Precogly MCP
MCP server for Precogly threat modeling, enabling users to integrate threat modeling capabilities into AI assistants.
README
Precogly MCP
MCP server for Precogly threat modeling.
Status
Early. One tool, read-only:
list_threat_models— threat models in the caller's organizations, most recently updated first. Returns the first page of twenty and cannot page past it.
Authentication is not finished. The server forwards a bearer token it does not own and never mints; today that token is a Precogly access token with a 60-minute lifetime, which is fine for development and cannot drive anything unattended. 0003 records what replaces it and why.
Configuration
Two environment variables, both read by the server process:
PRECOGLY_TOKEN |
Bearer token for the Precogly API. Required. |
PRECOGLY_URL |
Base URL of the deployment. Defaults to http://localhost:8000. |
Against a locally seeded instance, a token comes from the login endpoint:
export PRECOGLY_URL=http://localhost:8000
export PRECOGLY_TOKEN=$(curl -s -X POST "$PRECOGLY_URL/api/auth/login/" \
-H 'Content-Type: application/json' \
-d '{"email":"admin@precogly.dev","password":"admin123"}' \
| python3 -c "import sys,json;print(json.load(sys.stdin)['access'])")
Running it
The server speaks stdio. Either entry point works:
uv run precogly-mcp # console script
uv run python -m precogly_mcp.server # equivalent
Under the MCP Inspector, for poking at schemas by hand. --with-editable . is required —
mcp dev runs the file in an ephemeral environment containing only mcp, so without it
nothing in this package imports:
uv run mcp dev src/precogly_mcp/server.py --with-editable .
Connecting a client
Any MCP client that can launch a local stdio server. For opencode,
an opencode.json in the project root, with the token interpolated rather than written in:
{
"mcp": {
"precogly": {
"type": "local",
"command": ["uv", "run", "python", "-m", "precogly_mcp.server"],
"enabled": true,
"environment": {
"PRECOGLY_TOKEN": "{env:PRECOGLY_TOKEN}",
"PRECOGLY_URL": "{env:PRECOGLY_URL}"
}
}
}
}
Development
This project uses uv for dependencies and tooling.
uv sync # create .venv and install deps + dev tools
uv run pytest # run tests
uv run ruff check . # lint
uv run ruff format . # format
uv run mypy src # type-check (strict)
uv run pip-audit # scan dependencies for CVEs
Install the git hooks once:
uv run pre-commit install
Tests need no running Precogly. mcp.client.Client drives the server over in-memory
streams, so tools/list and tools/call are exercised as a client sees them, and
httpx2.MockTransport stands in for the API.
Design
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。