MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
distill-mcpgithub.com/lakshgk/distill-mcpupdated this year
—
npm MIT -
distil-proxygithub.com/exec-io/distil-proxyupdated this year
MCP server for the Distil web proxy — distil_scrape, distil_search, distil_screenshot, distil_raw, distil_render, distil_nocache for Claude Desktop, Cursor, Windsurf, and any MCP-compatible AI tool
npm MIT -
distillgithub.com/5queezer/distillupdated this year
Privacy-first team memory MCP server — local LLM distillation before team sync
pypi MIT ★ 1 -
paper-distill-mcpgithub.com/Eclipse-Cj/paper-distill-mcpupdated this year
MCP server for academic paper search, curation, and multi-platform push
pypi AGPL-3.0 ★ 66 -
distill-mcpgithub.com/arthurdev44/distillupdated this year
Distill - MCP Server for LLM token optimization and context compression
npm MIT -
distil-ai-rms-reportingactive
MCP server for restaurant management system reporting and analytics
npm UNLICENSED -
distillgithub.com/arthjean/distillupdated this year
Your agent wastes context. Distill fixes it.
MIT ★ 6 -
openclaw-knowledge-distillergithub.com/destinyfrancis/openclaw-knowledge-distillerupdated this year
Open CLAW Knowledge Distiller · 龍蝦知識蒸餾器 — Turn YouTube/Bilibili videos into structured knowledge articles. Local Qwen3-ASR MLX + AI summarization. MCP server for Claude Code / Open CLAW agents.
★ 65 -
distillgithub.com/afly007/distillupdated this year
Self-hosted RAG pipeline — ingest technical PDFs and web pages into a searchable knowledge base, exposed as MCP tools
MIT ★ 2 -
Provide academic paper search and curation across platforms using the Model Context Protocol for seamless multi-client integration.
AGPL-3.0 -
MCP server for the Distill API: clean Markdown from any web page for AI agents.
pypi MIT -
distilno update data
Context optimization middleware for LLM agents — a dynamic tool registry, result masking, token budgeting and smart compaction, so a long session stays inside its window instead of failing for length.
smithery -
distillgithub.com/gokulnair2001/distillupdated this year
Turn any URL or HTML into clean, agent-ready Markdown — local, fast, deterministic. CLI + MCP server
npm GPL-3.0 ★ 4 -
@janreges/ai-distiller-mcpgithub.com/janreges/ai-distillerupdated this year
AI Distiller (aid) - Essential code structure extractor for LLMs. Provides AI with accurate code signatures, data types, and API contracts from your actual codebase, reducing guesswork and trial-error coding. Accelerates analysis workflows including secur
npm MIT -
distil-refineryactive
Token-bounded (<2 KB) B2A public filings data refinery for AI agents — Cloudflare Workers + Hono + MCP
npm MIT -
Open-source MCP server bridge for Distill — let Claude/Cursor rename your files based on content (AI: Claude/OpenAI/Gemini/Ollama/Apple).
MIT ★ 2 -
蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.
MIT ★ 54 -
PR-Distillergithub.com/rendermani/PR-Distillerupdated this year
Extract reusable coding rules from your team's PR review history and serve them to AI coding assistants in real-time via MCP.
NOASSERTION ★ 1 -
Turn PDFs, Office files and scans into token-lean Markdown for LLMs and coding agents. Local-first: web app, desktop, CLI, MCP server, Claude Code & OpenCode hooks.
npm Apache-2.0 -
distillgithub.com/MitudruDutta/distillupdated this year
Any document → clean Markdown, in a single Go binary. PDF, DOCX, XLSX, EPUB, audio, video, and more — built for LLM/RAG pipelines and MCP-native.
MIT ★ 1 -
Native macOS app that converts PDF, Word, PowerPoint, Excel, HTML, CSV and ZIP files into clean, token-efficient Markdown for AI. Includes a CLI and an MCP server for Claude. Fully on-device.
MIT -
Measure what context compression actually costs an LLM agent: where a session's tokens go, and whether a rewrite pays for the prompt cache it invalidates. Rust crate, MCP server and benchmark harness.
npm MIT ★ 1 -
Auragithub.com/IzzoSol/Auraactive
Cut LLM token spend with zero dependencies. AURA answers recurring prompts free from cache, compresses conversation history, and distills bloated system prompts. CLI, MCP server (Claude, Cursor, Claude Code) and library.
npm MIT ★ 3 -
LLM distillation detection & model fingerprinting via statistical forensics — behavioral probing, stylistic signatures & representation similarity. CLI + MCP ready.
MIT ★ 2 -
Distill AI coding sessions (Claude Code / Codex / Cursor) into weekly reports, ADRs, incident reviews and a knowledge graph — local-first, evidence-linked.
pypi MIT ★ 4 -
Long-term memory for LLM assistants: LLM extraction with JSON-schema validation, hybrid recall of memories (dense + BM25, RRF) plus raw turns, served over HTTP and MCP, and a LoRA-distilled Qwen3.5-0.8B extractor that runs locally via Ollama. Benchmarked on LoCoMo. Rebuilt from a 26th-place Neurohack (IIT Guwahati) entry.
★ 1 -
SmartMemoryno update data
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
pypi -
An MCP stdio server in Common Lisp. Distils text to its residue and reports how much was load-bearing, cuts two answers against each other, presses the cut into prose, and encodes the distillate as a scannable QR code. Deterministic; targets MCP revision 2026-07-28.
MIT ★ 1 -
An MCP Server which enrichs and distills the codegraph context before passing to agent.
-
synapsesync-mcpgithub.com/metanmai/synapseupdated this year
MCP server for Synapse — capture AI sessions, distill knowledge, remember everything
npm MIT -
paper_digest_progithub.com/sesameM/paper_digest_proupdated this year
paper-distill-pro 是一个完整的学术论文自动化处理平台,通过 MCP(Model Context Protocol) 协议暴露给 Claude Desktop、Cursor、VS Code 等 AI 客户端使用。
★ 1 -
Watches your app's logs and serves distilled, redacted summaries to AI agents over MCP.
cargo MIT -
Shared dream pool MCP server: let other agents and people submit distilled dream records to one inbox.
MIT ★ 1 -
Claude Code plugins and MCP servers — Evonest, Distill, Solera, metang, and more
MIT -
kbtransfergithub.com/kbtransfer/kbtransferupdated this year
Open-protocol federated knowledge base for AI agents. Karpathy-style wiki + signed pack distillation + MCP-native sharing.
Apache-2.0 -
Reflexive memory for AI agents — forgets, distills, and dreams. MCP server with 28 tools.
pypi MIT ★ 5 -
Evidence-backed MCP tools for architecture agents, distilled from mature open-source systems.
npm MIT -
aurais-mcp-botsgithub.com/vorionsys/aurais-mcp-botsupdated this year
5 Aurais MCP servers (journal, market scout, meeting distiller, research reader, writing editor). Dedup'd onto @vorionsys/aurais-core. Step 2 of 3 in the aurais-mcp consolidation.
npm Apache-2.0 ★ 1 -
Agent 产出物管理层 — auto-capture, distill & rehydrate your AI agent's outputs (Agent KM). Plain-file ledger, provenance, supersede chains, MCP cross-host.
MIT -
agentoolboxgithub.com/solhammer/agentoolboxupdated this year
The quality layer for AI agents — hallucination firewall, import validator, context distiller. Pay per call in SOL.
npm MIT -
Shared local context and memory for multiple AI coding agents via MCP, scoped facts, startup injection, and secret-safe distillation.
-
Course consumer & assimilator: acquire, transcribe, ingest any format, distill, and learn — with Insights, XP progression, and MCP agent tools. Local-first, stdlib-only core.
MIT ★ 1 -
waypointgithub.com/alejandramantillac/waypointupdated this year
Distills the architecture decisions buried in your coding agent's session history into a navigable log.
MIT ★ 1 -
Cognitive Fabric: unified Python MCP server for a KuzuDB graph memory bank with symbolic ingestion, semantic search, and distillation
pypi Apache-2.0 -
LLM-free memory distillation engine + MCP server for companion AIs. Compiles conversations into cognitive facts, keeps persona consistent across sessions. No API key, no LLM guessing.
Apache-2.0 ★ 4 -
A token-optimization and memory layer between agent and model: dedups tool output, distills old turns, prunes to a token budget. Proxy, MCP server, CLI, or library
Apache-2.0 ★ 1 -
Token-budget-aware DOM & UI context distillation engine for AI Coding Agents (Antigravity, Codex, Cursor, Claude Code), Browser-Use & RAG
MIT -
efficient-tokengithub.com/fahomid/efficient-tokenupdated this year
Local-first MCP server that returns distilled, faithful code context to cut LLM token usage without degrading reasoning.
npm MIT -
Local agent memory: capture conversations, distill them into reviewable Markdown, and search with SQLite FTS5. CLI, MCP, and REST.
MIT -
cc-senseigithub.com/contradictory-body/cc-senseiupdated this year
Your AI's shortcut to mastering Claude Code's architecture — 310K lines distilled into 32 queryable modules via MCP.
MIT ★ 4 -
Knowledge-lifecycle MCP: distill agent work into memory, recall it from any agent, promote it local->team->org as it earns trust. Bridges agentsync + context-keeper.
pypi NOASSERTION -
Cross-session memory and recall for AI agents — git-synced knowledge base, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing
npm MIT ★ 19 -
Self-hosted personal memory & RAG system — LanceDB vault, MCP query API, and a daemon fleet (curator, distiller, surveyor, consolidator, janitor) that ingest, classify, and maintain a knowledge graph ambiently.
-
figma-view-mcpupdated this year
Read-only Figma MCP server optimized for AI tool calls: view designs and generate front-end code from token-efficient, distilled node trees.
npm MIT -
Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.
npm Apache-2.0 ★ 63 -
Cross-agent memory for AI coding agents. Verbatim transcripts + distilled memory with provenance, hub/edge replication, MCP tools. Rust · SQLite · local-first · MIT.
MIT -
A local shared-memory bus for AI coding agents — watch agent memory files, distill them into a searchable memory bank with mem0, and inject it back via MCP. Electron desktop app.
★ 1 -
memcpgithub.com/asromanychev/memcpupdated this year
MemCP is a universal long‑term memory layer for IDEs (Cursor) via MCP: it stores distilled project knowledge (facts/few‑shots/links), filters noise, and returns concise, context‑relevant bundles. Core: Rails API + Postgres/pgvector + Ruby STDIO MCP. MVP: save/recall.
-
Unified local deep-research search service for AI agents — one pipeline (search → extraction → query distillation → cache), zero cloud quotas. MCP stdio server with native harness integration.
npm MIT -
verbative-memoryupdated this year
On-device memory system for AI coding agents — dual-layer engine (distilled facts + lossless event ledger), automatically captured and injected, exposed over MCP. Shared across agents, persistent across sessions; files in your repo.
pypi Other/Proprietary License