"Automatic context compression tools or methods" matching MCP servers:

Drives real COMSOL Multiphysics sessions through natural language over MCP, covering geometry, materials, physics fields, coupling, meshing, studies, solving, and result visualization via 99 tools with session protection, serial execution, and HTTP authentication. Also provides an original 3D heat-sink example and curated classic case recipes across physics domains such as AC/DC, acoustics, heat transfer, structural mechanics, and optics.

A Model Context Protocol (MCP) server designed to easily dump your codebase context into Large Language Models (LLMs).

Lets AI agents inspect local or remote videos by reading metadata, detecting shots and cuts, extracting frames as images, and checking keyframes for seeking and streaming, all via local FFmpeg without an API key.

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.

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.

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 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.

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programming languages and authenticated CLIs.

MCP server for personal knowledge management providing AI-powered tools for semantic search, audio transcription, image generation, and PPT creation.

Provides official INDEC register designs and methodological rules to AI models, enabling accurate EPH data analysis code (R/Python) without hallucinations.

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.

Deterministic dependency + CVE context for AI coding tools, over the Model Context Protocol. A ~0.85 MB pure-Rust MCP server.

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.

Provides five safe tools (calc, search, model_drift, compare_runs, grade_answer) for arithmetic, keyword search, model drift monitoring, eval comparison, and answer grading against sources, all implemented directly from the MCP spec with zero dependencies.

Provides AI assistants with real-time visibility into your codebase's internal libraries, team patterns, naming conventions, and usage frequencies to generate code that matches your team's actual practices.

An MCP server that provides a persistent sandbox for AI coding agents to explore codebases server-side, returning only compact summaries to reduce context consumption.

Aggregator MCP proxy that collapses N downstream MCP servers into 4 meta-tools with progressive tool discovery, and compresses large tool outputs (HTML→Markdown, JSON summarization) with full-output retrieval via read_more and a per-session token-savings report.

Enables extraction of recipes from PDFs or JPG files and conversion into structured HTML, with interactive region selection and OCR via a web GUI.

Enables validating JSON/JSONC, getting/setting values with jq-like paths, pretty-printing or minifying, validating against Ajv JSON Schema, and diffing local files or inline strings without network calls.