"QA review sentinel test marker" matching MCP servers:

An MCP server that extracts fields from documents and holds uncertain extractions for human review, ensuring high confidence data flows automatically while uncertain cases are resolved manually.

Read-only MCP server for reconciling SimpleFIN bank data against Firefly III ledger, enabling audit and review workflows without mutation.

Enables users to review a supplied batch of supplier invoices or vendor bills for repeated references, normalized reference variations, and identical amount-and-date candidates, returning grouped evidence and exact review reasons from local history. Supports saved reports, CSV export, and use with MCP clients such as Claude Desktop, Claude Code, and Cursor.

A server that connects to PostgreSQL databases and provides tools for safely exploring schemas, running read-only SQL queries, and performing data analysis with pre-built templates.

A Python MCP server for hypothesis-driven data analysis, managing analysis designs, data catalogs, and review workflows through Claude Code or any MCP-compatible client.

A Model Context Protocol tool that retrieves daily stock market data for any stock symbol using the Alpha Vantage API.

A read-only MCP server that exposes dbt project artifacts and data quality result tables (BigQuery/Postgres) to LLM clients, enabling deep introspection, run-history analysis, source freshness, test coverage, and lineage walks.

Local-first Taiwan market evidence workbench for AI agents with persistent Watchlists, governed MCP, auditable evidence, and explicit execute-once retrieval. GitHub Repository URL

Enables AI assistants to validate, lint, explain, and test-run Open Lakehouse Contracts locally over stdio, with no network, account, or platform access.

Enables AI clients to access realtime quotes and K-line data from a running MyQuant terminal, including connectivity checks, symbol normalization, and historical/recent K-line queries. It bridges the terminal's Python SDK to MCP-compatible clients for technical analysis and review workflows.

dbt model and column lineage, downstream impact and test proposals; no warehouse or dbt compile

Enables read-only access to geotechnical investigation project databases and official standard data interface files from AI workflows, supporting project summaries, borehole lists, arbitrary table queries, and interface file generation, parsing and validation. It also recognizes Excel result tables such as exploration point schedules and dynamic penetration test statistics, converting them into normalized records.

Enables importing and reconciling Mexican bank statement PDFs and files into an auditable SQLite ledger, with tools to preview, review, and commit transactions via Claude.

MCP server for the Russian construction market — 3,395 contractor companies and 13,436 house-building projects across 18 regions. 21 tools for search, comparison, cost analytics, contractor recommendations, and quote requests.

基于Model Context Protocol (MCP) 的A股实时行情查询服务器，支持查询A股实时价格、历史K线数据、财务信息及市场概况。

Enables agents to retrieve learner profiles, analyze longitudinal academic and attendance trends, retrieve supporting evidence, and record teacher review decisions for evidence-backed, human-in-the-loop educational recommendations.

Enables AI assistants and agents to query exchange hours, futures expiries and roll calendars, settlement and FX sessions, DST gaps, Treasury yield curves, ECB FX rates, and CFTC positioning through paid x402 calls, while offering free catalog and listing helpers.

Enables users and AI agents to reconcile CSV bank statements against invoices or bills by matching amounts and references, then sorting each line into matched, likely, review, or unmatched groups with reasons. It exposes read-only tools for matching files and inspecting detected CSV columns and row counts.

Enables AI assistants to search, screen, and analyze all 8,200+ NSE and BSE listed stocks with live quotes, financials, a 326-ratio screener, technical indicators, FII/DII flows, option chains and IV, corporate filings, IPOs, bulk deals, and portfolio P&L. It connects to clients such as Claude, ChatGPT, Cursor, VS Code, Codex, and Gemini CLI over either a remote OAuth endpoint or a local npx/uvx bridge.

A local, keyless MCP server simulating Forge's industrial telemetry kernel, enabling agents to normalize vendor-specific machine data, forecast breaches, and test integrations against realistic equipment data without credentials or persistence.

Enables dialogue-guided Korean career discovery by saving a user’s role and industry scope, generating adjacent-role search plans and recent Google job-search links, and running a local pipeline to collect, normalize, score, and review Korean job postings from approved APIs and company sources.

Enables AI assistants to analyze CSV, Excel, or text exports from biometric attendance devices, detecting late days, estimated absences, missing punches, and column mappings. It supports multiple device formats and optional shift, weekend, holiday, and regional settings for pre-payroll attendance review.

Enables AI assistants to connect to a self-hosted card-transaction ledger over MCP, so they can refresh transactions from supported providers, review charges, categorize and tag them, add context, and mark review status.

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.

Enables comprehensive audit of WhatsApp business conversations, including history export, LLM analysis with verification, and multi-format report generation.

market-spread MCP — cross-venue prediction-market landscape scanner.

It enables users to infer bounded flat CSV/JSON/JSONL schemas, propose and review correspondences to a target contract, validate records, and generate versioned mappings with reusable Python transforms through nine stdio tools.

Enables AI agents to transcribe insurance rate filings into executable rating engines with full citation tracking, supporting validation, review, and quote generation through MCP tools.

Enables AI agents to inspect, query, test, and safely fix dbt projects and BigQuery warehouses under policy-enforced controls, with read-only direct queries and dbt-only allowlisted writes.

A governance proxy for the DataHub MCP Server that enforces catalog metadata as policy, providing allow, redact, review, and deny outcomes for agent tool calls, and writing agent actions back into DataHub.