Enables optimal freight-mode selection (air, sea-LCL, full container) by solving 3D bin-packing, cost optimization, and delivery-risk analysis behind two tools: solve for deterministic planning and explain for hallucination-proof natural-language narration of results.
Enables AI assistants to parse, validate, send, and inspect X12 EDI documents via the SignalEDI Core API, with optional QuickBooks integration and a demo mode for keyless local testing.
Enables Claude to inspect and operate Apache Airflow over its REST API, providing read tools and safe write operations (gated by read-only mode) for managing DAGs, runs, tasks, and pools.
A minimal MCP server that provides a persistent DuckDB SQL engine to AI assistants, enabling natural-language querying of CSVs, Parquet, and cloud data with 12 tools and optional read-only mode.
Enables MCP-compatible AI assistants and agents to browse reports, manage queries, and fetch results from Mode Analytics, with optional authoring/archiving and configurable read-only or delete controls.
Read-only MCP server for self-hosted Airbyte OSS 1.6.x, enabling monitoring of connections, jobs, and health via public and internal APIs. Optionally supports triggering syncs and canceling jobs.
Enables structured document understanding of local PDFs via a dual-extract MCP server, combining MinerU text/layout and Qwen3-VL vision with fusion adjudication for field extraction, tables, formulas, and validation. Fully local and offline.
Enables MCP clients to discover processor and controller service types, build and wire Apache NiFi 2.x process groups, schedule them, and debug queues and bulletins through the NiFi REST API. Supports flow spec application, automatic canvas layout, parameter contexts, and an optional read-only mode that blocks all writes.
Enables AI assistants to query fused 0-100 conviction scores, ranked watchlists, market briefings, and raw market signals from the Unusual Whales API, including a keyless demo mode.
Enables interaction with the Civis Platform for data exploration, querying, and workflow execution. Supports schema-restricted read-only mode and tools like run_query, list_tables, and publish_html_report.
Connects MCP clients to databases like Snowflake, BigQuery, and Databricks through Alkemi's data platform, enabling natural language database queries with proper schema understanding and metadata management for consistent team-wide access.
An MCP server that lets AI agents inspect, build, and operate Apache NiFi flows using plain username/password login, with no Knox or Cloudera gateway required. It offers 29 read-only tools by default and up to 66 tools in full mode, covering processors, connections, controller services, parameter contexts, and ports, with dry-run, toolset gating, and audit logging for safety.
MCP server for connecting to Microsoft Fabric and Power BI semantic models, enabling workspace browsing, dataset management, TMSL retrieval, DAX queries, model creation/editing, and includes a Best Practice Analyzer with 71 rules.
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.
Enables MCP clients such as Claude to query events, entries, start lists, results, clubs, members and activities across Eventor Australia, Sweden, Norway and IOF, with optional publishing of start and result lists. Responses are converted from Eventor's XML to compact JSON and cached, with read-only mode available to hide write tools.
Provides deterministic tools for understanding, transforming, and verifying structured data via MCP, enabling rule inference from examples and verification of transformed records.
Self-hosted MCP servers that let Claude, ChatGPT, or any MCP client answer questions about your own Google Maps data — where you were at a given moment, visits to specific places, dwell time, trips, distance traveled by mode, and your current position from a live feed. All tools are read-only and gated behind OAuth 2.1 tokens with configurable precision, so credentials and coordinates never leave your server.
Enables interaction with a DuckDB database through a single unified SQL query tool, supporting operations such as querying, table creation, and schema inspection. Can run in read-only mode to prevent write operations and keep data unaltered.
Enables interaction with DuckDB databases through the Model Context Protocol, supporting SQL query execution, table creation, and schema inspection with optional read-only mode.
Exposes an agentic AutoML pipeline as a callable tool so any MCP client can upload a CSV and natural language goal and receive a full ML analysis report with SHAP visualizations. Enables autonomous problem understanding, data cleaning, feature engineering, model training, and explainability through a single remote tool call.
Enables interaction with a DuckDB database through the Model Context Protocol, supporting SQL query execution, table creation, and schema inspection. It can also run in read-only mode to prevent write operations and maintain data integrity.
Enables interaction with a DuckDB database through MCP tools for executing SQL queries, creating tables, and inspecting schemas. It also supports read-only mode to prevent write operations.
Enables interacting with a DuckDB database through the Model Context Protocol, allowing SQL querying, table creation, and schema inspection. Optional read-only mode prevents write operations to protect data integrity.
Enables interaction with a DuckDB database through the Model Context Protocol, allowing database querying, table creation, and schema inspection. It supports executing arbitrary SQL statements, with optional read-only mode to prevent write operations.
Enables AI agents to list metrics and dimensions, inspect definitions, and run governed metric queries against Apache Iceberg tables through a semantic layer, without writing SQL or accessing raw rows or columns outside their role.
Enables AI agents and assistants to work with a Databricks workspace — SQL, clusters and warehouses, notebooks, Jobs, Lakeflow pipelines, Unity Catalog, Volumes, dashboards, Genie, model serving, Vector Search, Lakebase and Apps — under a safety-first model with read/write/destructive/security classification, confirmation steps for dangerous changes, production resource protection, and a fully read-only mode. Every call is checked against the official Databricks SDK, returns typed schemas and redacted secrets, and unsupported features report an explicit error rather than faking results.
Enables MCP clients to search and analyze monthly Hacker News "Who is hiring?" threads by parsing free-form job comments into structured fields such as company, role, location, work mode, salary, visa, and technologies, with tools for listing threads, searching jobs, retrieving individual posts, and viewing hiring trends.
Enables an agent to author StageFlow pipelines as JSON and check them against a live backend — its schema, stages, node types and plan ceilings — before spending a run, then execute or stop them and read back status, results, artifacts, meters and the node path a run took. It also exposes the same graphs to an open editor canvas and, when the backend asks, gathers the backend address through the client's own prompt rather than the conversation.
MCP server with 32 tools for ETL ingestion, AI-generated data quality rules, AI
transformations, vector search, and natural-language SQL. Works across Postgres,
MongoDB, Kafka, S3/MinIO, HashiCorp Vault, and five vector stores
(Qdrant, Weaviate, Milvus, Chroma, pgvector).
Enables orchestrating data quality checks, transformation, and deduplication pipelines via an MCP interface. Offers tools for listing pipeline stages, validating wiring, running the full check-transform-match pipeline, and explaining configurations.
Enables an AI assistant to turn a plain-language description into a working Apache NiFi 2.x flow, validate and layout the canvas, run test data, golden-file replays and diagnostics, and commit only verified versions to the NiFi Registry. It exposes 44 read-or-write tools for exploring, building, testing, debugging and releasing flows, staying read-only unless writes are explicitly enabled.
Enables agents to run zero-config entity resolution on messy records from CSVs, tables or databases, automatically choosing match rules and clustering duplicates into stable entities with per-field provenance. Exposes the resulting identity layer through dozens of tools for deduping, merging/splitting records, auditing changes, and answering Customer 360 questions.
