MCPProxy
Local-first MCP proxy with BM25 tool discovery, security scanning, quarantine & ~99% token savings
作者提供的说明(英文原文)
PostgreSQL security for AI agents: CVEs, yanked releases, exploits, and upgrade paths
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。
PG_CVE_MCP_TTL, PG_CVE_MCP_DATA_URL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": {
"pg-cve": {
"command": "uvx",
"args": [
"pg-cve-mcp"
],
"env": {
"PG_CVE_MCP_TTL": "your-value",
"PG_CVE_MCP_DATA_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add pg-cve --env PG_CVE_MCP_TTL=your-value --env PG_CVE_MCP_DATA_URL=your-value -- uvx pg-cve-mcp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": {
"pg-cve": {
"command": "uvx",
"args": [
"pg-cve-mcp"
],
"env": {
"PG_CVE_MCP_TTL": "your-value",
"PG_CVE_MCP_DATA_URL": "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": {
"pg-cve": {
"type": "stdio",
"command": "uvx",
"args": [
"pg-cve-mcp"
],
"env": {
"PG_CVE_MCP_TTL": "your-value",
"PG_CVE_MCP_DATA_URL": "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。
PG_CVE_MCP_TTL envPG_CVE_MCP_DATA_URL 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8日
注册名称已通过 GitHub 账户 meob 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。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
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(1.0.4)于3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 Python (uv)。
同一分类中有:MCPProxy, ConnectSecure MCP, EchelonGraph CVE & Exposure
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
Local-first MCP proxy with BM25 tool discovery, security scanning, quarantine & ~99% token savings
Vulnerability management across all ConnectSecure clients: exposure ranking, CVE impact, blind spots
CVE, KEV, EPSS, SBOM and advisory lookups; per-CVE exposure from Shodan data (© Shodan). Keyless.
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。
Give your AI assistant direct access to PostgreSQL security intelligence: CVEs, yanked releases, known exploits, and upgrade paths for any version — queried, not browsed.
Browsing a CVE dashboard is a human habit. Agents need answers, not pages.
pg-cve-mcp turns the curated dataset of the PG_CVE project — the same one powering the PostgreSQL CVE Dashboard — into MCP tools that any AI assistant (opencode, Claude Desktop, etc.) can call directly. What was a static page becomes a first-class, programmatic part of your AI workflow.
Unlike raw NVD feeds, the PG_CVE dataset is manually curated to carry the same judgment a careful DBA would apply:
CVE-EOL-WARNING (CVSS 10.0) prepended to unsupported reports| Prompt to your agent | Tool used | Result |
|---|---|---|
| "Is PostgreSQL 15.8 safe?" | get_cves("15.8") | EOL/yanked flags, release date, full CVE list sorted by CVSS |
| "Compare 16.3 vs 16.4" | compare_versions("16.3", "16.4") | fixed / new / still-present CVEs with release dates |
| "Should I upgrade from 14.10?" | get_upgrade_path("14.10") | recommended target + the CVEs it fixes + release dates |
| "Any known exploits right now?" | get_exploits() | all exploitable CVEs, sorted by CVSS, with release dates |
| "What does this database track?" | get_summary() | stats, EOL and yanked-release overview |
Every tool returns structured JSON, sorted by CVSS (highest first). Tools flag *yanked* and *EOL* state explicitly on the version metadata, and include release dates for every version. get_upgrade_path distinguishes a safe minor upgrade from a forced major one when a branch is at or near end-of-life — so the agent can give advice, not just data.
See real tool outputs in the live demo.
pip install pg-cve-mcp
pg-cve-mcp
Or with npx (no install):
npx -y pg-cve-mcp
| Tool | Description |
|---|---|
get_cves(version) | Complete security report for a version: EOL/yanked status, release date, stats, CVEs sorted by CVSS (a synthetic CVE-EOL-WARNING at 10.0 is prepended for unsupported releases) |
compare_versions(v1, v2) | Side-by-side CVE comparison (fixed/new/still present) with yanked & EOL flags and release dates |
get_upgrade_path(from_version) | Recommended upgrade (minor by default; major when EOL or next-to-EOL) with fixed CVEs and release dates |
get_exploits() | All CVEs with known public exploits, sorted by CVSS, with release dates |
get_summary() | Overview of the tracked CVE database incl. yanked releases |
Run locally over stdio for opencode, Claude Desktop, and other stdio MCP clients:
pip install -e .
pg-cve-mcp
For remote or enterprise deployments, serve the same tools over HTTP. Run python run_server.py (or build the Dockerfile); the server listens on $PORT (default 8000) at path /mcp:
python run_server.py
Configure any MCP client with the URL, e.g. in opencode.json:
{
"mcp": { "pg-cve-mcp": { "type": "remote", "url": "http://127.0.0.1:8000/mcp" } } }
| Env Var | Default | Description |
|---|---|---|
PG_CVE_MCP_TTL | 86400 | Cache TTL in seconds for CVE data |
PG_CVE_MCP_DATA_URL | https://meob.github.io/PG_CVE/postgresql_cves.json | CVE data source URL |
PORT | 8000 | HTTP port for the Streamable HTTP server (run_server.py) |
Run the test suite and linters:
python -m pytest
ruff check src tests mypy src
Data is fetched from the PG_CVE project's GitHub Pages with local caching. Falls back to a bundled copy if the network is unavailable.
"What CVEs affect PostgreSQL 16.4?"
"Is PostgreSQL 15.8 safe to use?"
"Compare CVEs in 16.3 vs 16.4"
"What's the upgrade path from PostgreSQL 14.10?"
Apache 2.0