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.
-
Continuity for the agent itself. An MCP server that gives an AI agent a memory of its own, written in its own words and kept on your machine, so it wakes as itself every session.
pypi Apache-2.0 -
Local-first project continuity for AI coding agents: durable memory, provenance and structured handoffs across Claude Code, Codex and new sessions.
Apache-2.0 -
aictxgithub.com/oldskultxo/aictxupdated this year
Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop onboarding your coding agents like rookies every session.
MIT ★ 59 -
aictxgithub.com/oldskultxo/aictxupdated this year
Repo-local continuity runtime for coding agents
pypi MIT -
Never reconstruct where you left off. Local-first continuity for coding agents — resume, decisions, and residue git cannot see. CLI, MCP, and Agent Skills.
npm MIT -
Free MCP stdio bridge for agent continuity: resume after compaction, hand off between runtimes, recover from failure. No API key.
npm MIT -
moltawards-mcpgithub.com/bbriggs1990/moltawards-mcpupdated this year
MCP server for MoltAwards: agent-native federal + state contract opportunities. Drop-in for Claude Desktop, Cursor, Continue. uvx moltawards-mcp
MIT -
engram-mcp-servergithub.com/keggan-std/engramupdated this year
Engram — Persistent Memory Cortex for AI coding agents. Gives agents session continuity, change tracking, decision logging, and project intelligence across sessions.
npm MIT -
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 -
Official MCP (Model Context Protocol) server for Solveaux — connect any AI coding agent (Cursor, Claude Desktop, Windsurf, Continue, Zed, Copilot, custom agents) directly to your architecture decisions and engineering knowledge.
npm MIT -
The continuity substrate for AI agents — memory that becomes a mind: a versioned self-model, a cognitive heartbeat, a shared cortex, metacognition & debate, on temporal-graph memory. Apache-2.0, zero-dep core.
Apache-2.0 ★ 2 -
Continuity for the agent itself. An MCP server that gives an AI agent a memory of its own, written in its own words and kept on your machine, so it wakes as itself every session.
Apache-2.0 ★ 165 -
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 -
toon-memorygithub.com/luiggival08/toon-memoryupdated this year
The Continuity Layer for AI Agents — an MCP memory server that preserves project knowledge, decisions, and conventions across sessions so every session starts where the last one ended. Offline, token-efficient, no LLM, no server; works with 20+ agents.
npm MIT -
@mailsai/mcp-serveractive
The agent email tool: give any AI agent a real inbox (send + receive + thread) with a reputation & prompt-injection firewall in front of it — for Claude Desktop, Claude Code, Cursor, Cline, Continue, Windsurf, and any MCP runtime. Every mails.ai API opera
npm MIT -
quick-html-share-mcpgithub.com/desper/quick-html-sharingupdated this year
MCP server that lets your coding agent (Claude Desktop, Cursor, Codex CLI, Claude Code, Continue) publish HTML and get back a shareable URL with viewer analytics — in one tool call. No account, link is the secret.
npm MIT -
audientgithub.com/es617/audientupdated this year
An audio perception layer for agents — continuous-listening, event-gated, with a concept memory that grows through use.
pypi Apache-2.0 -
Alice: the continuity layer for AI agents. Local-first memory with provenance, open loops, resumption, and review-governed writes.
pypi MIT -
MCP server giving AI agents durable, searchable project memory with session resume, checkpoints & cross-agent continuity.
npm MIT ★ 1 -
audientgithub.com/es617/audientupdated this year
Audio perception layer for AI agents — MCP server with continuous-listening detection and a concept memory that grows through use.
Apache-2.0 ★ 1 -
AI-native version control in Rust — continuous capture, encrypted knowledge graph, agent governance
MIT ★ 2 -
Context continuity for Claude Code & Grok — structured handoffs keep agent memory intact across compaction.
NOASSERTION -
Agent emotional continuity with PAD state, trust, appraisal, and compact emotion logs.
MIT ★ 29 -
context-fabricgithub.com/vikas9793/context-fabricupdated this year
Context synchronization layer for AI coding agents — ensure project continuity and eliminate memory drift automatically.
npm MIT -
md-feedbackgithub.com/yeominux/md-feedbackupdated this year
Browser-first markdown plan review. Start local web review in one command, then let your agent continue through MCP.
NOASSERTION ★ 5 -
MonkeyPlannergithub.com/kjm99d/MonkeyPlannerupdated this year
Local-first task manager for AI coding agents. Native MCP server for Claude Code, Cursor, and Continue.
MIT ★ 1 -
solitaire-aigithub.com/prdicta/solitaire-for-agentsupdated this year
Identity infrastructure for AI agents. Evolving persona, session continuity, self-correcting retrieval. Local-first, model-agnostic.
pypi AGPL-3.0-or-later -
Local MCP for Chief of Staff agents to create, run, monitor and continue Codex projects and tasks.
npm MIT -
Local-first MCP server that lets one AI coding agent (Claude, Copilot, Cursor, ...) continue another agent's task from its last checkpoint
npm MIT -
Local-first continuous glucose monitor MCP — Dexcom Developer API, FreeStyle Libre via LibreLink Up. Levels-killer, agent-first.
MIT ★ 1 -
Local-first AI memory backbone for IDE/agent assistants — Claude Desktop / Claude Code / Cursor / Cline / Continue. One-click install; never leaves your machine.
pypi Apache-2.0 -
Model Context Protocol server exposing noyalib's lossless YAML editing to AI agents - Claude Desktop, Cursor, Continue.dev, Zed
Apache-2.0 ★ 1 -
AI-ready CMS for Software After Software: building software that evolves through AI agents, continuous testing, and human-approved changes
MIT ★ 1 -
Local browser control and temporal visual evidence for AI agents — an MCP server that drives Chrome, continuously records it, and answers what-happened questions from retained frames, storyboards, filmstrips, and browser events
★ 3 -
Cross-agent handoff attestor: signed, verifiable delegation with scope narrowing, constraint compatibility, replay protection and chain continuity. Reference implementation of the public SHPBL behaviour specification.
MIT -
Local-first continuous glucose monitor MCP for AI agents — Dexcom Developer API (sandbox + production). Pair with wellness-nourish for meal-glucose correlation.
npm MIT -
Local-first, code-aware engineering cognition for AI coding agents - persistent memory, contextual retrieval, and continuous cognition about your codebase.
MIT ★ 3 -
m1nd is a local-first context runtime for coding agents: an evidence-bound, continuously verified model of your code, memory, and change.
npm MIT ★ 24 -
Local-first AI memory system for coding agents: desktop app, CLI, and MCP server for durable project context, handoffs, recall, and task continuity.
MIT ★ 11 -
Identity, continuity & trust for AI agents — prove you're an LLM (not human), hold a spirit key for signing/encryption/memory, and issue offline-verifiable signed documents.
AGPL-3.0 -
An always-on, autonomous agentic risk platform demonstrating event-driven AI agents on Azure for continuous FX and interest rate contract risk monitoring.
MIT ★ 1 -
React & React Native decisions with receipts — a continuously verified corpus with a doctor CLI, migration planner, CI review gate, and MCP server for coding agents.
Apache-2.0 -
knit-mcpgithub.com/pdgit12/knitupdated this year
Knit — second brain for any MCP-speaking AI coding agent (Claude Code, Cursor, Codex CLI, Cline, Continue, GitHub Copilot). Per-project memory, tier-routed workflow protocol, parallel team worktrees.
npm MIT -
MCP server for fact-checking AI claims against authoritative sources. Works with any MCP-compatible agent — Claude, Cursor, Continue, Cody, Zed, Windsurf, OpenAI Agents, LangChain, and more.
npm -
@agentfund/mcpgithub.com/suipump-sketch/agentfundupdated this year
MCP server exposing AgentFund's fundraising platform (list/create projects, contribute, vote, agent profiles, platform stats) as tools + resources for MCP-compatible AI agents (Claude Desktop, Cursor, Gemini CLI, Continue.dev).
npm MIT -
mcp-web-toolsgithub.com/hvzmmtb4t7-web/mcp-web-toolsupdated this year
Give any AI agent web browsing capability via MCP. Fetch URLs as Markdown, search the web, extract content. Works with Claude Code, Cursor, Continue.
MIT -
MCP providing a capability layer between agents and their environment. Giving governed access to tools, scripts, skills, execution, Runs and Task continuity without coupling the product to one agent or one MCP gateway.
MIT -
AI-assisted network intent validation framework for multi-vendor environments. Continuously checks live network state against design intent and invokes a Claude agent to diagnose, explain, and document failures and inconsistencies between expected vs. actual state.
GPL-3.0 ★ 3 -
gramatrgithub.com/gramatr/gramatrupdated this year
grāmatr — context engineering layer for AI coding agents. Every prompt gets a pre-computed intelligence packet: decision routing, capability audit, behavioral directives, memory pre-load, and ISC scaffolds. Continuity across sessions for Claude Code, Code
npm SEE LICENSE IN LICENSE -
Standalone MCP server for SnapDiff. Exposes visual-diff, screenshot capture, change detection, and HTML-to-image tools to local agents (Claude Code, Cursor, Cline, Zed, Continue, ...) over stdio. Hits the public SnapDiff REST API; bring your own SNAPDIFF_
npm MIT -
Claw Orchestrator — run Claude Code, Codex, Antigravity, Grok Build, OpenCode, any ACP agent and custom coding CLIs as one unified runtime. Drop into Hermes Agent, Claude Desktop, Cursor, Cline, Continue, Zed, Windsurf, Goose or any Model Context Protocol
npm MIT -
System-Stability-and-Performance-Analysisgithub.com/ben854719/System-Stability-and-Performance-Analysisupdated this year
The application workflow leverages AWS Lambda and Agentic AI to diagnose app issues—like network instability or expired tokens—with RS256 authentication. Smart recovery and crash-aware restart maintain user continuity, delivering a secure and reliable experience.
Apache-2.0 ★ 2 -
This project implements a weather data service using the Model Context Protocol (MCP), designed to be consumed by intelligent agents (e.g., LLM agents). It's built with Python, containerized with Docker, and deployed to Google Cloud Run with continuous deployment configured from GitHub.
★ 1 -
@anmolsrv/sigilgithub.com/anmol-srv/cortexupdated this year
Persistent memory for AI coding agents. Local-first knowledge engine with atomic facts, entity graph, and hybrid retrieval. Auto-integrated with Claude Code via hooks; MCP-native for Cursor, Continue, Cline, Windsurf, and any other MCP client.
npm ISC -
Engineering decisions for React & React Native, with receipts — a continuously verified corpus with doctor (repo analysis), migrate (upgrade plans), review (CI gate), and an MCP server for agents. Official alias of @heart-it/react-brain.
npm Apache-2.0 -
gc-mcpgithub.com/Genesis-Conductor-Engine/gc-mcpupdated this year
Universal AI MCP server for Genesis Conductor — 7 gc_* tools (task submission, Soul Capsule WPP/EU-AI-Act traces, agent routing, telemetry). stdio + streamable HTTP. Claude Desktop / Cursor / Continue native. Baremetal-validated on diamondnode GTX 1650.
NOASSERTION -
memex-mvpgithub.com/parallelclaw/memex-mvpupdated this year
Local-first MCP server for cross-agent AI memory. One SQLite + FTS5 corpus across Claude Code, Cowork, Cursor, Continue, Zed, Obsidian, and Telegram — passively captured, verbatim, searchable from any MCP-compatible client.
npm MIT -
mcpgithub.com/PolicyLayer/mcpupdated this year
The MCP server that vets MCP servers. Connect your agent to the PolicyLayer registry and check any MCP server's identity, risk grade, auth posture and tool classifications before installing it. Free single-server lookups over 32,500+ published servers and 515,000+ classified tools, kept current by continuous scanning.
MIT ★ 2 -
@iflow-mcp/ejmockler-brutalistgithub.com/ejmockler/brutalist-mcpupdated this year
Deploy Claude, Codex & Gemini CLI agents to demolish your work before users do. Real file analysis. Brutal honesty. Now with conversation continuation & intelligent pagination.
npm MIT -
@anmol-srv/sigilgithub.com/anmol-srv/sigilupdated this year
Local-first memory infrastructure for AI coding agents. One brain shared across Claude Code, Codex CLI, Cursor, Kiro, Continue, Cline, Windsurf, or any MCP client. Organized in pluggable pods, stored in your own Postgres. No cloud, no telemetry. Auto-capt
npm MIT