"Context compression techniques and methods" matching MCP servers:

A lightweight MCP server for semantic search over markdown knowledge bases, enabling AI coding agents to index, search, and answer questions from local markdown documents.

A task-aware context compression layer for Agent workflows, RAG pipelines, and AI Coding assistants, reducing noisy logs, retrieval chunks, and code context into high-signal LLM inputs via CLI, Python SDK, and MCP.

Enables AI agents and MCP clients to compress retrieved web documents against a query, pruning irrelevant noise through deterministic algorithmic scoring so downstream context stays lean. It exposes this capability over the Model Context Protocol for integration with Claude Desktop, Cursor, and similar clients.

Enables AI agents to compress retrieved web documents against a query, pruning irrelevant noise so only the most relevant context reaches the model. It runs as a zero-dependency Python MCP server that accepts a query payload and returns structured, scored output.

An MCP server serving a curated corpus of thinking techniques for AI agents, with tools to classify intents, find and apply techniques, and verify their effectiveness.

An MCP server that keeps raw tool output out of the context window by sandboxing and compressing results (about 98% reduction), persisting file edits, git operations, tasks and decisions in SQLite with BM25 retrieval so the agent resumes after compaction, and enforcing routing across 17 platforms via MCP and hooks. It also encourages the model to write scripts that compute answers and log only results instead of reading large data into context.

Multi-modal RAG engine for AI assistants. Stores conversation history, conclusions, diffs, error traces, and other development artifacts in LanceDB with vector search, multi-factor scoring, and an LLM-driven consolidation pipeline.

Enables semantic search across documentation stored in Gemini FileSearchStores, returning AI-generated answers with source citations.

Context Mode is an MCP server that reduces context window waste by sandboxing data-heavy tools, tracking session state in SQLite, and promoting code-based analysis over raw data reads, achieving up to 98% context savings.

An MCP server that provides dynamic codebase context to Claude Code through tools like hybrid search, recent changes, and symbol definitions, enhancing AI-assisted coding with local RAG.

Provides an external context buffer so a local model can maintain session memory across long tasks and search and page through large documents without loading them whole into its limited context window.

A local-first MCP server that ingests PDFs, extracts structure, and provides semantic search and sequential navigation tools for AI clients to query and learn from documents.

Give your AI agents access to 8,500+ community curated awesome lists with over 1 million curated resources.

Enables AI agents to parse PDFs and search local document context through multimodal extraction and vector-based retrieval, all exposed as MCP tools.

Provides persistent context management for AI agents by storing and querying semantic information using Upstash Vector DB and Google AI embeddings. It enables semantic search, batch operations, and metadata filtering to help agents retrieve relevant stored knowledge.

Context Forge is a vendor-neutral continuity layer for AI tools. It stores project context in Markdown and JSON, retrieves task-scoped context, and leaves structured handoffs so another model can continue without being taught the project again.

Enables MCP-capable clients to query coding-agent conversation exports and retrieve token-bounded evidence bundles with source provenance and hash verification, so LLMs can ground responses in verifiable history without replaying full transcripts.

Enables local-first context retrieval and management from JSONL and Markdown sources through MCP, with a rebuildable full-text search index and support for stable reference pagination.

Enables engineers and AI assistants to search source-backed hardware design guidelines, retrieve detailed conditions and limitations, and trace citations to original sources, all through a read-only offline interface.

A unified context layer that connects your local data — repositories, documents, remote machines, and notes — to LLM interfaces through the Model Context Protocol (MCP).