Context-Engine MCP - Agentic Context Compression Suite

Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

[ICML 2026] Meta Context Engineering via Agentic Skill Evolution

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

Local persistent memory store for LLM applications including continue.dev, cursor, claude desktop, github copilot, codex, antigravity, etc.

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.

A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project knowledge across agents and repos.

A context engine that treats skills as software.

rtfmbro provides always-up-to-date, version-specific package documentation as context for coding agents. An alternative to context7

Compiles AI agent traces and truns them into reusable context.

Memory and context manager just works.

Context engine for large codebases, exposed through MCP. Gives AI coding agents precise repository context; benchmarked at frontier-agent quality with ~25x lower model cost and 45% fewer tokens with semantic search.

BitDive Model Context Protocol (MCP) server. The Autonomous Quality Loop for AI agents. Provides real runtime context, before/after trace comparison, and integration testing workflows.

A Model Context Protocol (MCP) server that retrieves information from Wikipedia to provide context to LLMs.

Recursive Language Model patterns for Claude Code — handle massive contexts (10M+ tokens) by treating them as external variables

Compounding Context for AI Coding Assistants — MCP graph engine for Claude Code, Cursor, Copilot, Gemini, OpenCode

The Biomimetic Context Engine & Neural Runtime for AI Coding Assistants

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

Offline context handoff between coding agents. Read local histories into fresh sessions; source stores stay unchanged. Stdlib-only Python, not live session restore.

Model Context Protocol (MCP) Server to connect your AI with any MediaWiki

Algorand Local Model Context Protocol (Server & Client)

BioMCP: Biomedical Model Context Protocol

Structured planning and persistent context for AI coding agents. Plan multi-phase work once and any agent (Claude Code, Codex, OpenCode) executes it across sessions without losing the thread.