QueryWeaver
An MCP server for Text2SQL: transforms natural language into SQL using graph schema understanding.
Run isolated code and manage apps, databases and deployments on Lizard (lizard.build).
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(employ-woman-g1q2.us-east-1.onlizard.com) · ✓ 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
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Lizard MCPhttps://employ-woman-g1q2.us-east-1.onlizard.com/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
+ConnectorsLizard MCP
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
Plugins+Add custom MCP server
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
Lizard MCPhttps://employ-woman-g1q2.us-east-1.onlizard.com/mcp开启新聊天,输入前先从插件列表中选择 Lizard MCP
用 Lizard MCP 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 Lizard MCP,或回答中出现 Lizard MCP 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
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user lizard https://employ-woman-g1q2.us-east-1.onlizard.com/mcp应能看到 Lizard MCP 在列表中并显示已连接
用 Lizard MCP 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 Lizard MCP,或回答中出现 Lizard MCP 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
用 Lizard MCP 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 Lizard MCP,或回答中出现 Lizard MCP 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
用 Lizard MCP 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 Lizard MCP,或回答中出现 Lizard MCP 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://employ-woman-g1q2.us-east-1.onlizard.com/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user lizard https://employ-woman-g1q2.us-east-1.onlizard.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"lizard": {
"url": "https://employ-woman-g1q2.us-east-1.onlizard.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"lizard": {
"type": "http",
"url": "https://employ-woman-g1q2.us-east-1.onlizard.com/mcp"
}
}
}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。
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
服务器要求先登录,才会列出它的工具。
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15日
注册名称已通过 GitHub 账户 lizard-build 验证,该账户拥有此仓库
代码最后更新于4天前
使用 MIT
在 532 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
尚未检查;我们会在检查端点时读取工具列表
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
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 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。
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。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于4天前,最新版本(0.1.0)于30天前进入注册中心。
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)。
同一分类中有:QueryWeaver, Supabase, Neon, DBCode, Keboola MCP
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
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
An MCP server for Text2SQL: transforms natural language into SQL using graph schema understanding.
Official Neon MCP server for managing Neon projects and Lakebase Postgres databases.
Connect your AI assistants to Keboola and expose your data, transformations, SQL queries, ...
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。
An MCP server that lets ChatGPT, Claude and other MCP clients deploy and manage apps, run code in Lizard Sandboxes and work with Lizard Git repositories on Lizard (lizard.build).
Connect it once, then ask your assistant to ship a service, read logs, set secrets, scale replicas, attach a domain, run a script in a sandbox or open a pull request — in plain words.
The server speaks Streamable HTTP at POST /mcp, and stdio for clients that spawn a local process instead (below). A hosted instance runs at:
https://lizard.build/mcp
Every request carries a bearer token. A client that speaks OAuth gets one itself — the server advertises where, so there is nothing to paste. Clients that only send headers use a liz_ API key instead:
lizard keys create my-mcp-key
The dashboard creates the same thing under Sandboxes → Get started → New API key. Either way the key is shown once.
claude mcp add --transport http lizard https://lizard.build/mcp
Claude Code runs the OAuth flow on first use. To skip it and use a key:
claude mcp add --transport http lizard https://lizard.build/mcp \
--header "Authorization: Bearer liz_your_key"
Follow the Cline installation guide to connect the hosted server with a bearer token. Use Cline's streamableHttp transport, keep tool approval on, then check the connection with whoami. No local build is needed.
{
"mcpServers": { "lizard": { "url": "https://lizard.build/mcp", "headers": { "Authorization": "Bearer liz_your_key" } } } }
ChatGPT connects to a URL and runs OAuth itself — no key to paste. It needs developer mode and a registered connection; see Publishing to Codex / ChatGPT below.
Run it as described in the next section, then use http://localhost:3000/mcp in place of the hosted URL.
curl -sS -X POST https://lizard.build/mcp \
-H "Authorization: Bearer liz_your_key" \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Without a token the same call returns 401 and a WWW-Authenticate header pointing at the OAuth metadata. That is the server working, not failing.
npm install
npm run build npm start
For development with reload:
npm run dev
npm start serves HTTP. To have a client spawn the server instead, point it at dist/stdio.js:
{
"mcpServers": { "lizard": { "command": "node", "args": ["/path/to/lizard-mcp/dist/stdio.js"], "env": { "LIZARD_TOKEN": "liz_your_key" } } } }
A spawned process has no browser to run OAuth in, so the token comes from the environment and binds the process to one user. Without it the server still starts and lists its tools — calling one then returns a message asking for a key.
| Variable | Default | What it does |
|---|---|---|
PORT | 3000 | Port to listen on (HTTP only) |
PUBLIC_URL | http://localhost:$PORT | The URL clients reach this server on. Sets the OAuth resource identifier, so it must match the real address in production. |
PLATFORM_URL | https://lizard.build | The Lizard API this server talks to |
LIZARD_TOKEN | — | API key for stdio mode, where there is no OAuth handshake. LIZARD_API_KEY works too. |
The standalone HTTP server also serves /mcp/sandboxes. This profile includes sandbox creation, files, code execution, pause and resume, snapshots, forks and port access, plus account, project, region, limits and billing reads. It excludes CI, DNS, support, schedules and other platform tools. New tools stay out of this profile until its allowlist includes them. Excluded tools cannot be called by name.
Use the same server origin with /mcp/sandboxes as the client URL. It has its own OAuth resource metadata. /mcp and stdio still provide the full tool set. In-process hosts can select the same profile with getServer(token, { profile: "sandboxes" }); they must add the HTTP route and OAuth resource metadata themselves. Deploying this package alone does not add a route to an in-process host.
This profile needs a Lizard workspace and project with permission to use Sandboxes. It does not need CI access or an owned domain. Cloud usage still incurs charges. It can attach an existing volume by ID, but cannot list or create volumes.
| Area | Tools |
|---|---|
| Account | whoami, workspace_list, workspace_create, workspace_delete, project_list, project_create, project_delete, project_pause, project_resume, workspace_pause, workspace_resume, region_list, billing_status, billing_summary |
| Workspace limits | workspace_limits_get, workspace_limits_set, workspace_resale_pricing_get, workspace_resale_pricing_set |
| Services | service_list, service_show, service_create, service_set, service_rename, service_delete, service_pause, service_resume, service_sleep_status, service_sleep_set, service_scale, service_get_port, service_set_port, addon_create |
| Deploys | deploy_redeploy, deploy_restart, deploy_events |
| Functions | functions_deploy, functions_invoke, functions_logs, functions_list |
| Templates | template_list, template_show, template_deploy |
| Logs and metrics | logs_tail, metrics_get |
| Secrets | secrets_list, secrets_set, secrets_delete, secrets_refs |
| Domains | domain_attach, domain_verify, domain_delete, domain_owned_list, domain_dns_list, domain_dns_update |
| Volumes | volume_list, volume_create, volume_resize, volume_delete |
| GitHub connection | git_connect, git_checkout, git_status |
| Lizard Git | repo_list, repo_create, repo_show, repo_delete, repo_files, repo_read_file, repo_commit, repo_commits, pr_list, pr_create, pr_show, pr_merge, ci_run_list, ci_run_show |
| Sandboxes | sandbox_list, sandbox_show, sandbox_create, sandbox_exec, sandbox_read_file, sandbox_write_file, sandbox_list_files, sandbox_delete, sandbox_set_timeout, sandbox_pause, sandbox_resume, sandbox_snapshot, sandbox_snapshot_list, sandbox_snapshot_delete, sandbox_fork, sandbox_expose_port, sandbox_unexpose_port, sandbox_schedule, sandbox_schedule_list, sandbox_schedule_update, sandbox_schedule_run, sandbox_schedule_runs, sandbox_schedule_delete |
| Config as code | config_apply |
| Support | support, support_list, support_show, support_reply |
Tool names use snake_case (not the MCP spec's permitted dots) to match OpenAI's function-name pattern ^[a-zA-Z0-9_-]{1,64}$, which some ChatGPT/Codex surfaces enforce directly.
Every tool includes a title in both title and annotations.title. Read tools set readOnlyHint: true; all write tools set destructiveHint: true so clients can ask before changing resources. Shell access to app services is unavailable, so the server exposes no service-shell tool. Use sandbox_exec to run commands in Lizard Sandboxes.
Destructive tools — project_delete, workspace_delete, service_delete, secrets_delete, domain_delete, volume_delete, sandbox_delete, sandbox_snapshot_delete, repo_delete, and domain_dns_update with remove — require an explicit confirmation argument, so a client cannot delete anything or run arbitrary commands by accident.
project_delete puts the project's services and databases in trash for 3 days, but deletes its sandboxes, their volumes and snapshots at once.
billing_status is read-only: it shows the plan (Pro at $19/month with $19 of usage included each month, Pro 5x at $99 with $99, Pro 20x at $499 with $499, the trial, prepaid credits until November 1, 2026, or enterprise), the tier and the Billing link. Starting, changing tier, paying for and cancelling Pro happen in the browser. When the account has to pay before it can create something, the tool error gives the platform's sentence with the page to open on its last line, and structuredContent.error carries the code (PAYMENT_REQUIRED), paymentStatus and the links.
test/parity/cli-coverage.json maps every Lizard CLI command to the tools that cover it, or says why none does. The main gaps, on purpose:
lizard up and other commands that read local files: a remote server never sees them. Deploy from a GitHub or Lizard Git repo instead, or commit files with repo_commit.lizard keys), payments (lizard billing changes), agent credentials (lizard agents): they handle secrets or money and belong in the browser or a terminal.Bought domains: an API key can read their DNS records but not change them. Changes (domain_dns_update, domain_attach on a bought domain) need a client connected with OAuth.
repo_*, pr_* and ci_* reach Lizard Git (lizard.build/git) with the caller's own token, as Authorization: Bearer. Lizard Git refuses API keys with scopes. Every commit is made on the server with repo_commit; there is no clone. To deploy a repository, call service_create with repoUrl set to lizard:owner/name. LIZARD_GIT_URL points the server at another Lizard Git (default /git).
Lizard (lizard.build) provides Lizard Sandboxes for short-lived code execution. These resources are separate from app services. Start with project_list, then call sandbox_create with the chosen project and confirm: true. Keep the returned sandboxId for later calls.
{"name":"sandbox_create","arguments":{"project":"YOUR_PROJECT_ID","lifetimeMs":300000,"confirm":true}}
Use sandbox_write_file to write a script, sandbox_exec to run it, and sandbox_read_file to read its results. Finish with sandbox_delete. Create, execute, write, and delete need the user's approval before the client sets confirm: true. The MCP server does not open a confirmation dialog.
Sandboxes use the interpreter template and size small unless template and size say otherwise, with /workspace as the default path. Sizes are mini (1 vCPU / 2 GB; only the base, claude, codex and interpreter templates, no volume), small (2 vCPU / 4 GB), medium (4 vCPU / 8 GB) and large (8 vCPU / 16 GB). The trial runs 1 Small and 2 Mini at a time (US regions only); Medium and Large unlock after the first payment. They expire after five minutes by default; lifetimeMs accepts 60,000–86,400,000 milliseconds (a day), and sandbox_set_timeout changes it later. On the trial a sandbox lives 1 hour at most, then it is deleted: a longer lifetime fails with TRIAL_SANDBOX_LIFETIME, and sandbox_set_timeout cannot extend it past 1 hour from its creation. Expiry or deletion loses all files except those on an attached volume. Creation uses billed cloud resources. Host files, environment variables, and access tokens stay out of the sandbox.
sandbox_pause saves memory, processes and files and stops the sandbox; sandbox_resume continues it. sandbox_snapshot saves a running sandbox to start new ones from in the same project (sandbox_create with snapshotId), and sandbox_fork starts live copies. sandbox_expose_port gives a port an HTTPS URL that carries its access token (other clients send it as X-Lizard-Access-Token). Pause, resume and snapshot wait up to two minutes for the platfor