Packages

MCPStore is a Python orchestration layer that manages MCP service lifecycles and adapts them for use with popular AI agent frameworks like LangChain, LangGraph, AutoGen, CrewAI, and LlamaIndex through a unified API.

Provides two ways to run MCP (Model Context Protocol) servers that expose ACI.dev managed functions/tools to MCP clients: an apps-specific server that exposes tools from selected apps, and a unified server that can discover and execute tools across all available functions (via meta-tools).

An MCP server (Node.js) that lets MCP clients execute SQL against multiple database types via an apiSQL API gateway, with support for runtime switching between configured data sources (DS/SUDB), and both DDL/DML plus stored procedures/UDFs. It can run over MCP stdio by default and also offers a streamable HTTP transport mode.

Provides an MCP server that lets AI assistants query Azure retail pricing, compare prices across regions/SKUs, estimate usage-based costs, and perform FinOps-oriented analyses (RI break-even, region recommendations, spot intelligence, and orphaned resource cost estimation).

Dropbox MCP server (Go) that exposes Dropbox functionality (auth, file/folder operations, sharing, and revision history/restore) to AI assistants via the Model Context Protocol. Supports OAuth2 and large-file chunked uploads (per README).

mcp-wireshark is a Python-based MCP server that exposes Wireshark/tshark functionality to MCP-compatible AI clients. It can run live packet capture, read/analyze .pcap/.pcapng files, apply display filters, follow TCP/UDP streams, and export analysis results (e.g., JSON) via defined MCP tools.

An adapter extension for the Pi coding agent that proxies and manages MCP (Model Context Protocol) servers. It offers a single lightweight proxy tool for tool search/describe/calls, supports lazy/eager/keep-alive server lifecycles with cached tool metadata, optional promotion of specific MCP tools into Pi’s direct tool list, and MCP UI support with bidirectional messaging.

validation-mcp-server is an offline, Python-based Model Context Protocol (MCP) server that provides Ethereum address/key validation and related cryptographic utilities (e.g., EIP-55 checksum validation, private-key range checking, checksummed conversion, signature component/value validation, hashing like keccak256, function selector encoding/decoding, ENS format validation, and storage-slot computation).

Provides a Model Context Protocol (MCP) server exposing Wikidata exploration/query tools (item/property search, entity statements/values, hierarchy retrieval, and SPARQL execution). A hosted endpoint and local/Docker run instructions are provided.

Provides an MCP server (Python) exposing tools to parse, validate, extract, and manipulate XLIFF and TMX localization files, including tag-preserving processing, replacement of XLIFF targets from translated content, and CSV/JSON exports. Also ships a skills/catalog workflow layer intended for agent-guided localization tasks.

Oracle NetSuite's REST and SOAP APIs for accessing financial data, inventory, CRM, and operational business data from NetSuite's cloud ERP platform.

pyomop is a Python library/CLI for working with OHDSI OMOP CDM (v5.4/v6) databases using SQLAlchemy. It can create/init CDM tables, load OMOP vocabularies, run QueryLibrary queries, execute custom SQL and convert results to pandas DataFrames. It also includes FHIR Bulk Export (NDJSON/NDJSON) import utilities that map FHIR source values to OMOP concepts, and an optional MCP server exposing tools for database operations and query execution. There is also optional LLM-based natural-language query support via langchain extras.

12 x402-payable API tools for AI agents — web vitals, SEO, security, email, more.

An MCP server for macOS that exposes AppleScript-driven actions (calendar, clipboard, Finder, notifications, system controls, iTerm, Shortcuts, Mail, Messages, Notes, and Pages) to LLM/MCP clients via tool calls over stdio.

ARBuilder is an AI development assistant for the Arbitrum ecosystem that turns natural-language prompts into Stylus smart-contract code (Rust), cross-chain SDK/bridging and messaging code, and full-stack dApp scaffolding (backend/indexer/oracle/frontend/wallet integration), with additional Orbit chain deployment assistance. It uses a Retrieval-Augmented Generation (RAG) pipeline (hybrid search with vector + BM25 + reranking) and exposes functionality via an MCP server (19 tools), usable either hosted (via an MCP-remote URL and Bearer token) or self-hosted by running the MCP server locally.

CLI for deploying and querying a governed semantic/metrics layer for agentic analytics. Provides commands to scaffold projects, connect data sources, validate models, deploy with versioning/history, run queries, and set up an MCP server for governed agent queries, along with markdown dashboard tooling and programmatic access via a companion SDK/React packages.

Provides an MCP server that lets AI tools manage end-to-end BlazeMeter performance testing workflows (create/execute/report) via natural-language interactions, using BlazeMeter API credentials configured through the MCP host.

<!-- For a centered logo -->

Provides an MCP server that helps AI assistants create and maintain a structured “Memory Bank” (Markdown) for context preservation, including templates, structure descriptions, and suggestions based on a project summary.