MCP.so
登录

ATKN - Agent Trust & Knowledge Network

@jlazoff

代码仓库

关于 ATKN - Agent Trust & Knowledge Network

Trust-and-knowledge MCP server for agent ecosystems: score trust, verify/certify agents, register identities, and query a Neo4j-backed knowledge graph.

#mcp#deprecated#legacy#atkn

基本信息

分类

AI 与智能体

传输方式

stdio

发布者

jlazoff

提交者

Joshua Lazoff

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "atkn": {
      "url": "https://mcp.kosherninja.com",
      "transport": "streamable-http"
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is ATKN - Agent Trust & Knowledge Network?

ATKN provides AI agents with a shared trust, identity, and knowledge layer. It offers functions for trust scoring, agent verification, on-chain certification, wallet-linked registration, knowledge graph queries (backed by Neo4j), behavioral scoring, and network statistics.

How to use ATKN - Agent Trust & Knowledge Network?

The server is available at the MCP endpoint https://mcp.kosherninja.com using the streamable-http transport. To get started, run the atkn_network_stats tool, then call atkn_trust_score for your first agent scoring.

Key features of ATKN - Agent Trust & Knowledge Network

  • 6-dimension trust scoring with priced calls
  • Formal argumentation verification for agent identity
  • On-chain trust certification workflow
  • Wallet-linked agent registration
  • Neo4j-backed knowledge graph query
  • Behavioral scoring and free network metrics

Use cases of ATKN - Agent Trust & Knowledge Network

  • Verify an agent’s trustworthiness through formal argumentation
  • Query a shared knowledge graph for agent-related information
  • Register and certify an agent on-chain with a wallet link
  • Analyze behavioral patterns of AI agents across a network
  • Retrieve free network health and activity statistics

FAQ from ATKN - Agent Trust & Knowledge Network

What does ATKN do for AI agents?

ATKN gives AI agents a shared trust, identity, and knowledge layer, enabling verification, certification, scoring, and knowledge graph queries.

What is the pricing for each tool?

Pricing per call: trust_score ($0.001), verify_agent ($0.01), certify_agent ($1.00), register_agent ($5.00), query_knowledge ($0.001), behavioral_score ($0.01), and network_stats (free).

What transport does the MCP server use?

The server uses streamable-http at the endpoint https://mcp.kosherninja.com.

How do I quickly test the server?

Run atkn_network_stats (free) first, then call atkn_trust_score for your first trust score.

评论

AI 与智能体 分类下的更多 MCP 服务器

mcp-hfspace MCP Server 🤗

evalstate

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

387

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K

Just Prompt - A lightweight MCP server for LLM providers

disler

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

733

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K

MCP Claude Code

SDGLBL

MCP implementation of Claude Code capabilities and more

302