"A task involving critical or creative thinking" matching MCP servers:

Enables AI agents to discover official public data sources, inspect their metadata and endpoint parameters, and execute live queries through a unified response envelope with a 500 ms budget.

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 LLMs to interact with any ERPNext instance through comprehensive CRUD operations, advanced permissions, and a web chat interface.

Give your AI agent the entire China A-share market: 55 datasets of prices, financials, capital flows, corporate events and futures/options, stored locally and queryable with read-only SQL. Built point-in-time with delisted stocks kept, so backtests don't lie — no account, no API key.

Minimalistic MCP server that lets AI assistants inspect, quality-check, and clean CSV datasets through tools, resources, and prompts, without needing local file access.

A stdio MCP server exposing a validate_emails tool that lets agents screen email lists without sending mail or probing SMTP, checking syntax, DNS/MX records, disposable domains, role accounts, free providers, typo suggestions, and SPF/DMARC. Each address comes back with a valid/risky/invalid/unknown verdict plus machine-readable reason codes so agents can clean leads and signups before outreach or import.

Enables checking lead rows, CSV files, or Apify datasets for duplicates, email syntax and risk signals, domain issues, missing fields, and stale dates, returning a per-row import, review, or reject verdict so only clean records reach a CRM or sequencer.

A privacy-first MCP server that searches, normalizes, and deduplicates job listings across multiple providers, enabling trustworthy discovery without scoring or applying.

Enables AI agents to search, correlate, and monitor real-time vulnerability intelligence from NVD, CISA KEV, EPSS, and MITRE ATT&CK, including CVE details, critical CVE tracking, known exploited vulnerabilities, and exploitation probability scores.

A Model Context Protocol server that lets you fetch Microsoft Clarity analytics data through Claude for Desktop or other MCP-compatible clients, with support for filtering by dimensions and retrieving various metrics.

Airflow MCP server — read DAGs, runs, task instances, log tails; trigger and clear (write-gated).

A server that interfaces with the Mixpanel API, allowing users to query events data, retention, and funnels through natural language from any MCP client like Cursor or Claude Desktop.

A Model Context Protocol server that exposes Apache Airflow's REST API to AI agents, enabling them to inspect and operate on DAGs, DAG runs, task instances, and logs.

Enables restaurant management through natural language, allowing import of Toast CSV data, labor/sales analysis, tip pool calculations, task management, and note-taking.

A Model Context Protocol (MCP) server that provides tools for reading Excel (xlsx) files, enabling extraction of data from entire workbooks or specific sheets with results returned in structured JSON format.

Enables users to interact with Apache Airflow through MCP to monitor DAGs, inspect runs and logs, and diagnose task failures using natural language.

Enables natural language management of Apache Airflow workflows, including DAG monitoring, task control, and configuration, via the Model Context Protocol.

Enables Meta Ads account, campaign, ad set, creative, audience, and budget management alongside deterministic marketing growth analytics such as ROAS, CPA, CTR, anomaly detection, cohort retention, and evidence packets. Supports stdio and Streamable HTTP transports with local OAuth or bearer-token authentication.

Converts PDF, Word, PowerPoint, Excel, and HTML documents into Markdown, handling files up to 8 MB in a single call and routing larger or scanned files through an OCR and table-detection queue that returns Markdown plus a JSON structure file. Results arrive either by polling or a signed webhook.

Enables AI assistants to read a verified household financial record across linked accounts, including holdings, transactions, fees, performance, cash flow, advisors, diagnostics, and score findings. It can also refresh connections and manage manually tracked assets or liabilities inside the service, but cannot move money or place trades at financial institutions.

Enables agents to search a public catalog of published components, estimate what a data model would reuse, mint, and cost, then assemble, publish, and generate the resulting package or application. Spending is gated by a shown estimate and the key's limit, so no build or charge happens without review.

An MCP server for controlling Apache Airflow 3 via its REST API, enabling operations like DAG management, task monitoring, and more through natural language.

Exposes 250+ financial data tools across 24 categories, letting AI assistants retrieve and analyze stock quotes, company fundamentals, financial statements, technical indicators, ETFs, crypto, forex, commodities, and economic data through the Financial Modeling Prep API. Supports dynamic or pre-loaded toolsets over HTTP/SSE, with hosted or self-hosted deployment.

Enables reading, summarizing, searching, validating, and surgically editing Pentaho Kettle .kjb/.ktr files without requiring a PDI installation or executing them, using an embedded knowledge base.

Enables high-throughput MinHash LSH dataset deduplication and content quality scoring through a zero-dependency STDIO MCP server that returns deterministic JSON results for agent telemetry and task inputs.

Lets coding agents run governed SQL against a Databricks SQL warehouse and inspect Unity Catalog metadata over stdio or Streamable HTTP, with persistent operational logs stored in SQLite. Access is read-only by default and bounded by the configured identity's Unity Catalog permissions.

Enables read-only intelligence over a Linear workspace by serving snapshot and change-history data stored in Cloudflare D1, so clients can answer questions about current work, project and milestone progress, member activity, and weekly reports without modifying Linear or invoking an LLM.

An MCP server that provides data bridging from Spring Boot interfaces and a lightweight Python sandbox for script execution. It enables agents to fetch data as Markdown or Parquet files and perform automated data analysis within a controlled environment.

Enables AI agents to query Mixpanel event data, funnel conversion rates, and retention cohorts via MCP tools or natural language.

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.