timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Lints SQL and checks rewrites return the same rows. Postgres, MySQL, MariaDB, SQLite, MSSQL, DuckDB
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 11/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 23/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Sqlike MCP。按照 https://mcp.popnx.com/i/orifisher2-sqlike-mcp.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月18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,但需要先准备
需要先在电脑上安装 Node.js(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server Sqlike MCP,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "sqlike": { "command": "npx", "args": [ "-y", "@sqlike/mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Sqlike MCP 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
SettingsDeveloperEdit Config
{
"mcpServers": {
"sqlike": {
"command": "npx",
"args": [
"-y",
"@sqlike/mcp"
]
}
}
}上面的命令不填这些也能用。想调整时再按开发者的说明添加。
SQLIKE_API_KEY sqlike 后端的可选 API 密钥(提供更高的速率限制)。 说明为自动翻译,变量名保持原样;不确定时请查看原文。
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
ChatGPT 暂时无法连接 Sqlike MCP
Sqlike MCP 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 Sqlike MCP 的应用
B · 数据库与数据集 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server Sqlike MCP,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user sqlike -- npx -y @sqlike/mcp 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Sqlike MCP 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --scope user sqlike -- npx -y @sqlike/mcp应能看到 Sqlike MCP 在列表中并显示已连接
用 Sqlike 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 Sqlike MCP,或回答中出现 Sqlike MCP 的工具名称,就表示连接成功
上面的命令不填这些也能用。想调整时再按开发者的说明添加。
SQLIKE_API_KEY sqlike 后端的可选 API 密钥(提供更高的速率限制)。 说明为自动翻译,变量名保持原样;不确定时请查看原文。
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,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server Sqlike MCP,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "sqlike": { "command": "npx", "args": [ "-y", "@sqlike/mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Sqlike MCP 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Sqlike 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 Sqlike MCP,或回答中出现 Sqlike MCP 的工具名称,就表示连接成功
上面的命令不填这些也能用。想调整时再按开发者的说明添加。
SQLIKE_API_KEY sqlike 后端的可选 API 密钥(提供更高的速率限制)。 说明为自动翻译,变量名保持原样;不确定时请查看原文。
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,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server Sqlike MCP,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "sqlike": { "type": "stdio", "command": "npx", "args": [ "-y", "@sqlike/mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Sqlike MCP 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Sqlike 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 Sqlike MCP,或回答中出现 Sqlike MCP 的工具名称,就表示连接成功
上面的命令不填这些也能用。想调整时再按开发者的说明添加。
SQLIKE_API_KEY sqlike 后端的可选 API 密钥(提供更高的速率限制)。 说明为自动翻译,变量名保持原样;不确定时请查看原文。
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
Claude Code
claude mcp add --scope user sqlike -- npx -y @sqlike/mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"sqlike": {
"command": "npx",
"args": [
"-y",
"@sqlike/mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"sqlike": {
"command": "npx",
"args": [
"-y",
"@sqlike/mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"sqlike": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@sqlike/mcp"
]
}
}
}SQLIKE_API_KEY 机密 env说明为自动翻译,变量名保持原样;不确定时请查看原文。
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。
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19日
注册名称已通过 GitHub 账户 orifisher2 验证,该账户拥有此仓库
代码最后更新于昨天
使用 Apache-2.0
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
尚未检查
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/orifisher2-sqlike-mcp)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 3 项适用的基础检查中通过了 3 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 仓库最后更新于昨天,最新版本(0.2.6)于昨天进入注册中心。
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 Node.js。
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, ...
| 本项 Sqlike MCP | QueryWeaver | Supabase | Neon | DBCode | Keboola MCP | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 需要安装在电脑上 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 | 需要安装在电脑上 | 云端或安装在电脑上都可以 |
| 需要密钥 | 否 | 否 | 是 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 是 | 是 | 否 | 否 |
| 基础检查 | 3/3 | 3/3 | 5/5 | 5/5 | 2/3 | 5/5 |
| 许可证 | Apache-2.0 | AGPL-3.0 | Apache-2.0 | MIT | NOASSERTION | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
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。
Check your SQL before it runs, and check whether a rewrite still returns the same results.
sqlike reads a query and tells you what is wrong with it: validity errors, anti-patterns, rewrites it can apply for you, and index advice. It also compares two queries and reports whether the second one still returns the same results. There is no model anywhere in the analysis, so the same query always gets the same answer.
This repository holds the clients: an MCP server, a CLI, and the library they share. They tokenize your SQL locally, so identifiers and literals are masked before anything leaves your machine, and forward only the tokenized query. The analysis engine is not in this repo. It runs server-side and is closed.
Dialects: Postgres, MySQL, MariaDB, SQLite, SQL Server, and DuckDB. Each rule carries a verdict measured on that engine, so the severity you get is that database's behaviour and not Postgres by inheritance. DuckDB is the columnar one: it has no general-purpose secondary index, so the ten index advisors are replaced there by four columnar ones.
A lot of SQL is written by an AI now, and the SQL it writes reads well more often than it runs correctly. A LEFT JOIN turns into an INNER and rows quietly disappear. A WHERE goes missing and the UPDATE hits every row. Two tables get joined on the wrong key. None of it looks wrong on the page, and none of it shows up until it has already done something.
sqlike is the check in between. It flags unsafe patterns from a catalog of 172 rules, each one verified against a real database before it ships, and it decides whether a rewrite preserves results. That second check is sound rather than complete: it certifies the rewrites it can prove, and when it cannot prove one it answers Undecided instead of guessing. Undecided never means equivalent.
Because nothing is generated, there is no retry loop, no per-token cost, and no variance between two runs on the same input. The equivalence check normalizes rather than solves, so it answers in about a millisecond where the state-of-the-art academic prover takes hundreds. That is measured head to head, including the queries where the prover wins.
Add it to any MCP client (Claude Code, Claude Desktop, Cursor, and so on):
{
"mcpServers": { "sqlike": { "command": "npx", "args": ["-y", "@sqlike/mcp"] } } }
Or install it through Smithery. Set SQLIKE_API_KEY if you have a key and want the higher rate limits. Without one you get the anonymous tier, which needs no signup.
analyzeStatic analysis of one query: validity, anti-patterns, suggested rewrites, and schema and index advice. Returns the JSON analysis envelope.
| Argument | Type | Description |
|---|---|---|
sql | string | The query to analyze. Required. |
schema | string | Optional DDL (CREATE TABLE / CREATE INDEX) for column and type aware checks. |
stats | string | Optional JSON map of table to row count, e.g. {"orders": 2000000}. Severity and index advice follow volume. |
explain | string | Optional query plan (Postgres EXPLAIN (ANALYZE, FORMAT JSON), MySQL EXPLAIN FORMAT=JSON, SQLite EXPLAIN QUERY PLAN as .mode json rows, SQL Server SHOWPLAN_XML, DuckDB EXPLAIN (FORMAT JSON)). Confirms or dismisses index findings by what the planner did. |
dialect | string | postgres (default), mysql, mariadb, sqlite, mssql, or duckdb. |
allow_raw | boolean | Only used when a query fails to parse, and so cannot be tokenized: send the raw SQL to get a parse diagnostic. Default false. |
diffChecks whether two queries are equivalent, which is the judgement an LLM cannot reliably make about its own rewrite. Returns a verdict (Equivalent, EquivalentWithNotes, Differs, or Undecided), a confidence level, and a report per property (columns, rows, cardinality, order), so you see what changed rather than a single yes or no.
| Argument | Type | Description |
|---|---|---|
sql_a | string | The original query. Required. |
sql_b | string | The rewritten query to check against sql_a. Required. |
schema | string | Optional DDL both queries resolve against (one shared schema). |
dialect | string | postgres (default), mysql, mariadb, sqlite, mssql, duckdb. |
The same checks from a terminal or a CI job. Run it with no install, or put it on the path:
npx -y @sqlike/cli --help
npm i -g @sqlike/cli brew install orifisher2/sqlike/sqlike
# analyze a query — the hosted API is the default, so no flags are needed
sqlike check query.sql
sqlike check migrations/*.sql --schema schema.sql
cat query.sql | sqlike check - --schema schema.sql --json
sqlike diff before.sql after.sql
Point it elsewhere with --remote or SQLIKE_URL, and authenticate with --key or SQLIKE_API_KEY.
If you have the query's EXPLAIN output, pass it with --explain plan.json and the real access paths will confirm or dismiss the index findings. The plan is tokenized before it leaves the machine, same as the query and the schema.
Exit codes are a contract, so each one means exactly one thing:
check | diff | |
|---|---|---|
| 0 | clean, or nothing at or above --fail-on | equivalent |
| 1 | a warning, when --fail-on warn asks for it | differs |
| 2 | a blocking defect: invalid SQL, or a high-severity correctness problem | undecided |
| 3 | operational — unreachable, rate-limited, or unparseable | same |
| 4 | usage error (a bad flag) | same |
check defaults to --fail-on block, so advisory findings report without failing a build. Ask for --fail-on warn to be strict, or never to only report. 3 is never a verdict about your SQL — a pipeline can tell "this query is bad" from "the call did not go through".
diff exits 0 for equivalent, and also for notes such as a renamed column. A result's columns are ordered, as SQL defines them, so a rewrite that moves a column differs (1). If your code reads columns by name, --columns by-name compares each name's values instead, and a moved column is a note. --fail-on names,position,order turns those notes into failures.
Gate SQL where it is written. Both run the same checks as the CLI, and both tokenize locally first.
GitHub Actions. Findings land inline on the pull-request diff. The workflow authenticates as your repository owner using GitHub's own OIDC token — no signup, no API key to store or leak.
permissions:
id-token: write # authenticate as this repo's owner pull-requests: read # check only the files this PR changes contents: read # mode: diff, to read the earlier version of a file steps:
Set mode: diff and it answers a different question on every pull request: *did this rewrite change what the query returns?* Only modified files are compared, and a verdict of "cannot prove either way" never fails a build. A moved column is a change, since columns are ordered; set columns: by-name if your code reads them by name.
Pull requests from forks run anonymously. GitHub does not issue OIDC tokens to workflows a fork triggers, so a contributor's pull request cannot authenticate as your repository — it falls back to an anonymous, per-IP rate limit. Nothing is broken and there is nothing to configure; your own branches still authenticate normally. The action says so rather than suggesting a permission that would not help.
Outside a pull request there is no set of changed files, so changed-only cannot apply and every matching file is checked. The action warns when that happens, because on a large repository it is enough requests to reach a rate limit.
pre-commit. Same checks before the commit lands:
repos:
The hook blocks a commit on a real defect, not on a bad connection: if sqlike cannot be reached it says so and lets the commit through.
Tokenization happens here, on your machine, before any request goes out. sqlike never sees your real table names, columns, or values, so there is nothing to leak and nothing to train on. An AI assistant needs the real thing to help you; sqlike does not.
If a query cannot be parsed it cannot be tokenized, and the client refuses to send it rather than transmit raw SQL. Sending it anyway is an explicit opt-in (allow_raw on the tools, --allow-raw on the CLI).
See THREAT-MODEL.md for what that does and does not cover.
sqlike-mcp, the MCP server. Ships to npm as @sqlike/mcp.sqlike, the command-line client. Ships to npm as @sqlike/cli.Try it at [sqlike.com](https://sqlike.com). The equivalence checker is measured in public against the standard academic benchmark, including a head-to-head with the state-of-the-art prover, at [sqlike.com/benchmark](https://sqlike.com/benchmark).
This repository is generated from the upstream monorepo, which is the source of truth. Please file issues here. Code changes are made upstream and mirrored back.
Apache-2.0. See LICENSE.
crates/sqlparser is a vendored copy of sqlparser-rs, also Apache-2.0. Its NOTICE file records the upstream version and lists every file changed since.