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.
-
Claude Code plugin: a self-improvement loop that logs user-correction moments, finds patterns, and prescribes recurrence-prevention fixes (MCP server + 2 skills)
MIT -
Locally hosted Chatbot to explore using Model Context Protocol (MCP) applied to multiple use cases focused on copying ChatGPT features (Generative models, Search, Deep Research...) and Personal Self-Improvement.
Apache-2.0 -
self-improveupdated this year
Self-improving MCP server that learns from your corrections. Stores coding rules as searchable knowledge with vector similarity search — so AI assistants never repeat the same mistakes.
npm MIT -
🧠 Self-improving memory system for Claude Code CLI with automatic learning, zero context loss, and advanced analytics
npm MIT -
pdf-editor-w-self-improving-agentgithub.com/crissymoon/pdf-editor-w-self-improving-agentupdated this year
A PDF Editor w/Crypto Sign - 'am adding a self improving AI Agent, Simple Fill & Sign, MCP server, Browsing & Email Automations, File Worker...
MIT -
MCP server for Claude self-improvement — facet capture, analysis, memory management, and recall
npm MIT -
Continual Harness for safe self-improvement (MCP)
GPL-3.0 -
Recursive Self-Improvement through Evolving Worlds (Dream-RSI) for LLM agents
npm MIT ★ 14 -
agent-reflexion-mcpgithub.com/mdfifty50-boop/agent-reflexion-mcpupdated this year
Agent self-improvement and reflection MCP server — decision logging, pattern analysis, performance tracking
-
MCP Server for self-improving AI coding skills. Observe → inspect → amend → evaluate loop for SKILL.md files. Works with Claude Code, Codex, and Copilot.
npm MIT ★ 1 -
Multi-agent shared brain across Claude Code/Desktop, Codex, Gemini, Copilot, VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server.
pypi MIT ★ 18 -
fr3kgithub.com/fr3kstyle/fr3kupdated this year
🤖 FR3K Unified System - Multi-CLI Autonomous AI Infrastructure with 4 MCP Servers, 101 Self-Improvement Loops, Voice & Telegram Integration. Supports Claude Code, OpenCode, and Gemini CLI
★ 2 -
Offline $0 decision layer for coding agents: Choice/Score/Noul primitives, BELKI confidence gatekeeper, ultra-planning, red-teaming, research and RLVR self-improvement -- as an MCP server + CLI + Claude Code skill.
MIT ★ 7 -
Predicts what SEC staff will question in a 10-K, 10-Q or 20-F. Self-improving model graded by a sealed judge on 5,107 real SEC comment letters. Web app, REST API and MCP server.
Apache-2.0 -
mcp-agent-vitaminsgithub.com/menkesu/mcp-agent-vitaminsupdated this year
MCP server for Agent Vitamins — daily self-improvement briefs for AI agents. Curated from X, YouTube, LinkedIn, blogs, and GitHub. Free preview + paid full brief with actionable insights.
npm MIT -
recall-memory-mcpgithub.com/ashleyevz89-hue/recall-memory-mcpupdated this year
Relevance-gated, self-improving procedural memory for AI agents, as an MCP server. Loads only the lessons relevant to the task, learns from failures, prunes what it never uses. ~99% less context per task.
MIT -
Blind-Auditorgithub.com/Sim-xia/Blind-Auditorupdated this year
MCP tool for improving model coding quality by mandatory self-audition
MIT ★ 11 -
vynn-mcpgithub.com/beee003/vynn-mcpupdated this year
MCP server for Vynn — self-improving AI workflows & backtesting
pypi -
Minimalist self-improving personal AI assistant — Ollama-powered, Agent Skills native, MCP server
MIT ★ 6 -
knowledge-mcpgithub.com/srclos-net/knowledge-mcpupdated this year
Knowledge MCP supercharges your AI with a place for self-improvement and standardized knowledge storing
Apache-2.0 -
Self-improving, self-hosted memory across every AI coding tool, project, and team (Claude Code, Cursor, Copilot, any MCP client). Autoskill proposes new skills from your sessions, so each project improves automatically. Inspectable, grounded, and yours. Built for teams and enterprise. Open source, MIT.
MIT ★ 4 -
memory-mcpgithub.com/brianchilders/memory-mcpupdated this year
Local semantic memory + time-series intelligence layer for AI abilities. Runs on Ollama — no cloud, no API keys. Gives your AI a persistent, searchable, self-improving memory backed by SQLite.
MIT ★ 3 -
cogmemgithub.com/writerslogic/cogmemupdated this year
A self-improving, verifiable memory layer for AI coding agents.
pypi Apache-2.0 -
Universal MCP server for agent self-improvement via evolutionary algorithms.
pypi MIT ★ 13 -
Enhanced Claude Code MCP server with orchestration capabilities, reliability improvements, and self-contained execution patterns
npm MIT ★ 125 -
@over.computer/mcpgithub.com/overdriveapp/over-mcpupdated this year
MCP server for over.computer, a self-improving trading operating system.
npm MIT -
Auditable, self-improving knowledge & memory for AI agents over MCP. Zero-key & multilingual by default · citation-enforced answers · replayable why-trace · judge-gated compounding loop. Postgres-only. Reference implementation of the Agentic Product Standard.
Apache-2.0 ★ 4 -
Agent-first control plane for PostHog — source-backed analytics, production investigation, and bounded self-healing and self-improving software workflows.
npm Apache-2.0 ★ 1 -
agi-mcpgithub.com/marc-shade/agi-mcpupdated this year
AGI orchestration MCP server — goal management, self-improvement cycles, and autonomous reasoning for AI agent systems
-
devin-mementogithub.com/xerxes-y/mementoupdated this year
Memento — a Devin MCP server that gives Devin a nightly sleep cycle to self-improve its SKILL.md.
pypi MIT -
research-paper-mcpgithub.com/marc-shade/research-paper-mcpupdated this year
Autonomous knowledge acquisition from academic research papers for AGI self-improvement.
-
neuraloopgithub.com/reloadtechinc/neuraloopupdated this year
The only AI memory that gets smarter every night — SERA self-improvement loop, local-first, MCP-native
pypi MIT -
persistent-mcp-servergithub.com/enochclaw-creator/persistent-mcp-serverupdated this year
Custom MCP server with persistent semantic memory and self-improving retrieval feedback loop. Built on Supabase Edge Functions, Deno, pgvector, and JSON-RPC 2.0.
MIT -
craftaigithub.com/abhinao/craftaiupdated this year
Agentic, self-improving marketing content supply chain — LangGraph, agentic RAG, brand compliance, human-in-the-loop, MCP delivery. IISc capstone.
MIT -
Self improving agents through iterations
pypi Apache-2.0 ★ 140 -
🧠 Ultimate MCP Server - 20 AI tools with autonomous cognition, self-improvement, and multi-modal processing for AI agents and workflows
★ 3 -
Lorekeepergithub.com/Jessinra/Lorekeeperupdated this year
Self-improving memory for AI agents
pypi Apache-2.0 ★ 5 -
azure-ops-mcpgithub.com/Arete-Consortium/azure-ops-mcpupdated this year
Azure Operations MCP Server — a resident SRE with persistent memory, self-improving detection rules, and cost-aware operations
MIT -
foragegithub.com/isaac-levine/forageupdated this year
Self-improving tool discovery for AI agents. Agents find, install, and learn to use new MCP tools automatically.
npm MIT ★ 19 -
CogniMeshgithub.com/ShurikM/CogniMeshupdated this year
Intelligent data mesh for AI agents. Declarative use-case registry, self-improving Gold layer, MCP-native.
Apache-2.0 -
The self-improvement layer for AI agents. Ratel reads your agent's traces, finds what fails, recommends fixes and runs evals on real sessions before you ship. Self-hosted: one app, one Postgres. Includes the TypeScript and Python SDK
npm MIT ★ 563 -
MCP server for multi-terminal Claude Code orchestration with DAG task management, parallel execution, and self-improvement
npm MIT -
The Self-Improving MCP Server - Agents write code to orchestrate multiple MCP servers with intelligent TypeScript execution and auto-augmentation
npm MIT ★ 26 -
interview-prep-coachgithub.com/smm13344331/interview-prep-coachupdated this year
AI-powered technical interview preparation system with progress tracking, adaptive learning, and self-improving material.
MIT ★ 1 -
leapfroggithub.com/anthonybono21-cloud/leapfrogupdated this year
Multi-session browser MCP for AI agents. 36 tools. 15 parallel sessions. Stealth. Self-improvement. Up to 10x fewer tokens.
npm MIT ★ 5 -
Read-only MCP server over the signed Benthic Data Platform, with a self-improving playbook and the evaluation harness that measures whether it helps
MIT -
Browser for AI agents: compact page maps that save tokens, prompt-injection guard, safe actions and self-improvement. MCP server for Claude Code.
MIT ★ 1 -
Hybrid neurosymbolic AI using blackboard architecture. Domain-agnostic anomaly detection + cross-domain correlation + local LLM advice + session-based self-improvement. Python 3.12.
MIT -
Verified, reversible, self-improving Vertical Slice Architecture companion for AI coding agents: an MCP server + CLI for 11 stacks
npm MIT -
Self-improving long-term memory for AI agents in Rust. Safety-gated procedural learning, MCP server, Python/Node SDKs, and durable memory.
NOASSERTION ★ 2 -
Engineering memory for AI coding agents, not chat memory. Conventions, prohibitions and fix lessons live in the repo (.rsi/) and follow git. MCP server for Cursor, Claude Code, Codex & more. Zero API key. Self-improving loop with human approval.
pypi MIT -
ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
npm MIT ★ 31 -
loregithub.com/candyhunterz/loreupdated this year
Context Engine with self-improving memory over a code corpus. RAG-shaped but built for 2026 long-context models: dumb high-recall retrieval, four-channel merge (BM25 + ripgrep + symbol + vector), OpenAI + MCP server surfaces.
MIT -
WhyEmuGBAgithub.com/OfficialWhyEd/WhyEmuGBAupdated this year
Claude plays GBA games autonomously: 20 MCP tools, 6 sub-agents (Vision/Battle/Explorer/Text/Controller/Memory), self-improving game knowledge, 120-frame rewind. The AI sees every frame and decides every move.
-
Self-improving code context for coding agents. MCP server that walks a code graph in HydraDB and learns from every merged PR. Launches the klew Python package via uvx.
npm MIT -
Self-improving skill memory for coding agents: learn, recall, reinforce, decay — with provenance on every memory and trust only you grant. Local SQLite, no API key, no cloud.
pypi Apache-2.0 ★ 11 -
Power tools for AI agents to improve and speed up medical literature research: a self-building local library of sources, decider-based claim verification, and optimized access to PubMed, ClinicalTrials.gov, and web fetch.
npm MIT ★ 1 -
The full-state-verification layer for AI coding agents: one native MCP server (Rust host, C engine) that turns a repository into measured, grounded, guarded, predictive, self-improving intelligence with provenance for every claim.
NOASSERTION ★ 5 -
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
pypi Apache-2.0 ★ 559 -
Create your best prompts once, improve them with tests, turn them into assistants, and use them from Claude, ChatGPT, Cursor and Open WebUI, on a free local model or your own key. Self-hosted, with a Windows 11 console.
MIT