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.
-
kiro-learngithub.com/brendangeck/kiro-learnupdated this year
Continuous learning for Kiro agent sessions on AWS. Passive tool-use capture, LLM extraction, and synchronous context injection — inspired by claude-mem, aligned with Bedrock AgentCore Memory.
npm Apache-2.0 -
claude-gladiator-mcpgithub.com/vvkmnn/claude-gladiator-mcpupdated this year
An MCP server for continuous learning in Claude Code
npm MIT -
claude-gladiator-mcpgithub.com/Vvkmnn/claude-gladiator-mcpupdated this year
⚔️ An MCP server for continuous learning in Claude Code
MIT -
graphonomousgithub.com/c-u-l8er/graphonomousupdated this year
Continual learning MCP server for AI agents — topology-aware knowledge graph with kappa-routing, exposed as 5 loop-phase machines (retrieve/route/act/learn/consolidate), causal metadata, and neural embeddings. One of four MCP servers in the [&] three-prot
npm Apache-2.0 -
A bunch of MCP servers...Initially created to learn more about MCP. Now I continue to create these servers because I’m having fun😁
-
DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase.
MIT ★ 49 -
Persistent codebase memory for AI coding agents — Claude Code, Codex, Cursor, Cline, Continue and any MCP client. Learns which files go together from how you work and serves compact, ranked context: the gold file on 40 of 40 public-benchmark queries to keyword ripgrep's 32 of 40, at 31-67× fewer tokens than ripgrep and 51-242× fewer than pasting every source file (a larger 150-question eval misses 10). Local-first, no telemetry by default.
pypi MIT AND LicenseRef-NeuralMind-Commercial -
Self-learning loop for Claude Code — corrections and failures become skills, behind a human gate. MCP + hooks, Windows-native, zero background LLM calls.
MIT ★ 7 -
os-prismgithub.com/c-u-l8er/ampersandboxdesignupdated this year
PRISM OS-009 reference MCP server — 6 loop-phase machines (compose, interact, observe, reflect, diagnose, config) that benchmark any PULSE-conforming memory system. One of four MCP servers in the [&] three-protocol stack (box-and-box, graphonomous, os-pri
npm Apache-2.0