"Debugging and Testing Errors in Rust Code" matching MCP servers:

Exposes a synthetic issue tracker and pipeline warehouse as callable tools so an agent can answer operational questions about tickets, pipeline health, runs, incidents, and governed metrics with every claim cited to the exact tool call it came from. All writes are proposal-only, requiring human approval through a gated apply path that logs each step for audit.

MCP server for configuring the konsol Frappe app via the CLI. Enables AI clients to manage dimensions, measures, fact tables, connectors, and schemas using natural language.

Enables users to preprocess, analyze, and visualize CSV data through comprehensive tools for data manipulation, statistical analysis, and graph generation.

This server facilitates scalable discovery and execution of OpenAPI endpoints using semantic search and high-performance processing, overcoming limitations of large spec handling for streamlined API interactions.

Exposes local DuckDB pizza sales data as MCP tools for querying store-level and total sales metrics via natural language, enabling local LLMs to perform real-time analytical queries.

Enables AI to interact with Microsoft Access (.mdb, .accdb) and SQLite 3 databases, including read-only support for Access 97 databases. Supports executing SQL queries, importing/export data from CSV and Excel files, and storing notes about database files.

Provides stock market data and computes technical indicators like EMA, MACD, and RSI across multiple timeframes using the LongPort API and TA-Lib. It enables users to perform detailed financial analysis and multi-timeframe market reviews through standard MCP tools.

Enables schema-aware exploration of JSON data by uploading samples, flattening nested structures, and using heuristic search with token overlap and fuzzy matching to find field paths for target names, accelerating ETL and API onboarding workflows.

An MCP server that enables AI coding assistants to interact with a local Airflow cluster via its REST API for triggering DAG runs, monitoring status, reading logs, and diagnosing errors.

Enables querying, inserting, and managing unstructured data in RawTree via SQL, JSON ingestion, and log inspection through MCP clients like Claude Code, Cursor, and Claude Desktop.

Provides AI-assisted guidance for the Weik.io integration platform, enabling planning, implementation, testing, and deployment of integrations using Apache Camel and specialized Weik.io features.

A Python MCP server that lets you manage Microsoft Fabric through natural language in Claude Code or Claude Desktop, with 77+ tools covering workspaces, lakehouses, warehouses, SQL, DAX, semantic models, notebooks, pipelines, OneLake, and Microsoft Graph.

Exposes ERP data (production orders, inventory, BOM, customers) to any MCP client through a backend-neutral interface, with a mock backend for testing.

Enables Claude to query a Postgres analytics schema via a read-only MCP server, with tools auto-generated from live database introspection and configurable SQL queries defined in YAML.

Provides MCP tools that help AI agents get their bearings in a codebase with unified SQL views over code, git, docs, and conversations, powered by DuckDB.

MCP server for analyzing China's 福彩3D lottery data with deterministic math engines, forward-testing, and safety checks. Enables data import, statistical testing, coverage optimization, risk control, and optional LLM interpretation.

Enables Claude Code to generate Kafka producer and consumer code using predefined event schemas, with tools to list events, get schemas, and validate code.

Aggregates job listings from multiple ATS and job board APIs via MCP, enabling unified search and retrieval in a structured format without HTML parsing.

A versatile tool that enables querying and exporting data from multiple relational databases (MySQL, PostgreSQL, Oracle, SQLite, etc.) in read-only mode for data safety.

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.