DataFinder MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 697 installs a week from npm. Last commit 24 Oct 2026.
DataFinder analytics with 52 tools, metric dictionaries, persistent jobs and confirmed changes.
What the code does
We read the source, 21 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
register('find_assets','查找资源','实时搜索项目内账号可见的看板和报表；事件与属性元数据仅限配置的应用，报表按批准的项目范围读取。',{kind:z.enum(['reports','dashboards','events','params','virtual_events','virtual_params']),keywor…
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
const worker=spawn(process.execPath,[entry,'--worker','--once'],{env:{PATH:process.env.PATH,...written},stdio:['ignore','pipe','pipe']});let err='';worker.stderr.on('data',b=>err+=b);const code=await new Promise(resolve=>worker.once('exit',resolve));assert.equal(code,0,err);
const text=await readFile(path.join(source,name),'utf8');
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add datafinder-mcp -e 'DATAFINDER_AK=<DATAFINDER_AK>' -e 'DATAFINDER_SK=<DATAFINDER_SK>' -e 'DATAFINDER_PROJECT_ID=<DATAFINDER_PROJECT_ID>' -e 'DATAFINDER_APP_ID=<DATAFINDER_APP_ID>' -e 'DATAFINDER_SUBJECT_ID=<DATAFINDER_SUBJECT_ID>' -- npx -y @cyuanxv/datafinder-mcp{
"mcpServers": {
"datafinder-mcp": {
"command": "npx",
"args": [
"-y",
"@cyuanxv/datafinder-mcp"
],
"env": {
"DATAFINDER_AK": "<DATAFINDER_AK>",
"DATAFINDER_APP_ID": "<DATAFINDER_APP_ID>",
"DATAFINDER_PROJECT_ID": "<DATAFINDER_PROJECT_ID>",
"DATAFINDER_SK": "<DATAFINDER_SK>",
"DATAFINDER_SUBJECT_ID": "<DATAFINDER_SUBJECT_ID>"
}
}
}
}[mcp_servers.datafinder-mcp]
command = "npx"
args = ["-y", "@cyuanxv/datafinder-mcp"]
env = { DATAFINDER_AK = "<DATAFINDER_AK>", DATAFINDER_SK = "<DATAFINDER_SK>", DATAFINDER_PROJECT_ID = "<DATAFINDER_PROJECT_ID>", DATAFINDER_APP_ID = "<DATAFINDER_APP_ID>", DATAFINDER_SUBJECT_ID = "<DATAFINDER_SUBJECT_ID>" }{
"mcpServers": {
"datafinder-mcp": {
"command": "npx",
"args": [
"-y",
"@cyuanxv/datafinder-mcp"
],
"env": {
"DATAFINDER_AK": "<DATAFINDER_AK>",
"DATAFINDER_APP_ID": "<DATAFINDER_APP_ID>",
"DATAFINDER_PROJECT_ID": "<DATAFINDER_PROJECT_ID>",
"DATAFINDER_SK": "<DATAFINDER_SK>",
"DATAFINDER_SUBJECT_ID": "<DATAFINDER_SUBJECT_ID>"
}
}
}
}{
"servers": {
"datafinder-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cyuanxv/datafinder-mcp"
],
"env": {
"DATAFINDER_AK": "<DATAFINDER_AK>",
"DATAFINDER_APP_ID": "<DATAFINDER_APP_ID>",
"DATAFINDER_PROJECT_ID": "<DATAFINDER_PROJECT_ID>",
"DATAFINDER_SK": "<DATAFINDER_SK>",
"DATAFINDER_SUBJECT_ID": "<DATAFINDER_SUBJECT_ID>"
}
}
}
}Put your own values in place of
<DATAFINDER_AK> (Your DataFinder access key), <DATAFINDER_SK> (Your DataFinder secret key), <DATAFINDER_PROJECT_ID> (Your DataFinder project ID), <DATAFINDER_APP_ID> (Your DataFinder app ID), <DATAFINDER_SUBJECT_ID> (Your configured analysis subject ID).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
DATAFINDER_ALLOW_PROJECT_WIDE (Explicitly allow aggregate queries across authorized apps in the configured project. Default false), DATAFINDER_DB_PATH (Absolute path to your independent SQLite database), DATAFINDER_LOCAL_OWNER (Local owner scope used for stored data), DATAFINDER_ALLOW_LOCAL_WRITES (Enable confirmed local changes and background tasks), DATAFINDER_ALLOW_UPSTREAM_WRITES (Separately enable confirmed DataFinder metadata changes).
Alternatives to DataFinder MCP
same job, measured the same wayPersistent memory with contradiction detection, burnout monitoring, and 69 intelligence tools.
Analytics for founders: traffic, search, ad spend, revenue and retention per product.
Yandex Direct, Metrica, Wordstat, VK Ads and Avito Ads in chat. Changes need your confirmation.
Read-only Recharge store analytics: metrics, dimensions, and governed queries in plain language.
Datasets for founders: directories, newsletters, and agencies, with metrics attached.
MCP server for Yandex Metrica API: list counters, goals and pull web-analytics statistics.
The AI data platform for commerce: Shopify, Amazon, ads and Klaviyo data with metrics defined once.
Google Search Console, Ads and AdSense analytics for AI clients. Hosted, read-only, 57 tools.
DataFinder MCP — questions
Answers built from our own checks of this server.