etl-pipeline-mcpCAUTION
A sovereign, local-first MCP-Native ETL System with Hot/Cold tiering, PII scrubbing, ID stitching, Parquet buffers, and data warehouse exports.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A sovereign, local-first, open-source Model Context Protocol (MCP) server for end-to-end Big Data Extraction, Transformation, Identity Resolution, and Warehouse Loading (ETL/ELT).
💖 Sponsorship & B2B Custom Solutions
👨💻 Lead Architect & Attribution
Designed and engineered by [Momenul Ahmad](https://github.com/MOBILEPHONE), Lead Architect and Founder of [SEOSiri](https://seosiri.com).
🚀 Capabilities
- Multi-Platform Ingestion: Ingests real-time webhooks (CMS, email, social) and batch CRM records (HubSpot, Salesforce).
- Decoupled Hot/Cold Storage: In-memory SQLite Hot Tier for low-latency queueing + on-disk Cold Tier for permanent, anonymized storage.
- Identity Resolution: Merges fragmented user identities across CRM, social, and email records under a single
mcp_root_idvia ID stitching. - GDPR/HIPAA PII Redaction: Automatic SHA-256 hashing and string redaction of PII before long-term storage or export.
- Warehouse Exporter: Exports clean, transformed data buffers directly to Snowflake, ClickHouse, or BigQuery.
Quickstart
- Install in Editable Mode:
pip install -e .
- Run Unit Tests:
pytest tests/test_etl_pipeline.py
🔌 Connecting to Claude Desktop / Cursor
Local Script Execution
Add this block to your claude_desktop_config.json:
{
"mcpServers": {
"etl-pipeline-mcp": {
"command": "python",
"args": [
"D:/seosiri-etl-pipeline-mcp/src/main_server.py"
],
"env": {
"PYTHONPATH": "D:/seosiri-etl-pipeline-mcp"
}
}
}
}Remote Execution via GitHub
Or for zero-setup execution directly from GitHub using uv:
{
"mcpServers": {
"etl-pipeline-mcp": {
"command": "uv",
"args": [
"run",
"--github",
"SEOSiri-Official/etl-pipeline-mcp",
"src/main_server.py"
]
}
}
}License
Distributed under the
f6fd98095574OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add etl-pipeline-mcp -- uvx etl-pipeline-mcp
{
"mcpServers": {
"etl-pipeline-mcp": {
"command": "uvx",
"args": [
"etl-pipeline-mcp"
]
}
}
}Exposed tools (9)
9 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
export_to_data_warehouse | read | |
export_to_parquet_buffer | read | |
extract_realtime_stream | read | |
get_live_throughput_metrics | read | |
get_pipeline_analytics_summary | read | |
ingest_hubspot_webhook | read | |
ingest_universal_event | read | |
poll_crm_batch | read | |
transform_and_stitch_batch | read |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
etl_pipeline_mcp-1.0.3-py3-none-any.whl
etl_pipeline_mcp-1.0.3.tar.gz
new_root_id = hashlib.sha1(f"{h_email}:{crm_id}:{social_id}:{stripe_id}:{github_id}:{now_str}".encode()).hexdigest()[:16]Gates applied: no_behavioural_pass.
f6fd98095574full audit observations/trust-audit/mcp-server/seosiri-official__etl-pipeline-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | f6fd98095574 | CAUTION | B | 89 | first audit |
Questions
What is the etl-pipeline-mcp MCP server?
A sovereign, local-first MCP-Native ETL System with Hot/Cold tiering, PII scrubbing, ID stitching, Parquet buffers, and data warehouse exports.
What tools does etl-pipeline-mcp expose?
9 in total: 9 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is etl-pipeline-mcp safe to connect to an agent?
With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does etl-pipeline-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does etl-pipeline-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as etl-pipeline-mcp.
How current is this page?
The grade is for one exact copy of the source (f6fd98095574), read on 2026-10-11. The repository is watched and re-audited when it changes.