Code. Survives compaction and session boundaries: anti-patch reconcile-on-write with LLM-judged de-duplication, a forced PROGRESS.md handoff, a live PLAN.md anchor with an enforced directive ledger, FTS5 search, MCP tools and a GUI. Pure stdlib Python, zero runtime dependencies.
🧠 Mnema — Long-term memory for AI via MCP × Vector DB. Pluggable backends, hybrid search, Auto Dream consolidation, CLI + REST API + SDK.
Zero-overhead MCP proxy for AI coding agents — transparent wrapper gives subagents MCP access without loading schemas into the main context