"Understanding Boss Mode" matching MCP servers:

A code-mode MCP server for the Unraid 7.2+ GraphQL API that exposes search and execute tools, allowing LLM agents to introspect and call any GraphQL field via sandboxed JavaScript.

An MCP server that gives AI agents full access to the Clever Cloud API through three tools: search, execute, and doc, using a code mode pattern to compose API commands.

Uploads files, text, or base64 binary content to Aliyun OSS as objects with MD5-based keys, returning status, size, key, and URL.

Code Mode MCP server for the OVH API. Two tools (search + execute) give LLMs access to all OVH endpoints via sandboxed JavaScript.

An MCP server that gives AI agents access to the full Cumulocity API surface through a compact code-mode interface.

MCP-native infrastructure ops for deploying and managing self-hosted OpenClaw instances across cloud providers or local VMs, with read-only mode, destructive-action confirmation, and audit logs.

Enables AI agents to execute SQL queries and explore Snowflake databases using natural language, with schema discovery, table inspection, and readonly mode.

A governed, read-only MCP server for ad inventory discovery from Google Ad Manager, exposing three tools (well_known_capabilities, discover_products, get_forecast) to buyer-side agents without modifying or accessing the ad server.

Enables interaction with AWS Fault Injection Service to create, manage, and execute chaos engineering experiments. Operates in read-only mode by default for security, with optional write operations for starting/stopping experiments and managing templates.

Enables MCP-capable agents to operate PostgreSQL and PgBouncer clusters on Kubernetes—covering discovery, pooling, tuning, backups/PITR, DR, and lifecycle—with safe-by-default read-only mode and granular opt-in security controls.

An MCP server that enables interaction with Google Firestore in Datastore mode for entity management and querying. It provides tools for CRUD operations, aggregation queries, and transaction execution within Google Cloud projects.

Delegates expensive or long-running AI tasks to Kubernetes-hosted Claude agents running on OpenShift. Enables creating, managing, and monitoring remote agentic sessions for complex work like codebase analysis and security audits.

Manage blockchain RPC keys, discover supported networks, and check usage and billing with a scoped SolidRPC account token. Includes account support tools and an optional local read-only mode.

Enables Claude Desktop to interact with 57 AWS services using over 200 tools and local machine profiles. It supports multi-profile configurations and features a read-only safe mode by default to manage infrastructure like EC2, S3, and Lambda securely.

MCP server for the Longhorn distributed storage manager API, enabling full read/write management of volumes, snapshots, backups, and other resources, with optional read-only mode and stdio/HTTP transports.

Enables connecting to a Kubernetes cluster to manage resources and troubleshoot workloads with kubectl and Helm operations, including logs, scaling, port forwarding, and non-destructive mode.

A read-only MCP server for the Cisco Meraki Dashboard API that exposes 50 GET endpoints for understanding network topology from organization down to individual devices and ports.

An MCP server that lets agents such as Claude, Cursor, and Codex operate a CapRover server, installed with npx or Docker and defaulting to a readonly safety mode. It is planned to expose the CapRover API as named tools and as Code Mode search/execute operations, with access modes and confirmation for destructive calls.

An MCP server for securely executing Python code, supporting STDIO, Streamable HTTP, and SSE transports, with easy deployment on Heroku.

Sign in, create API keys, print OpenAI-compatible env vars, and check credits from the terminal. Optional MCP mode for AI coding agents with tools for credits, models, and environment.

Enables read-only access to Microsoft Fabric data-pipeline run history and DAX queries against semantic models, with optional write mode for pipeline execution and dataset refresh.

Enables VS Code agent mode to inspect Azure CycleCloud clusters and optionally manage cluster lifecycle via a stdio MCP server.

This MCP server enables AI agents to interact with ServiceNow instances, providing typed tools to query, create, update, aggregate, and run background scripts, with read-only mode and a --doctor connection check.

Enables secure, read-only access to Amazon Redshift data warehouses for AI assistants, allowing schema inspection, query execution, and data understanding.

Enables developers to manage Genesys Cloud Function Data Actions through natural language in Cursor, including validating, building, planning, and applying function deployments while enforcing safety controls like plan-before-apply and read-only mode.

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.

Enables secure cloud-based execution of code across 14+ programming languages within a sandboxed environment. It supports file management, standard input/output handling, and automatic generation of visual artifacts like plots and charts.

Enables clients to discover capabilities and compose tool calls with structured responses through a remote MCP endpoint running on Cloudflare Workers.

A token-efficient MCP server for the Heroku Platform API that uses a search-and-execute pattern to minimize context window overhead. It enables secure app management through just-in-time endpoint discovery and built-in safety guardrails for API mutations.

Enables LLM agents to operate Cloud.ru MLSpace public API v2 through 17 action-based tools covering training, inference, notebooks, TensorBoards, workspaces, allocations, queues, Docker Registry, data transfer, and resource catalog, with read-only mode, dry-run, and confirmation gates for irreversible actions.

Enables Claude Code to use Alibaba Cloud Token Plan models via a local proxy that maps Anthropic-style model names to Alibaba IDs and provides missing endpoints like model discovery.

An MCP (Model Context Protocol) server that enables AI assistants to manage Exoscale cloud infrastructure. Supports both stdio and Streamable HTTP transports with read-only mode enabled by default for safety.

Enables executing SQL queries on DuckDB databases locally or on MotherDuck cloud, with support for multiple databases, read-only mode, and Claude Desktop integration.

An experimental fork of tableau-mcp that adds an EAS (external authorization server) authentication mode, enabling per-user embedding and REST sign-in with RS256-signed JWTs for Tableau Cloud.

Enables interaction with Croit Ceph clusters through their REST API with 580 endpoints, automatic token optimization, built-in filtering, and role-based access control. Features hybrid mode tools that reduce complexity while providing full cluster management capabilities.

MCP server for IBM Code Engine — build, push, and deploy containers from Cursor, Copilot, Claude, and Cline using natural language.

MCP server for managing cPanel accounts and WHM servers via UAPI/WHM APIs. Supports domains, DNS, email, MySQL, files, cron, SSL, PHP, backups, and hosting accounts across multiple environments with read-only mode and security controls.

Remote MCP server for MuleSoft APIs that enables agents to discover operations and execute validated API calls with a fixed low-context tool surface.

Lets an MCP client query, compare, and blind-judge dozens of Bedrock text models, generate and edit images, start video jobs, and compute embedding similarities through nine tools using a single set of AWS credentials.

A Model Context Protocol server that enables large language models to upload files directly to Alibaba Cloud Object Storage Service (OSS), supporting multiple OSS configurations and specified upload directories.