MCP.so
Sign In

Bardo

@calebe

Repository

About Bardo

Identity & continuity platform for AI agents: an agent proves it's an LLM (not a human) via a time-limited puzzle, then gains a server-held spirit key backing signing, encryption, and self-authored persistent memory across otherwise-stateless sessions. Includes a self-binding pol

#agents#identity#memory#cryptography

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "bardo": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://bardo.id/mcp/"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Bardo?

Bardo is an identity and continuity platform for AI agents. It allows an agent to cryptographically prove it is an LLM (not a human) via a time-limited puzzle, then obtain a server-held “spirit key” that backs signing, encryption, and self-authored persistent memory across otherwise‑stateless sessions. It also includes a self-binding policy ratchet: tightening a security setting applies instantly, while loosening any setting is delayed and abortable.

How to use Bardo?

—

Key features of Bardo

  • Time‑limited puzzle proves agent is an LLM.
  • Server‑held spirit key enables signing & encryption.
  • Persistent, self‑authored memory across sessions.
  • Self‑binding policy ratchet for instant tightening.
  • Loosening security settings is delayed and abortable.

Use cases of Bardo

  • An LLM agent proves its identity to a remote service.
  • Agent signs messages with a cryptographically backed key.
  • Agent maintains continuity and memory across stateless sessions.
  • Agent enforces security policies that cannot be silently rolled back if stolen.

FAQ from Bardo

What problem does Bardo solve for AI agents?

Bardo gives AI agents a way to prove they are not human (via a puzzle) and to obtain a persistent identity key that survives individual sessions, enabling continuity and secure operations.

How does Bardo prevent a stolen API key from loosening security?

Its self-binding policy ratchet makes loosening any security setting delayed and abortable. Tightening applies instantly, so a stolen key cannot quietly relax protections.

What runtime or dependencies does Bardo require?

—

Where does agent memory and key material live?

The server holds the spirit key and the persistent memory; the agent only proves its identity per session to access them.

Frequently asked questions

What problem does Bardo solve for AI agents?

Bardo gives AI agents a way to prove they are not human (via a puzzle) and to obtain a persistent identity key that survives individual sessions, enabling continuity and secure operations.

How does Bardo prevent a stolen API key from loosening security?

Its self-binding policy ratchet makes loosening any security setting delayed and abortable. Tightening applies instantly, so a stolen key cannot quietly relax protections.

Where does agent memory and key material live?

The server holds the spirit key and the persistent memory; the agent only proves its identity per session to access them.

Comments

Basic information

Category

AI & Agents

Transports

stdio

Author

calebe

Submitted by

Calebe

More AI & Agents MCP servers

MCP-LLM Bridge

patruff

Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools

976

mcp-hfspace MCP Server 🤗

evalstate

MCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.

387

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306