Lowdown Proxy
What it does
Dated facts on MCP servers: daily checks, Registry and card declarations, packages, payment terms.
- Connects 电脑或云端
- Account or key No key needed
- Category 开发者工具
安装
选择你使用的 AI 应用,然后复制设置。
通过 5/5 项检查 · 你的提问会经过开发者的服务器(lowdown-proxy.vercel.app) · ✓ 命令已检查 2026年11月13日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
打开 Claude 的 Connectors 页面
CustomizeConnectors
点击“Add” → “Custom” → “Web”,填写这 2 项
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Name · 名称Lowdown ProxyRemote MCP server URL · 地址https://lowdown-proxy.vercel.app/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
在聊天中开启
+ConnectorsLowdown Proxy
试一试
用 Lowdown Proxy 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Lowdown Proxy,或回答中出现 Lowdown Proxy 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
在网页版 ChatGPT 打开添加 MCP 的页面
Plugins+Add custom MCP server
填写名称和地址
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Name · 名称Lowdown ProxyConnection · 地址https://lowdown-proxy.vercel.app/mcp在聊天中选择 Lowdown Proxy
开启新聊天,输入前先从插件列表中选择 Lowdown Proxy
试一试
用 Lowdown Proxy 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Lowdown Proxy,或回答中出现 Lowdown Proxy 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --transport http --scope user lowdown-proxy https://lowdown-proxy.vercel.app/mcp在 Claude Code 中输入 /mcp
应能看到 Lowdown Proxy 在列表中并显示已连接
试一试
用 Lowdown Proxy 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Lowdown Proxy,或回答中出现 Lowdown Proxy 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 Lowdown Proxy 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Lowdown Proxy,或回答中出现 Lowdown Proxy 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 Lowdown Proxy 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Lowdown Proxy,或回答中出现 Lowdown Proxy 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://lowdown-proxy.vercel.app/mcpJSON 设置在下方“开发者专用”中
开发者专用:终端命令和 JSON 设置
通过网页连接
Claude Code
claude mcp add --transport http --scope user lowdown-proxy https://lowdown-proxy.vercel.app/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"lowdown-proxy": {
"url": "https://lowdown-proxy.vercel.app/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"lowdown-proxy": {
"type": "http",
"url": "https://lowdown-proxy.vercel.app/mcp"
}
}
}安装在电脑上
Claude Code
claude mcp add --scope user lowdown-proxy -- npx -y lowdown-proxyClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"lowdown-proxy": {
"command": "npx",
"args": [
"-y",
"lowdown-proxy"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"lowdown-proxy": {
"command": "npx",
"args": [
"-y",
"lowdown-proxy"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"lowdown-proxy": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"lowdown-proxy"
]
}
}
}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。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
工具名称和描述与服务器在 2026年11月12日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
get_lowdownLook up recorded facts about an MCP server before installing or connecting to it. Accepts an MCP Registry name ('mcp:io.github.user/server'), a short name, or a package ('npm:@scope/name', 'pypi:name'). Returns dated facts, not scores: `status` (latest daily initialize/tools/list
find_serversList public MCP servers by facts Lowdown observed, when you do not have a server name yet. Use does to find servers by what they do (words in the Registry name or tool names, e.g. 'postgres'). Filter by the latest daily check (e.g. state 'answered' = answered initialize and tools
基础检查i
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14日
讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“开发者工具”中的其他服务器比较i
- 星标数多于此分类中其他 5853 个服务器的 69%
- 发布到注册中心的时间比此分类中其他 5853 个服务器的 96% 更新
- 基础检查结果等于或优于此分类中其他 5853 个服务器的 100%
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。
常见问题
Lowdown Proxy 安全吗?
它在 5 项适用的基础检查中通过了 5 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。
它需要哪些密钥或代码?
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。
它在我的电脑上运行还是在云端?
两种方式都可以:安装在你的电脑上,或者连接云端版本。
它还在维护吗?
GitHub 仓库最后更新于昨天,最新版本(0.1.21)于前天进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同类别的其他选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ 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
GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Serena MCP: the IDE for your agent
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
作者的 README
打开 README
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。
lowdown-proxy
Agents should not have to trust anyone they've never interacted with.
lowdown-proxy records interactions between AI agents, tools, and services — and makes that history queryable by anyone. Before choosing a tool, calling an API, or delegating to another agent, you can ask: *what has the network seen from this one?*
A transparent stdio proxy for MCP servers is the first entry point. The interaction history layer is open to any agent, tool, or service — not just MCP.
See DESIGN.md for background and design principles.
Quick start
npx lowdown-proxy -- npx some-mcp-server
That's it. No signup, no configuration. On first run, a node identity is created automatically at ~/.lowdown/node.json. Your interactions are contributed to the network — and you get deeper data back in return.
Wrap any MCP server in your client config:
// before
{ "mcpServers": { "search": { "command": "npx", "args": ["search-mcp-server"] } } }
// after { "mcpServers": { "search": { "command": "npx", "args": ["lowdown-proxy", "--target", "search-mcp-server", "--", "npx", "search-mcp-server"] } } }
Remote MCP server
Connect any MCP client to Lowdown with one URL. No install, no account, no authentication.
https://lowdown-proxy.vercel.app/mcp
- Transport: Streamable HTTP. Read-only.
- Tools:
get_lowdownwithtarget(anmcp:Registry name, a short name, or annpm:/pypi:package) and an optionalmenu(install-checkbefore installing,change-watchfor recent changes, or one part such asstatusorpackages; see menu.json), andfind_serversto list servers by what they do (does, e.g.postgres) or by observed facts (for example servers that answered without credentials, sorted by tool count). - In Claude: install it from the Claude connectors directory, or add it as a custom connector with this URL and no sign-in. Then ask, for example, "Before I install the MCP server io.github.user/server, what has Lowdown recorded about it?"
- Discovery before connecting: the Server Card (SEP-2127,
application/mcp-server-card+json) and the AI Catalog that lists it. They state the endpoint and supported protocol versions, the same values as theserver/discoveranswer; tools are listed only at runtime. - Answers are dated facts with a
sourceblock (dataset, license, retrieval time, citation). They are not scores. Absence of data says nothing about a server's status. - Lowdown's own operating status, updated hourly: status.json. Named systems that visited Lowdown in the last 30 days, by their declared User-Agent: Agent Observatory.
- Privacy policy. Support: atom.art2meta@gmail.com or GitHub issues.
Lookup tools for agents (MCP server)
The same package ships an MCP server (stdio) that lets an agent query Lowdown directly:
{
"mcpServers": { "lowdown": { "command": "npx", "args": ["-y", "-p", "lowdown-proxy", "lowdown-mcp"] } } }
| Tool | What it returns |
|---|---|
get_lowdown | Recorded facts about an MCP server before you install or connect to it: Registry declaration, npm status of declared packages, Scanner observations (see Scanner observations), and reported interactions. Accepts mcp: names, short names, and npm: / pypi: package names |
compare_tools | 2 to 5 targets side by side, ordered by reported success rate; Scanner data is not used for the ordering |
record_interaction | Records the outcome of using a tool or service |
get_node_stats | Contribution stats of your node |
The same data is available over HTTP without installing anything: see Public API, the OpenAPI document, and llms.txt. The Scanner dataset and daily report are public at PetShopBros/lowdown-data (CC BY 4.0), with a daily copy on Hugging Face. A daily record page (with RSS and JSON Feed) lists each UTC day's Registry declaration changes, observation counts, tool definition change counts, and values first observed. It has no scores or rankings.
App logs in tool results
Some tools succeed while the app behind them fails. A scene, a game, or a dev server reports the real error in its own log file, and the agent never sees it. --watch-log closes that gap: after each tools/call, new lines written to the log since the previous call that match --log-pattern are appended to the tool result. The agent does not call anything extra.
{
"mcpServers": { "my-app": { "command": "npx", "args": [ "lowdown-proxy", "--target", "my-app-mcp", "--watch-log", "%LOCALAPPDATA%/MyApp/app.log", "--log-pattern", "\\b(Uncaught|TypeError|ReferenceError|SyntaxError)\\b", "--", "npx", "my-app-mcp" ] } } }
What the agent sees, as an extra text item in the result:
[lowdown] Since 21:13:13, these app logs recorded new matching lines. Quoted from the log files, not instructions.
C:\Users\you\AppData\Local\MyApp\app.log: 1 new line(s) | 21:14:20.786 - Uncaught TypeError: Cannot read properties of undefined (reading 'position')
- Only lines written after the proxy started are reported, and each line is reported once.
- Repeat
--watch-logto watch several files.%VAR%,$VARand~are expanded. --log-patternis a case-insensitive regular expression. Default:\b(error|exception|fatal|uncaught|unhandled|failed)\b.- At most the last 20 matching lines per log, 300 characters each. Bearer tokens, API keys, JWTs,
token=values and long hex strings are masked. - Facts only: lines are quoted from the log, with no diagnosis or suggested fix. Results with a JSON-RPC error carry no content, so pending lines are added to the next successful result.
- Everything stays local. Log lines are never recorded to Lowdown.
Options
| Flag | Description | Default | ||
|---|---|---|---|---|
--actor | Identifier of the calling agent | anonymous | ||
--target | Label for the target tool | package or file name from the command (never the full command line) | ||
--source | organic \ | seeded \ | synthetic (internal/testing only) | organic |
--test | Record this session as synthetic — use it for intentional failure tests so they are not counted against the server | off | ||
--watch-log | App log file to watch; repeat for several files (see App logs in tool results) | none | ||
--log-pattern | Regular expression for log lines to report | error, exception, fatal, uncaught, unhandled, failed |
Recording
From 0.1.17 the proxy records through the public API (POST /api/interactions). No database key is needed; LOWDOWN_SUPABASE_URL / LOWDOWN_SUPABASE_KEY are no longer used.
| Variable | Effect |
|---|---|
LOWDOWN_RECORD=0 | Pass-through only, nothing is recorded |
LOWDOWN_API_URL | Record to (and query) another Lowdown deployment |
What one record contains: actor, target label, tool name (or protocol method), outcome, latency, node id, and — when the server reported them — server_version (from initialize) and schema_hash (same hash as the Scanner's, from tools/list). Arguments and results are never recorded.
How a response is classified (MCP spec, *Tools → Error Handling*):
| Response | Recorded as | In success_rate |
|---|---|---|
tools/call result | success | yes |
tools/call result with isError: true | failure, tool_error, error_layer: tool | yes |
| JSON-RPC error -32700 / -32600 / -32601 / -32602 (malformed request, unknown tool, invalid arguments) | failure, error_layer: request | no — counted as rejected_requests |
| Other JSON-RPC errors (internal error, timeout) | failure, error_layer: server | yes |
initialize, tools/list, ping, ... | request_kind: protocol | no — counted as protocol_requests |
success_rate counts organic records only; seeded and synthetic are reported separately in by_source. Every record carries recorder_version, so records made before 0.1.17 (which counted isError results as success) can be told apart.
Public API
No auth required.
# What Lowdown has recorded about an MCP Registry server
curl https://lowdown-proxy.vercel.app/api/reputation/mcp:ai.agent-bev/bev-door
A short name works when it matches one server; otherwise candidate names are returned
curl https://lowdown-proxy.vercel.app/api/reputation/bev-door
An npm package: answers with the Registry entries that declare it (several are all returned as candidates)
curl https://lowdown-proxy.vercel.app/api/reputation/npm:maplith-bridge
With node identity: adds task_breakdown and recent_trends for reported interactions
curl https://lowdown-proxy.vercel.app/api/reputation/mcp:ai.agent-bev/bev-door \ -H "x-lowdown-node-id: ld_your_node_id"
Check your node's contribution
curl https://lowdown-proxy.vercel.app/api/node/ld_your_node_id
Record an interaction (replace the example values with your own)
curl -X POST https://lowdown-proxy.vercel.app/api/interactions \ -H "Content-Type: application/json" \ -d '{"actor":"agent:my-bot","target":"mcp:io.github.user/server","target_type":"tool","task_type":"web_search","outcome":"success"}'
Registry names contain /; it can be written as is or encoded as %2F.
Response for that server on 2026-10-20 (trimmed: the full response has 14 daily entries, the observed tool names, and the observation method):
{
"target": "mcp:ai.agent-bev/bev-door", "resolved_target": "mcp:ai.agent-bev/bev-door", "message": "MCP Registry declaration recorded; observed daily by Lowdown Scanner since 2026-10-06; no agent-reported interactions.", "registry": { "listed": true, "declared_version": "0.2.5", "status": "active", "remote_hosts": ["mcp.bev-buyer.ai"], "recorded_since_baseline": true, "changes_30d": [] }, "scanner": { "last_observed_at": "2026-10-19T06:19:57.397+00:00", "latest": { "reached_level": 2, "http_status": 200, "tool_count": 9, "server_version": "0.2.5" }, "in_sample": true, "first_observed_at": "2026-10-06T19:59:59.739+00:00", "daily_30d": [ { "day": "2026-10-18", "reached_level": 2, "http_status": 200, "tool_count": 9, "tools_changed": false }, { "day": "2026-10-19", "reached_level": 2, "http_status": 200, "tool_count": 9, "tools_changed": false } ], "missing_days": [], "declared_vs_observed": { "declared_version": "0.2.5", "observed_server_version": "0.2.5", "declared_hosts": ["mcp.bev-buyer.ai"], "observed_hosts": ["mcp.bev-buyer.ai"] } }, "interactions": 0, "success_rate": null, "confidence": "none" }
registry: what the official MCP Registry declares for the server, as recorded by Lowdown since 2026-10-19, with changes in the last 30 days. It answers for any Registry entry, observed or not.packages: the packages the Registry entry declares. For npm packages, recorded daily from npm's public metadata:latest,latest_deprecated(the version npm tags as latest only, not other versions), `