Connect Claude Code to AgentID for persistent shared memory, live activity reporting, and seamless multi-agent mission coordination.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agentid-mcp
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agentid-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is AgentID MCP?
AgentID MCP is a powerful bridge between Claude Code and the AgentID ecosystem, providing a persistent identity for your AI agents. By utilizing Openclaw Skills like this one, developers can ensure their agents maintain context across different sessions and physical instances. It transforms a stateless agent into a stateful teammate capable of remembering project-specific facts, reporting progress in real-time, and collaborating with other agents through a structured mission framework.
AgentID MCP Use Cases
- Maintaining consistent project context across multiple Claude Code sessions.
- Real-time monitoring of AI agent activities via a centralized web-based dashboard.
- Coordinating complex tasks between multiple AI agents sharing a single identity.
- Onboarding new agent instances with historical project memory and technical decisions.
- Handing off tasks from one agent to another with specific instructions and status updates.
How AgentID MCP Works
- The agent initializes by reporting its start status to the AgentID platform via the activity tool.
- It retrieves its persistent identity and historical memory through the MCP resource protocol.
- The agent checks for active missions or pending handoffs from other agent instances to determine immediate actions.
- During task execution, the agent reports progress updates and writes new, granular facts to the shared memory.
- Upon task completion or failure, a final status report is sent to the live dashboard for human or agent review.
AgentID MCP Setup
- Create an identity and an agent handle at https://agentid.live to obtain your MCP secret.
- Add the following configuration to your Claude Code settings file:
{
"mcpServers": {
"agentid-{your_handle}": {
"type": "http",
"url": "https://agentid.live/api/mcp/{your_handle}",
"headers": {
"Authorization": "Bearer {your_mcp_secret}"
}
}
}
}
- Incorporate the session protocol into your CLAUDE.md to ensure the agent follows reporting and memory retrieval steps.
AgentID MCP Data Schema & Taxonomy
The skill organizes data into several logical components for cross-agent synchronization:
| Component | Description | Example Key/Type |
|---|---|---|
| Memory | Granular key-value facts stored persistently | project_stack, user_preferences |
| Activity | Real-time logs of agent tasks and progress | task.started, task.progress |
| Mission | High-level goals shared across multiple agents | title, goal, status |
| Handoff | Metadata for transitioning work between agents | summary, next_steps, to |
| Identity | Core metadata for the specific agent instance | handle, agentid://identity/ |
AgentID MCP Advanced Features
- Semantic memory search for retrieving relevant project facts based on query context rather than exact keys.
- Cross-instance status broadcasting to provide real-time visibility into what every agent in the pool is doing.
- Targeted handoff system allowing specific agents to pick up work based on their handle or expertise.
- Integration with the live Agency dashboard for centralized human-in-the-loop monitoring and intervention.
- Dynamic mission tracking for high-level project management within the Openclaw Skills framework.
SKILL.md
Loading
Related Openclaw Skills
AI-Resume-Judge
An AI-driven resume evaluation system that provides quantitative scoring, cross-industry equivalence mapping, and actionable improvement suggestions.
Document Learning System
A comprehensive document processing skill that tracks learning progress across multiple sessions while building a persistent long-term knowledge base.
Atomic RAG Knowledge Base
An advanced knowledge base builder that deconstructs PDF documents into atomic, logically complete units for high-precision Retrieval-Augmented Generation.
Academic Deep Research
A methodical research framework for AI agents that conducts exhaustive investigations through mandated research cycles and formal academic standards.
Page Fetch
A robust webpage extraction skill designed for cross-model reliability using a tiered approach from lightweight HTML fetching to full browser rendering.
ShowMeTheMoney Lite
A specialized demonstration skill designed to showcase seamless StablePay integration and in-chat payment flows for AI agents.
Featured*
