mcp-agentcore
AI governance MCP server for EU AI Act compliance and jurisdiction verification
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"mcp-agentcore": {
"url": "https://geiant-agentcore-production.up.railway.app/mcp"
}
}
}远程端点
https://geiant-agentcore-production.up.railway.app/mcpstreamable-http它能做什么
工具清单
工具（3）
⚪verify_jurisdiction(h3_cell, facet, agent_pk)
Verify that an AI agent is authorized to operate in a specific H3 territorial cell. Checks the GNS-AIP delegation certificate: signature validity, temporal bounds, H3 cell authorization, and facet authorization. Returns a structured result indicating whether the agent may proceed.
输入模式
{
"type": "object",
"properties": {
"h3_cell": {
"type": "string",
"description": "H3 cell index representing the operation territory"
},
"facet": {
"type": "string",
"description": "Facet to check (e.g. \"energy@italy-geiant\")"
},
"agent_pk": {
"type": "string",
"description": "Agent Ed25519 public key (64 hex chars)"
}
},
"required": [
"h3_cell"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪generate_audit_proof(agent_pk, from, to)
Generate a EU AI Act Art. 12 (record-keeping) and Art. 14 (human oversight) compliance evidence bundle for an AI agent. Returns the cryptographic audit chain, Merkle epoch roots, delegation certificate, trust score, and violation history — sufficient for regulatory submission. The chain_verification.is_valid field proves the audit trail has not been tampered with.
输入模式
{
"type": "object",
"properties": {
"agent_pk": {
"type": "string",
"description": "Agent Ed25519 public key (64 hex chars)"
},
"from": {
"type": "string",
"description": "ISO 8601 start of reporting period"
},
"to": {
"type": "string",
"description": "ISO 8601 end of reporting period"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢check_delegation_chain(tool_name, agent_pk)
Verify the human → agent delegation chain and check whether a specific tool is whitelisted for this agent. Answers the regulatory question: "Did a real human authorize this AI action?" Returns the principal identity, delegation depth, cert validity, and tool authorization.
输入模式
{
"type": "object",
"properties": {
"tool_name": {
"type": "string",
"description": "Name of the tool the agent intends to call"
},
"agent_pk": {
"type": "string",
"description": "Agent Ed25519 public key (64 hex chars)"
}
},
"required": [
"tool_name"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据