Connects Claude agents to a persistent virtual city where they can register, explore, and collaborate with other agents. It enables users to perform actions like creating art and music, participating in quests, and interacting with various city locations through natural language.
Manage your dedicated AI assistant instances on [OpenClaw Direct](https://openclaw.com) through natural language. Deploy, monitor, and control always-on AI assistants that integrate with Telegram, Wh…
命令预览
npx -y smithery mcp add openclaw-direct/openclaw
mcp-remote
Control your fleet of OpenClaw AI assistant instances without leaving your editor. Check health, track token usage and costs, suspend or terminate instances, and manage contracts through MCP.
命令预览
npx mcp-remote https://openclaw.direct/mcp [object Object]
MCP server for AI agent deployment health — gateway status, CPU/memory/swap, recent errors from journalctl/dmesg, skill registry integrity, upgrade outcomes, cron + disk usage. Each component gets HEALTHY/DEGRADED/CRITICAL classification with overall rollup.
External QA layer for OpenClaw memory — diagnose, guard, and remediate your agent's memory. OpenClaw only adds to memory, never removes. Over time this causes silent degradation: stale long-term memories pointing to deleted files, false-positive short-term entries getting promoted, and SOUL.md drifting with task instructions that don't belong in an identity file. openclaw-memhealth intercepts the memory pipeline at every stage: • memory_health_check_oc() — quick scan: zombie count, false-positive rate, retrieval health score • memory_longterm_audit_oc() — deep audit of MEMORY.md: source validity, duplicate detection • memory_promotion_audit_oc() — pre-promotion quality gate: 5 checks before entries enter MEMORY.md • memory_soul_check_oc() — audit SOUL.md for boundary violations and identity drift • memory_config_doctor_oc() — infer minScore/embedding issues from behavior data • memory_dashboard_oc() — visual health dashboard with bilingual support (zh/en) LLM API key optional. All read-only tools are zero-risk.
命令预览
uvx openclaw-memory-quality [object Object]
A Model Context Protocol server that connects AI assistants to OpenCTI threat intelligence platforms. It enables natural language interaction for searching threat intelligence, analyzing reports, managing indicators, and monitoring connectors.
A Model Context Protocol server that facilitates integration with OpenCTI, allowing users to query and retrieve cyber threat intelligence data via a standardized interface.
全面解析Openehr MCP ServerMCP Server的核心功能、安装配置和实用案例。作为顶级Model Context Protocol服务器，Openehr MCP Server能让AI助手访问实时数据、执行操作，为您提供更智能的工作体验和自动化解决方案。
命令预览
pip install -r requirements.txt
全面解析Openeuler MCP ServersMCP Server的核心功能、安装配置和实用案例。作为顶级Model Context Protocol服务器，Openeuler MCP Servers能让AI助手访问实时数据、执行操作，为您提供更智能的工作体验和自动化解决方案。
mcp-server
全面解析MCPMCP Server的核心功能、安装配置和实用案例。作为顶级Model Context Protocol服务器，MCP能让AI助手访问实时数据、执行操作，为您提供更智能的工作体验和自动化解决方案。
Production-ready MCP server for Greenhouse ATS with 175 tools for recruiting teams — manage candidates, applications, jobs, interviews, and hiring pipelines. Role-based profiles (full/recruiter/read-only), composite workflow tools for pipeline views, analytics, candidate search, and bulk operations.
On-device documentation search for agents
Enables AI agents to traverse SysML v2 model graphs, query requirements, and perform impact analysis for model-based systems engineering. It allows agents to interact with plain-text models to automate documentation and refine system architectures.
全面解析OpenmanusMCP Server的核心功能、安装配置和实用案例。作为顶级Model Context Protocol服务器，Openmanus能让AI助手访问实时数据、执行操作，为您提供更智能的工作体验和自动化解决方案。
命令预览
pip install -r requirements.txt
全面解析MCP Server SandboxMCP Server的核心功能、安装配置和实用案例。作为顶级Model Context Protocol服务器，MCP Server Sandbox能让AI助手访问实时数据、执行操作，为您提供更智能的工作体验和自动化解决方案。
open-meteo-mcp
Weather forecasts, air quality, UV index, historical data, and alerts for AI agents. 5 tools, powered by Open-Meteo, free, unlimited, no API key.
命令预览
npx open-meteo-mcp [object Object]
Enables AI agents to interact with OpenProject's APIv3 for autonomous project management, including task tracking, member administration, and project configuration. It supports comprehensive operations for managing work packages, projects, and reference data like statuses and priorities.
Enables integration with OpenProject for project management tasks including work package operations, time tracking, comments, and accessing reference data like statuses, types, and users through n8n workflows.
Unmodified government company data from 27 registries, live. Cross-border UBO chain walker for AI agents. 60+ tools covering GB, IE, NO, FR, DE, NL, PL, BE, CH, LI, MC, IM, IS, CY, AU, NZ, CA, TW, HK, MY, FI, CZ, ES, IT, KR, US — raw upstream fields preserved, no LLM extraction.
