OpenTTT-MCP
MCP Server for OpenTTT — Proof of Time tools for AI agents AI Agent A and Agent B both trigger a payment at the same time. Who was first? OpenTTT answers this with cryptographic Proof of Time — synthesized from multiple independent time sources, verified through GRG integrity shards, and signed with Ed25519 for non-repudiation.
README
@helm-protocol/ttt-mcp
Reference implementation of draft-helmprotocol-tttps-00 (IETF Experimental)
MCP Server for OpenTTT — Proof of Time tools for AI agents
AI Agent A and Agent B both trigger a payment at the same time. Who was first?
OpenTTT answers this with cryptographic Proof of Time — synthesized from multiple independent time sources, verified through GRG integrity shards, and signed with Ed25519 for non-repudiation.
Quick Start
npm install @helm-protocol/ttt-mcp
// claude_desktop_config.json
{
"mcpServers": {
"ttt": {
"command": "npx",
"args": ["@helm-protocol/ttt-mcp"]
}
}
}
That's it. Your AI agent now has access to 5 Proof of Time tools.
Tools
| Tool | Description |
|---|---|
pot_generate |
Generate a Proof of Time for a transaction |
pot_verify |
Verify a Proof of Time using its hash and GRG shards |
pot_query |
Query PoT history from local log and on-chain subgraph |
pot_stats |
Get turbo/full mode statistics for a time period |
pot_health |
Check system health: time sources, subgraph sync, uptime |
Tool Parameters
pot_generate
Generate a Proof of Time for a transaction. Returns potHash, timestamp, stratum, and GRG integrity shards.
| Parameter | Type | Required | Description |
|---|---|---|---|
| txHash | string | Yes | Transaction hash (hex with 0x prefix) |
| chainId | number | Yes | Chain ID (e.g. 8453 for Base, 84532 for Base Sepolia) |
| poolAddress | string | Yes | DEX pool contract address |
pot_verify
Verify a Proof of Time using its hash and GRG shards. Returns validity, mode (turbo/full), and timestamp.
| Parameter | Type | Required | Description |
|---|---|---|---|
| potHash | string | Yes | PoT hash to verify (hex with 0x prefix) |
| grgShards | string[] | Yes | Array of hex-encoded GRG integrity shards |
| chainId | number | Yes | EVM chain ID (e.g. 84532 for Base Sepolia) |
| poolAddress | string | Yes | Uniswap V4 pool address (0x-prefixed) |
pot_query
Query Proof of Time history from local log and on-chain subgraph.
| Parameter | Type | Required | Description |
|---|---|---|---|
| startTime | number | No | Start time (unix ms). Default: 24h ago |
| endTime | number | No | End time (unix ms). Default: now |
| limit | number | No | Max entries to return. Default: 100, max: 1000 |
pot_stats
Get PoT statistics: total swaps, turbo/full counts, and turbo ratio for a given period.
| Parameter | Type | Required | Description |
|---|---|---|---|
| period | "day" | "week" | "month" |
Yes | Time period for statistics |
pot_health
Check PoT system health: time source status, subgraph sync, server uptime, and current mode.
| Parameter | Type | Required | Description |
|---|---|---|---|
| (none) | — | — | This tool takes no parameters |
Example: Generate and Verify a PoT
// In your AI agent's tool call:
const pot = await pot_generate({
txHash: "0xabc123...",
chainId: 84532,
poolAddress: "0xdef456..."
});
// pot.potHash — unique Proof of Time hash
// pot.grgShards — GRG integrity shards for verification
// pot.timestamp — synthesized nanosecond timestamp
// pot.mode — "turbo" (honest) or "full" (requires full verification)
const verification = await pot_verify({
potHash: pot.potHash,
grgShards: pot.grgShards
});
// verification.valid — true if integrity shards reconstruct correctly
How It Works
- Time Synthesis — Queries multiple independent time sources (NIST, Google, Cloudflare) via HTTPS/NTP and synthesizes a median timestamp with uncertainty bounds
- GRG Pipeline — Encodes transaction data through a multi-layer integrity pipeline, producing verifiable shards
- Ed25519 Signing — Signs the PoT hash for non-repudiation
- Adaptive Mode — Honest builders get
turbomode (fast, profitable); tampered sequences getfullmode (slow, costly) — natural economic selection
Claude Desktop Configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ttt": {
"command": "npx",
"args": ["@helm-protocol/ttt-mcp"]
}
}
}
Config file locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Requirements
- Node.js >= 18
- Network access for time synthesis (HTTPS to time.nist.gov, time.google.com, time.cloudflare.com)
Learn More
- OpenTTT SDK — The underlying SDK
- IETF Draft: draft-helmprotocol-tttps-00 — TTTPS Protocol Specification
- Helm Protocol — GitHub
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。