Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Abnormal Security MCP: threats, search, remediation, ATO cases, vendor/BEC, and evidence download.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
ABNORMAL_API_TOKEN, ABNORMAL_BASE_URL, ABNORMAL_ALLOW_RESPONSE, ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD, ABNORMAL_MAX_EVIDENCE_BYTES标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"abnormal": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ABNORMAL_API_TOKEN",
"-e",
"ABNORMAL_BASE_URL",
"-e",
"ABNORMAL_ALLOW_RESPONSE",
"-e",
"ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD",
"-e",
"ABNORMAL_MAX_EVIDENCE_BYTES",
"ghcr.io/gregdog/mcp-server-abnormal:v1.1.0",
"serve"
],
"env": {
"ABNORMAL_API_TOKEN": "your-value",
"ABNORMAL_BASE_URL": "your-value",
"ABNORMAL_ALLOW_RESPONSE": "your-value",
"ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD": "your-value",
"ABNORMAL_MAX_EVIDENCE_BYTES": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add abnormal --env ABNORMAL_API_TOKEN=your-value --env ABNORMAL_BASE_URL=your-value --env ABNORMAL_ALLOW_RESPONSE=your-value --env ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD=your-value --env ABNORMAL_MAX_EVIDENCE_BYTES=your-value -- docker run -i --rm -e ABNORMAL_API_TOKEN -e ABNORMAL_BASE_URL -e ABNORMAL_ALLOW_RESPONSE -e ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD -e ABNORMAL_MAX_EVIDENCE_BYTES ghcr.io/gregdog/mcp-server-abnormal:v1.1.0 serve运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"abnormal": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ABNORMAL_API_TOKEN",
"-e",
"ABNORMAL_BASE_URL",
"-e",
"ABNORMAL_ALLOW_RESPONSE",
"-e",
"ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD",
"-e",
"ABNORMAL_MAX_EVIDENCE_BYTES",
"ghcr.io/gregdog/mcp-server-abnormal:v1.1.0",
"serve"
],
"env": {
"ABNORMAL_API_TOKEN": "your-value",
"ABNORMAL_BASE_URL": "your-value",
"ABNORMAL_ALLOW_RESPONSE": "your-value",
"ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD": "your-value",
"ABNORMAL_MAX_EVIDENCE_BYTES": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"abnormal": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ABNORMAL_API_TOKEN",
"-e",
"ABNORMAL_BASE_URL",
"-e",
"ABNORMAL_ALLOW_RESPONSE",
"-e",
"ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD",
"-e",
"ABNORMAL_MAX_EVIDENCE_BYTES",
"ghcr.io/gregdog/mcp-server-abnormal:v1.1.0",
"serve"
],
"env": {
"ABNORMAL_API_TOKEN": "your-value",
"ABNORMAL_BASE_URL": "your-value",
"ABNORMAL_ALLOW_RESPONSE": "your-value",
"ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD": "your-value",
"ABNORMAL_MAX_EVIDENCE_BYTES": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
ABNORMAL_BASE_URL envABNORMAL_ALLOW_RESPONSE envABNORMAL_ALLOW_EVIDENCE_DOWNLOAD envABNORMAL_MAX_EVIDENCE_BYTES env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 GregDog 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:ABNORMAL_API_TOKEN
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.1.0)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Docker。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A secure, open-source Model Context Protocol server for Abnormal Security.
This project is not an official Abnormal product and is not endorsed by Abnormal AI.
abnormal-mcp lets MCP clients such as Cursor and Claude Desktop query Abnormal Security over stdio (default) or Streamable HTTP. It uses a lightweight handwritten client against the Abnormal Security Client API.
MCP Client
→ Abnormal MCP Server (stdio or HTTP) → Abnormal REST API
The server is read-only by default. Response and evidence download tools are opt-in and independent. Abnormal authorization still applies to every request.
Read (always on)
abnormal_threat_action_get)since, sender, sender_domain, recipient, subject, url, attachment, sender_ip, judgement)Response (opt-in: `ABNORMAL_ALLOW_RESPONSE=true`)
delete, move_to_inbox) with confirm: true preview gateconfirm: true preview gateconfirm: true preview gateconfirm: true preview gateEvidence download (opt-in: `ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD=true`)
cloud_message_id)io.github.GregDog/mcp-server-abnormal)Create an Abnormal REST API token in the Abnormal portal under Integrations → Abnormal REST API.
export ABNORMAL_API_TOKEN="your-token"
abnormal-mcp serve
git clone https://github.com/GregDog/mcp-server-abnormal.git
cd mcp-server-abnormal make build
docker run --rm -i \
-e ABNORMAL_API_TOKEN \ ghcr.io/gregdog/mcp-server-abnormal serve
See examples/cursor.mcp.json.
See examples/claude-desktop.json.
27 read tools are always registered. With ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD=true, five evidence tools are added (32 total). With ABNORMAL_ALLOW_RESPONSE=true, four response tools are added (31 total, or 36 with both gates enabled).
| Area | Tools |
|---|---|
| Threats | abnormal_threats_list, abnormal_threat_get, abnormal_threat_action_get, abnormal_threat_links_list, abnormal_threat_attachments_list |
| Search | abnormal_search_messages, abnormal_search_activities_list, abnormal_search_activity_get |
| Messages | abnormal_message_remediation_history |
| Mailbox | abnormal_mailbox_campaigns_list, abnormal_mailbox_campaign_get, abnormal_mailbox_unanalyzed_list |
| Employees | abnormal_employee_get, abnormal_employee_identity_get, abnormal_employee_logins_list |
| ATO cases | abnormal_cases_list, abnormal_case_get, abnormal_case_analysis_get, abnormal_case_action_get |
| Vendors | abnormal_vendors_list, abnormal_vendor_get, abnormal_vendor_activity_list, abnormal_vendor_cases_list, abnormal_vendor_case_get |
| Detection 360 | abnormal_detection360_reports_list |
| URL rewrite | abnormal_url_rewrite_clicks_list |
| Audit logs | abnormal_audit_logs_list |
| Evidence (opt-in) | abnormal_message_eml_get, abnormal_search_message_eml_get, abnormal_message_attachment_get, abnormal_message_attachment_download, abnormal_search_attachment_download |
| Response (opt-in) | abnormal_search_remediate, abnormal_threat_remediate, abnormal_case_update, abnormal_detection360_report_submit |
See docs/tools.md for parameters.
| Variable | Default | Purpose |
|---|---|---|
ABNORMAL_API_TOKEN | (required) | Bearer token |
ABNORMAL_BASE_URL | https://api.abnormalplatform.com/v1 | API base URL |
ABNORMAL_ALLOW_RESPONSE | false | Enable response tools (Phase 2+) |
ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD | false | Enable evidence download (Phase 5+) |
ABNORMAL_MCP_TRANSPORT | stdio | stdio or http |
Full list: docs/configuration.md.
Read tools are always on. Response and evidence tools require explicit opt-in.
Local use only: this server has no built-in authentication or RBAC. Use stdio (default) or loopback HTTP on the same machine. Do not expose the HTTP endpoint on a network without your own access controls.
See docs/security.md and SECURITY.md.
make check
make test-access # optional live API smoke test make test-phase34 # Phase 3/4 live smoke test make test-phase5 # Phase 5 evidence smoke test (requires ABNORMAL_ALLOW_EVIDENCE_DOWNLOAD)
See docs/development.md.
Apache-2.0. See LICENSE.