arpeio-mcp
OfficialThe Arpeio MCP server provides a unified interface for AI assistants to build, preview, and execute high-performance data operations across four Arpe.io CLI tools — no binaries required for command-building.
FastBCP (Database Export) — 3 tools
Preview export commands for databases (SQL Server, PostgreSQL, Oracle, MySQL, etc.) to formats like CSV, Parquet, JSON, XLSX, with auto-suggested parallelism and support for local, S3, Azure, and GCS targets
Execute pre-built export commands
Get supported formats, parallelism recommendations, and workflow guidance
FastTransfer (Database-to-Database Transfer) — 3 tools
Preview high-performance transfer commands between databases (e.g., PostgreSQL → SQL Server, Oracle → DuckDB)
Execute pre-built transfer commands
Get supported source/target combinations, parallelism recommendations, and workflow guidance
LakeXpress (Database-to-Cloud Lake Pipelines) — 3 tools
Preview commands for the full pipeline lifecycle: init, config create/delete/list, sync, run, status, cleanup, and lock management
Execute pre-built pipeline commands
Get capabilities, supported storage backends, publish targets, and workflow sequences
MigratorXpress (Cross-Platform Database Migration) — 4 tools
Preview migration commands covering DDL translation, table creation, data transfer, diffs, and constraint copying (Oracle, PostgreSQL, SQL Server, Netezza, MySQL)
Execute pre-built migration commands
Validate credential JSON auth files before running migrations
Get supported platforms, task sequences, and workflow guidance
Meta / Discovery Tools — 4 tools
Check installation status of all Arpe.io CLI tools
Get quick-start guidance by describing a use case in plain English
Search Arpe.io documentation and blog for parameters, examples, and best practices
Retrieve release notes for any product, optionally filtered by version
Key design features:
No binaries needed for command building/preview; execution tools require the respective binary
All execute tools require explicit
confirmation=trueas a safety gateStructured JSON + human-readable markdown output for programmatic chaining
Typical workflow:
*_preview_*→*_execute_*(2 calls)
Allows GitHub Copilot in VS Code to build, preview, and execute high-performance data commands (database export, transfer, pipeline, migration) using Arpe.io data tools.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@arpeio-mcpexport my PostgreSQL database to S3"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
title: Arpeio MCP emoji: 🛠️ colorFrom: blue colorTo: indigo sdk: docker pinned: false
arpeio-mcp
Unified MCP server for Arpe.io data tools — build, preview, and execute high-performance data commands through AI assistants.
Tool | Description |
FastBCP | High-performance parallel database export to files and cloud |
FastTransfer | High-performance parallel data transfer between databases |
LakeXpress | Automated database-to-cloud data pipeline as Parquet |
MigratorXpress | Cross-platform database migration with parallel transfer |
No binaries required. All tools work in command builder mode out of the box — command building, preview, and informational tools work without any Arpe.io binary installed. To enable execution, download the binaries from arpe.io and set the corresponding
*_PATHenvironment variables.
Related MCP server: DBHub
Connect your AI assistant
A hosted instance is available at https://arpe-io-arpeio-mcp.hf.space/sse — no installation required. For local installation with execution support, use the stdio transport via pip install arpeio-mcp.
ChatGPT | Claude Code | Claude Desktop | Cursor | Gemini CLI | HuggingChat | Kiro IDE | Le Chat (Mistral) | VS Code | Windsurf
ChatGPT
Available for paid plans only (Plus, Pro, Team, and Enterprise).
Open ChatGPT in your browser, go to Settings > Apps and connectors.
Open Advanced settings and enable Developer mode.
Go to Connectors > Browse connectors > Add a new connector.
Set the URL to
https://arpe-io-arpeio-mcp.hf.space/sseand save.
Claude Code
claude mcp add --transport sse arpeio https://arpe-io-arpeio-mcp.hf.space/sseOr for local installation with execution support:
pip install arpeio-mcp
claude mcp add arpeio arpeio-mcpClaude Desktop
Add the following to your Claude Desktop configuration file:
Linux:
~/.config/Claude/claude_desktop_config.jsonmacOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Remote (no installation)
{
"mcpServers": {
"arpeio": {
"command": "npx",
"args": [
"mcp-remote",
"https://arpe-io-arpeio-mcp.hf.space/sse"
]
}
}
}Local (with execution support)
{
"mcpServers": {
"arpeio": {
"command": "arpeio-mcp",
"env": {
"FASTBCP_PATH": "/path/to/FastBCP",
"FASTTRANSFER_PATH": "/path/to/FastTransfer",
"LAKEXPRESS_PATH": "/path/to/LakeXpress",
"MIGRATORXPRESS_PATH": "/path/to/MigratorXpress"
}
}
}
}Cursor
Open Cursor Settings and search for "MCP".
Add a new MCP server with the following configuration:
{
"mcpServers": {
"arpeio": {
"url": "https://arpe-io-arpeio-mcp.hf.space/sse"
}
}
}Gemini CLI
Add the following to your ~/.gemini/settings.json file:
{
"mcpServers": {
"arpeio": {
"uri": "https://arpe-io-arpeio-mcp.hf.space/sse"
}
}
}HuggingChat
In the chat interface, click the + icon, select MCP Servers, then Manage MCP Servers.
Click Add Server.
Set the Server Name to
Arpe.ioand the Server URL tohttps://arpe-io-arpeio-mcp.hf.space/sse.Click Add Server and verify the health check shows Connected.
Kiro IDE
Add the following to your Kiro MCP configuration file (.kiro/settings/mcp.json in your workspace):
{
"mcpServers": {
"arpeio": {
"url": "https://arpe-io-arpeio-mcp.hf.space/sse"
}
}
}Le Chat (Mistral)
Available on all plans, including free.
Go to Intelligence > Connectors.
Click Add connector > Custom MCP Connector.
Set the name to
Arpe.ioand the URL tohttps://arpe-io-arpeio-mcp.hf.space/sse.Leave authentication disabled and click Create.
VS Code (GitHub Copilot)
Add the following to your VS Code MCP configuration. Run MCP: Open User Configuration from the Command Palette to open it.
Linux:
~/.config/Code/User/mcp.jsonmacOS:
~/Library/Application Support/Code/User/mcp.jsonWindows:
%APPDATA%\Code\User\mcp.json
{
"servers": {
"arpeio": {
"url": "https://arpe-io-arpeio-mcp.hf.space/sse",
"type": "sse"
}
}
}Windsurf
Add the following to your Windsurf configuration file:
Linux:
~/.codeium/windsurf/mcp_config.jsonmacOS:
~/.codeium/windsurf/mcp_config.jsonWindows:
%USERPROFILE%\.codeium\windsurf\mcp_config.json
{
"mcpServers": {
"arpeio": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://arpe-io-arpeio-mcp.hf.space/sse"
]
}
}
}Local Installation
For full execution support (not just command building), install locally:
pip install arpeio-mcpThen configure your AI assistant to use the arpeio-mcp command (stdio transport) with optional binary paths — see the Claude Desktop local configuration for an example.
Environment Variables
Variable | Description | Required |
| Path to FastBCP binary | No |
| Path to FastTransfer binary | No |
| Path to LakeXpress binary | No |
| Path to MigratorXpress binary | No |
| FastBCP directory for LakeXpress | No |
| FastTransfer directory for MigratorXpress | No |
| Per-tool execution timeout (seconds) | No |
| Per-tool log directory | No |
| Logging level (DEBUG/INFO/WARNING/ERROR) | No |
Available Tools (17)
Read-only advisory tools were consolidated into one *_info tool per product (with an action enum) and per-product release-notes tools were merged into a single arpe_release_notes. Auto-parallelism is now suggested inside preview so the typical workflow is 2 calls (preview → execute) instead of 4.
FastBCP (3 tools)
fastbcp_info— Read-only advisory:action="formats" | "parallelism" | "workflow" | "version"fastbcp_preview_export— Validate parameters and render the command (auto-suggests parallelism whenmethodis omitted)fastbcp_execute_export— Run the export
FastTransfer (3 tools)
fasttransfer_info— Read-only advisory:action="combinations" | "parallelism" | "workflow" | "version"fasttransfer_preview_transfer— Validate parameters and render the command (auto-suggests parallelism)fasttransfer_execute_transfer— Run the transfer
LakeXpress (3 tools)
lakexpress_info— Read-only advisory:action="capabilities" | "workflow" | "version"lakexpress_preview_command— Build any LakeXpress command (lxdb_*,config_*,sync,sync[export],sync[publish],run,status,cleanup). On v0.4.0+ binaries, warns when-a/--lxdb_auth_id/--sync_idare missing on sync-family callslakexpress_execute_command— Run the command
MigratorXpress (4 tools)
migratorxpress_info— Read-only advisory:action="capabilities" | "workflow" | "version"migratorxpress_validate_auth_file— Validate the JSON auth file (only file-I/O advisory tool kept separate)migratorxpress_preview_command— Build the migrate command. Accepts the newprojecttag (v0.6.30+); warns onmigration_db_type="postgres"against pre-0.6.32 binariesmigratorxpress_execute_command— Run the migration
Meta (4 tools)
arpe_get_status— Status of all four CLIs (installed / command-builder-only)arpe_quick_start— Detect the right tool from a plain-English use case and return a workflow guidearpe_release_notes— Return release-notes chunks for any product (product="fastbcp" | "fasttransfer" | "lakexpress" | "migratorxpress", optionalversion)search_docs— BM25 full-text search over arpe.io docs sites and blog
Structured output
The command-building, execution, and discovery tools return structured content
(outputSchema + structuredContent) alongside the human-readable markdown, so
MCP clients can chain calls programmatically instead of parsing prose:
*_preview_*→ the builtcommand(argv),command_string, maskedcommand_display,explanation, and versionwarnings. The exact command can be handed straight to the matching*_execute_*tool.*_execute_*→success,return_code,stdout,stderr, and parseddiagnostics.search_docs→ rankedresultsrecords;arpe_get_status→ per-product status;arpe_release_notes→ release-noteschunks.
Each payload carries a status field (ok / error) so success and error responses are both machine-checkable.
Prompts (5)
Conversation starters surfaced by clients that support MCP prompts (Claude Desktop, Cursor, etc.):
export-table, transfer-data, lakehouse-pipeline, migrate-database, troubleshoot.
Resources (4)
Static capability matrices served as MCP resources so clients can prefetch them without a tool call:
arpeio://capabilities/fastbcp-formats, fasttransfer-combinations, lakexpress-capabilities, migratorxpress-capabilities.
Evaluations
evaluations/arpeio_eval.xml holds 10 read-only, verifiable questions used to check
that an LLM can drive the server to correct answers (tool selection, parallelism
recommendations, capability lookups, version gating). A guard test re-derives every
answer from the capability registries so the answer key stays honest:
python -m pytest tests/test_evaluations.py -qLicense
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/arpe-io/arpeio-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server