SEOSiri Data Pipeline MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ingest_realtime_webhookA | Ingests high-velocity, real-time events (CMS, email opens, social mentions) directly into the Hot Tier. Verifies webhook authenticity via HMAC-SHA256. |
| ingest_batch_api_pollC | Ingests heavy, non-real-time data (CRM profiles) directly to on-disk Cold Storage. Executes PII redaction and maps unique stitched identities instantly. |
| process_lambda_pipelineB | Migrates Hot Tier events to Cold Storage, executing ID stitching, PII anonymization, and priority scoring. |
| export_to_data_warehouseA | Simulates exporting the anonymized, prioritized, and stitched historical dataset from the Cold Storage DB directly to an enterprise data warehouse (Snowflake/ClickHouse/BigQuery). |
| retrieve_analytical_summaryB | Queries and aggregates statistics across both Hot Tier (RAM) and Cold Tier (Disk). |
| sanitize_and_validate_payloadC | Universal Security Gatekeeper: Validates proposed payloads against OWASP rules and compliance profiles. |
| fetch_hubspot_contactsC | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a distinct stage or mode (source-specific fetch, real-time ingest, batch ingest, processing, export, summary retrieval, payload validation) with minimal conceptual overlap. The descriptions clearly separate concerns, making tool selection unambiguous.
All tool names follow a consistent verb_noun pattern in snake_case (fetch_, ingest_, process_, export_, retrieve_, sanitize_and_validate_). The compound verb in sanitize_and_validate_payload is a minor deviation but still fits the pattern and is readable.
7 tools is well-scoped for a data pipeline server, covering ingestion (real-time and batch), processing, export, summary retrieval, and validation. Each tool serves a clear purpose without unnecessary bloat.
The core pipeline lifecycle (ingest -> process -> export -> summarize) is covered, plus validation. A notable gap is the lack of a tool to retrieve raw processed records directly; only aggregated statistics are available via retrieve_analytical_summary, which may hinder granular data access needs.