跳过安装。2 分钟内即可运行。
在 cloud.anythingmcp.com 开始免费试用，一键添加 GLPI，然后将你的 AI 客户端（Claude、ChatGPT、Copilot 或 Cursor）指向生成的 MCP 端点。无需 Docker，无需 git clone，无需任何工程经验。
Summary
GLPI open-source ITSM and asset management: tickets, computers, monitors, software, users and entities, plus GLPI's search engine. REST API on your own instance, session-token auth with an App-Token.
试试这样问
GLPI 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → GLPI、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
GLPI + Cursor
GLPI open-source ITSM and asset management: tickets, computers, monitors, software, users and entities, plus GLPI's search engine. REST API on your own instance, session-token auth with an App-Token.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
GLPI_URL, GLPI_APP_TOKEN, GLPI_USER_TOKEN
步骤 1 — 获取凭证
GLPI needs two tokens, and both are easy to confuse.
- App-Token — identifies the application. In GLPI go to Setup → General → API, enable 'Enable Rest API' and 'Enable login with external token', add an API client, and copy its application token. Put it in
GLPI_APP_TOKEN. - User-Token — identifies the person. Open the GLPI user the agent should act as, go to the API tab of their profile, and regenerate the remote access key (personal API token). Put it in
GLPI_USER_TOKEN. - Set
GLPI_URLto the instance root (no trailing slash); the adapter appends/apirest.php.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
步骤 3 — 在 Cursor 中添加连接器
Cursor 从 ~/.cursor/mcp.json 读取 MCP 服务器。添加以下条目:
{
"mcpServers": {
"anythingmcp": {
"url": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key: Profile → MCP API Keys → New Key。
- 保存文件并重启 Cursor。
- 打开 Cursor → Settings → MCP 确认
GLPI已列出且为 "Connected" 状态。 - 开始对话 — 所有
GLPI工具均可调用。
可用工具
| Tool | What it does |
|---|---|
glpi_get_active_entities | Read the entities the logged-in user is currently scoped to |
glpi_list_tickets | List tickets in the active entity with their status, priority, category, requester and dates |
glpi_get_ticket | Read one ticket in full, with its description, status, urgency, impact, priority, requester, assignee and SLA dates |
glpi_get_ticket_followups | Read the follow-ups (the conversation) on one ticket, in order, with author, date and whether each is private |
glpi_search | Run a GLPI search with criteria |
glpi_list_search_options | Read the searchable field map for one item type: which field number means status, requester, serial number and so on |
glpi_list_computers | List computers from the asset inventory with their name, serial number, model, operating system and assigned user |
glpi_get_computer | Read one computer in full: hardware, OS, network interfaces, contracts, location and the user it is assigned to |
glpi_list_users | List GLPI users with their login, name, e-mail, entity and active flag, to resolve who a ticket or an asset belongs to |
glpi_list_software | List software items from the inventory with their publisher, category and the number of installations, for licence questions |
FAQ
Cursor 免费套餐支持自定义 MCP 服务器吗? 是的 — Hobby、Pro 和 Business 套餐均可用。
下一步
这份指南对你有帮助吗?
