DataFinder MCP
Chat analytics on Volcengine DataFinder: 52 tools, metric dictionary, local jobs
- Pricing
- Open source
- Platforms
- CLI, self-hosted
- Runs
- Locally
- Version
- 0.2.5
- Listing updated
- today
Similar MCP servers
About DataFinder MCP
DataFinder MCP is an open-source MCP server for analytics and data. It runs locally on your machine and is started by your AI client.
DataFinder MCP is written mainly in Chinese and targets Volcengine's DataFinder product-analytics service. Product managers, growth teams and analysts can ask in plain language for active users by channel, next-day retention against last week, or a one-day conversion funnel, then follow up with a filter such as iOS only and export the result as CSV.
The 52 tools cover queries, analysis, a metric dictionary, task records and controlled configuration. The dictionary stores names, definitions, sources and versions so later questions reuse the same definition, and SQL metrics can be bound to explicit tables and columns. Results keep their source, date range and quality notes. The standalone package ships an independent SQLite database, persistent jobs and a separate background process, and needs Node.js 24 or later.
Writes are off by default. Local changes and upstream metadata changes are separate switches, and each follows a preview, confirm and read-back flow. Project-wide queries are also disabled until enabled. Arbitrary SQL execution is not offered. Setup needs an access key, secret key and project, app and subject IDs.
Install
Run in a terminal
claude mcp add datafinder-mcp --env DATAFINDER_AK='<DATAFINDER_AK>' --env DATAFINDER_SK='<DATAFINDER_SK>' --env DATAFINDER_PROJECT_ID='<DATAFINDER_PROJECT_ID>' --env DATAFINDER_APP_ID='<DATAFINDER_APP_ID>' --env DATAFINDER_SUBJECT_ID='<DATAFINDER_SUBJECT_ID>' -- npx -y @cyuanxv/datafinder-mcpAdd to claude_desktop_config.json
{
"mcpServers": {
"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>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"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>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"datafinder-mcp": {
"type": "stdio",
"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>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"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>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"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>"
}
}
}
}Using several servers? Build one config file with the MCP config generator.
Configuration
DATAFINDER_AKYour DataFinder access keyRequiredDATAFINDER_SKYour DataFinder secret keyRequiredDATAFINDER_PROJECT_IDYour DataFinder project IDRequiredDATAFINDER_APP_IDYour DataFinder app IDRequiredDATAFINDER_SUBJECT_IDYour configured analysis subject IDRequiredDATAFINDER_ALLOW_PROJECT_WIDEExplicitly allow aggregate queries across authorized apps in the configured project. Default false.DATAFINDER_DB_PATHAbsolute path to your independent SQLite databaseDATAFINDER_LOCAL_OWNERLocal owner scope used for stored dataDATAFINDER_ALLOW_LOCAL_WRITESEnable confirmed local changes and background tasksDATAFINDER_ALLOW_UPSTREAM_WRITESSeparately enable confirmed DataFinder metadata changes
What it does
- Natural-language queries
- Asks for reports, events, retention and funnels without writing SQL.
- Metric dictionary
- Saves definitions, sources and versions for reuse.
- Follow-up questions
- Reuses earlier conditions to drill into channel or platform.
- Report export
- Exports results as CSV or Excel-readable files.
- Persistent jobs
- Keeps task progress and history in a local SQLite database.
- Confirmed changes
- Metadata edits require preview, confirmation and read-back.
- Scoped access
- Project-wide queries are off unless explicitly enabled.
Good for
- Check yesterday's active users by channel and system
- Compare next-day retention week on week
- Analyse a conversion funnel with a one-day window
- Record an agreed metric definition for later reports
Pricing
Open source
MIT licence; requires your own DataFinder account
DataFinder MCP FAQ
What do I need to run it?
Node.js 24 or later and your own DataFinder access key, secret key, project ID, app ID and subject ID.
Can it change my DataFinder setup?
Only if you enable upstream writes, and each change needs preview, confirmation and read-back.
Can it run any SQL?
No. The README says unrestricted arbitrary SQL is not provided.
Is it open source?
Yes, under the MIT licence.
Is DataFinder MCP free?
Yes. DataFinder MCP is open source, so you can use and self-host it for free.
How do I add DataFinder MCP to Claude Code?
Run this command in your terminal: claude mcp add datafinder-mcp --env DATAFINDER_AK='<DATAFINDER_AK>' --env DATAFINDER_SK='<DATAFINDER_SK>' --env DATAFINDER_PROJECT_ID='<DATAFINDER_PROJECT_ID>' --env DATAFINDER_APP_ID='<DATAFINDER_APP_ID>' --env DATAFINDER_SUBJECT_ID='<DATAFINDER_SUBJECT_ID>' -- npx -y @cyuanxv/datafinder-mcp
What are the best alternatives to DataFinder MCP?
The closest alternatives to DataFinder MCP are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, dashboard-icons, Tapetide - Indian Stock Market MCP and World Monitor.
Where this comes from
- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

