"Loop" matching MCP servers:

Enables autonomous data quality inspection and repair workflows. It scans DuckDB warehouses for anomalies, generates and verifies fixes in a dry-run copy, then applies them after validation, with full audit logging.

Enables AI agents to discover and access 800TB+ of public geospatial data from Source Cooperative, with tools for listing organizations, products, files, and fuzzy search.

Enables MCP-compatible hosts to record, retrieve, and verify LoopGrid decision evidence through tools for decisions, reviews, actions, outcomes, and verification.

Exposes Iceberg-backed ontology objects, links, and actions as typed MCP tools for LLM agents, enabling governed data access and operations without raw SQL.

Drives Lumen's data-to-SQL-to-chart-to-report loop from any MCP client, supporting keyless SQL and charting or keyed agentic data analysis.

Deterministic bank-statement parsing for AI agents: messy CSV/OFX exports to clean, categorized ledger rows. In-memory only, no storage, no external calls, no LLM in the loop.

Enables MCP-compatible agents to run the complete document extraction loop as remote tools: upload files, submit extraction jobs with plain-language instructions, answer clarifying questions, inspect review-needed rows and failed pages, and download results as spreadsheets or JSON.

An MCP proxy server that intercepts large tabular tool results, ingests them into an embedded DuckDB, and provides a compact envelope with schema and query capabilities, enabling efficient cross-server data analysis.

Enables AI agents to retrieve and analyze breeding data from BrAPI-compliant databases through shared tools, with human-in-the-loop approval and verification.

This MCP server enables human-in-the-loop semantic labeling by creating self-contained HTML forms for ambiguous data and securely retrieving labeled results.