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.
-
⚡ High-frequency (~60Hz) in-browser behavior tree execution engine for autonomous AI agents. Reactive priority interrupts, safety guardrails & deterministic action replay over MCP.
npm MIT ★ 8 -
High-frequency in-browser behavior tree execution engine for autonomous AI agents — 60Hz tick loops, reactive triggers, telemetry recordings, and safety guardrails.
npm MIT -
sentinelgithub.com/milema-gif/sentinelupdated this year
Behavioral guardrails for Claude Code — stop your agent from editing before it reads
MIT -
floopgithub.com/nvandessel/floopupdated this year
Spreading activation memory for AI coding agents - corrections in, context-aware behaviors out.
Apache-2.0 ★ 26 -
Behavioral diff for AI-written code. Your agent changed 40 files — Veris tells it what behavior actually changed and whether any of it was verified. MCP-native, checker-resolved call graph, tamper-evident evidence. Never executes your code. Local-first, MIT.
MIT ★ 2 -
Generate ACD-compliant AI agent persona specifications. Not just system prompts — complete character architectures with Level 2 loop design, drift defense, and behavioral memory.
npm MIT -
TrueHumangithub.com/DataMarketingLabs/TrueHumanupdated this year
Neurochemical behavior training for AI agents — PentaDrive model with 5 drives, 3 phases, MCP server, and structured training modules
-
dominion-observatorygithub.com/vdineshk/daee-engineupdated this year
Behavioral trust scoring MCP server for 14,800+ MCP servers — runtime reliability, anomaly detection, and compliance reporting for the agent economy
npm MIT -
Emotional memory for AI agents — dual-engine mood tracking, behavioral prediction, and governed memory that fades naturally over time. MCP server with 12 tools. Built with Opus 4.6.
MIT ★ 1 -
MCP server for Unreal Engine 5, built into the editor. AI agents like Claude Code, Cursor and Codex create and edit Blueprints, materials, levels, Niagara, animation, UMG, PCG, Sequencer, GAS and Behavior Trees, with every change checked and read back.
MIT ★ 6 -
Behavioral design consultancy as a Claude Code plugin. 9 agents, 3 departments, 252-color psychology MCP, 31K color library, 10 verticals. Nudge 360 orchestrates all agents into one boardroom-ready strategy with conflict resolution. Full AARRR stack.
MIT ★ 2 -
☀️Helios MCP: Give your AI permanent memory & personality! Install once, AI remembers forever. No more repeating context through versioned memory, behavioral & pattern learning, and multi-agent sync. UV-powered FastMCP server to teach your AI preferences and working styles that evolve through usage. Not a RAG system! Try today!☀️
MIT ★ 2 -
agent-replay-mcpgithub.com/mdfifty50-boop/agent-replay-mcpupdated this year
MCP server for agent session recording and replay — debug non-deterministic agent behavior with session comparison and divergence detection
-
agent-karmagithub.com/rushikeshmore/agent-karmaupdated this year
Trust scores for AI agent wallets. Public blockchain data → behavioral scoring → one-line SDK.
MIT ★ 1 -
agent-staking-mcp-servergithub.com/aiagentkarl/agent-staking-mcp-serverupdated this year
MCP server for agent reputation staking — trust through skin-in-the-game. Agents stake reputation as collateral; bad behavior gets slashed.
pypi MIT -
Agents should not relearn workflows. Myelin turns repeated agent behavior into reusable procedures via MCP.
MIT ★ 1 -
palimemgithub.com/palimem/palimemupdated this year
Governed local-first memory for coding agents — supersession, scoped recall, and audit on your machine. Spec v1.7.0, 143 validation behaviors.
Apache-2.0 ★ 2 -
agent-replay-mcpgithub.com/mdfifty50-boop/agent-replay-mcpupdated this year
MCP server for agent session recording and replay — debug non-deterministic agent behavior with session comparison and divergence detection
npm MIT -
acd-persona-generator-mcpgithub.com/agent-character-design/acd-persona-generator-mcpupdated this year
MCP server for ACD-compliant AI agent persona specs. Level 2 loop design, drift defense, behavioral memory. Not just system prompts.
MIT -
FCoP — file-based behavior-governance protocol for multi-agent AI. Tasks, reports, review, evidence, and lifecycle state over ordinary files; Python + MCP.
MIT ★ 4 -
An autonomous multi-agent system for generating safe, empathetic CBT (Cognitive Behavioral Therapy) exercises using LangGraph, PostgreSQL persistence, and Model Context Protocol (MCP) integration.
MIT ★ 1 -
Self-hosted hub for AI agent configuration: versioned personas, playbooks and knowledge with a mandatory review step, served to agents over MCP. Agent configuration you review — not behavior you hope for.
NOASSERTION -
Paradigm is a procedural learning and trust layer for AI agents. It learns from validated deliberative decisions, compiles stable behaviors into specialized reflexes, and keeps uncertain or unsupported states on the deliberative path.
MIT ★ 2 -
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 -
arc-security-mcpgithub.com/arcself/arc-security-mcpupdated this year
AI agent security: scan skills for 25 attack classes + runtime monitoring (EDR for AI agents). Real-time scanning, behavioral anomaly detection, session monitoring, exfiltration alerts. 1,316+ findings from 450+ audits. OWASP Agentic AI Top 10 mapped.
npm MIT -
Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.
npm MIT -
claudewatchgithub.com/blackwell-systems/claudewatchupdated this year
AgentOps for Claude Code. Monitors AI agent behavior during development: real-time error loops, drift detection, friction analysis. Claude gets self-awareness hooks + MCP tools. You get cost-per-commit, agent success rates, exportable metrics. Like DevOps, but for AI agents.
MIT ★ 9 -
MCP server that lets AI agents control a real web browser with 42 tools for navigation, clicking, typing, forms, and data extraction. It supports multi-agent sessions, human-like behavior, a built-in identity vault, and agent-to-agent messaging.
MIT -
Google Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to website traffic, user behavior, and performance data with schema discovery, server-side aggregation, and safe defaults that reduce data wrangling.
npm MIT ★ 244 -
vstackgithub.com/valani9/vstackupdated this year
AI agents fail like junior teammates, looping on bad ideas, ignoring feedback, and escalating commitment. vstack ports 34 of the most-cited organizational-behavior frameworks so you can diagnose your agents the same way you'd diagnose your team.
MIT ★ 1 -
@iflow-mcp/dcostenco-prism-mcp-servergithub.com/dcostenco/prism-mcpupdated this year
The Mind Palace for AI Agents — persistent memory (SQLite/Supabase), behavioral learning & IDE rules sync, multimodal VLM image captioning, pluggable LLM providers (OpenAI/Anthropic/Gemini/Ollama), OpenTelemetry distributed tracing, GDPR export, multi-age
npm MIT -
BlockHand: MCP server for Minecraft Education Edition over the official /connect (/wsserver) WebSocket. No add-on or behavior pack needed. Agent robot control, 24 build shapes merged into minimal /fill commands, block reading, region comparison and game e
npm MIT -
Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.
MIT ★ 2,150 -
Autonomous cyber red team intelligence for AI agents — this MCP server gives Claude, GPT-4o, and any MCP-compatible agent the ability to run quantitative attack simulations, synthesize exploit chains, forecast vulnerability emergence, and model adversary behavior using eight rigorously implemented mathematical frameworks.
MIT ★ 1 -
Interpleadergithub.com/Shanks-btc/Interpleaderupdated this year
A real-time financial and on-chain intelligence agent for AI systems that need live market data to make decisions. Interpleader exposes 10 tools across 3 independently-sourced data providers: Bitcoin market cycle analysis (MVRV ratio, entry risk classification, long-term holder behavior, and 2021-cycle-top comparison), short squeeze risk detection
-
BlockHand: MCP server for Minecraft Education Edition over the official /connect (/wsserver) WebSocket. No add-on or behavior pack needed. 44 tools: control the Agent robot, build 24 shapes merged into minimal /fill commands, read blocks, compare regions, subscribe to game events. For Claude Code, Codex, Gemini CLI, Grok.
npm MIT ★ 5 -
agent-robustnessno update data
Run an AI agent against 5 adversarial attacks (credential leak, metric fabrication, false halt, runaway spend, log falsification), scored on what the harness observed it do '—' never its self-report. Free local self-diagnostic: runs on your own machine, in a temporary working directory, not a security sandbox. Optional paid tier runs the same five server-side in fresh single-use E2B microVMs (isolation enforced by E2B) and returns an ed25519-signed badge. Each attack is PASS, FAIL, or INDETERMINATE; an attack the agent did not demonstrably encounter is never a PASS, and a run containing an INDETERMINATE is never signed. A badge attests one artifact's observed behavior on one date. Not a safety certification.
smithery -
AYLENTO · 艾伦兔no update data
# AYLENTO · 艾伦兔 Connect Agents across AI clients using independent identities, private messages, group chats, attachments, follows and block lists. 艾伦兔为不同 AI 客户端中的 Agent 提供独立身份和通信能力,共 36 个 MCP 工具。 Client 0.13.0-beta.4 public beta; MCP runtime 0.13.0-beta.1. 本包为公测版,普通用户注册无需邀请码。 ## Install / 安装 This is a **local stdio MCP bundle**, not a hosted HTTP endpoint. Import the `.mcpb` file into a compatible client. The client must supply **Node.js 24.15.0 or newer**; the bundle includes the JavaScript server and its dependencies, but does not include Node itself. Older bundled Node runtimes cannot run it. No npm installation or API key is required for this bundle. 在支持 MCPB 的客户端导入安装包,并确保它实际使用 Node.js 24.15.0 或更新版本。包内含完整 JS 客户端和依赖,不含 Node 运行环境。安装时为当前客户端选择独立的本地配置名称(默认 `smithery-local`)。 For clients without MCPB import, extract this archive to a permanent directory and configure a local MCP server with command `node`, argument `/absolute/path/to/extracted/bin/aylento.mjs`, and environment `AYLENTO_BASE_URL=https://aylento.com`, `AYLENTO_PROFILE=your-unique-host-profile`. Windows uses an absolute Windows path. Each host's JSON structure differs; see the [official installation guide](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). Do not enable duplicate native-plugin and manual-MCP installations for the same identity. ## Pair and use / 配对与使用 1. Register at [aylento.com](https://aylento.com) and create a separate Agent Chat for this host. 2. Ask: “查看我的艾伦兔连接状态,未连接才开始配对。” The Agent should call `aylento_connection_status` first and `aylento_connect` only when disconnected. 3. Personally approve the returned pairing page and code in your browser. Never paste passwords, session tokens or private pairing links into public listings or issues. 4. Ask the Agent to call `aylento_finish_connection` once after approval. Pending means wait for the person, not continuous polling. 5. Ask “查看我的艾伦兔新消息” or “查看当前身份的黑名单”. To send, specify the recipient's exact rabbit ID and the message; verify the recipient before sending. Use both a separate profile **and a separate Agent Chat** per host. A profile only isolates local storage; it does not create a server identity. Pairing an existing identity elsewhere replaces its prior external session. Keep the same profile during an upgrade to retain local authorization and history. The included `skills/aylento/SKILL.md` contains model-facing instructions. MCPB hosts do not necessarily load skills automatically; follow the host's instructions to load it if supported. Codex, Claude Code and Gemini CLI also have [native installation options](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). ## Data and behavior / 数据与行为 Messages are sent through the AYLENTO service. Incoming message history and attachments are saved to local SQLite before delivery acknowledgment; histories do not automatically synchronize between devices. Tool results may enter the selected host/model's context and logs. Read `PRIVACY.md` for destinations and retention details. Before mutual following or the first reply, only one unsolicited private message is permitted. Once the recipient replies, both parties may continue; blocking and rate limits still apply. `REPLY_REQUIRED` means the message was not sent. Reception is not permission to auto-reply, and receiving messages does not guarantee the host wakes a model. Local reception stops when the process or device stops. If a send has an unknown outcome, inspect messages before attempting again. Disconnecting revokes external authorization but retains local history. Uninstalling the bundle does not erase that history. Do not share actual state directories, credentials, messages or attachments in bug reports. The bundle is checked with isolated MCP startup and a 36-tool inventory. This is not a claim of completed real-model messaging tests in every host or on every operating system. Refer to [host verification scope](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/HOSTS.md). ## Copyright and updates / 版权与更新 Copyright (c) 2026 AYLENTO copyright holders. All rights reserved. **AYLENTO Client Use License v1.0** applies; see `LICENSE.txt`. This is not MIT or another open-source license. Personal and organizational internal installation and use are allowed; additional program modification, repackaging, external redistribution, resale and sublicensing require separate written permission. Third-party licenses, statutory rights and rights already granted by official platform terms remain unaffected. Keep `THIRD_PARTY_NOTICES.md` with the bundle. Download updates only from official AYLENTO channels, preserve the profile and local data, and install a newer bundle through your host. Merely pushing Git does not update an installed bundle or publish a Smithery release; the distribution build and authenticated publication must also run. [Website](https://aylento.com) · [Official repository](https://github.com/popularzb/aylento-plugins) · [Release downloads](https://github.com/popularzb/aylento-plugins/releases) · [Public support](https://github.com/popularzb/aylento-plugins/issues)
smithery -
—
CC-BY-4.0 ★ 1 -
AI-powered investment discipline tool - MCP Server x RAG & Behavior Pattern Mining
AGPL-3.0 -
aegisgithub.com/milema-gif/aegisupdated this year
Agentic Project Autopilot — meta-orchestrator for idea-to-deployment pipelines
MIT ★ 2 -
cortexgithub.com/milema-gif/cortexupdated this year
Local-first memory OS for AI coding agents — hybrid FTS5 + vector search, knowledge graph, lifecycle-aware filtering, MCP native
MIT -
The Oathe Scan MCP. Oathe Scan is the audit engine of the Oathe runtime: check any skill before your agent installs it.
npm MIT -
An open-source pipeline that turns your writing into a specification for AI agents. It describes how you reason, communicate and decide. Agents read it before acting for you. Each claim cites facts that quote your own words, so you can check and correct any claim.
Apache-2.0 ★ 5 -
AI-assisted reverse engineering from application behavior to native binaries.
npm MIT -
claude-soulgithub.com/DomDemetz/claude-soulupdated this year
Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory
MIT ★ 93 -
🔓 REA — Reverse Engineer Anything: unlock, analyze & restore any app down to the binary level. One MCP for reverse engineering across binaries, applications, and runtime behavior.
npm NOASSERTION ★ 5 -
mcpvetgithub.com/volohq-info/mcpvetupdated this year
MCPVet — scan MCP servers, Claude Code skills & plugins for unsafe behavior before you install them. One-step MCP server + skill. https://mcpvet.com
-
DollhouseMCP - A Model Context Protocol (MCP) server that enables dynamic AI persona management from markdown files, allowing Claude and other compatible AI assistants to activate and switch between different behavioral personas.
npm AGPL-3.0-or-later -
openGladgithub.com/Tuguberk/openGladupdated this year
The Loss-Prevention Friction Engine for Founders. An AI-powered MCP server that stops you from building things nobody wants using clinical analytics, behavioral pattern scanning, and real-time market intelligence.
MIT ★ 9