ChatWise

Private, free, open-source local AI chat and MCP host. Run 1000+ LLMs on your device, connect any MCP server (STDIO, HTTP, SSE) and use tools with local or cloud models - no cloud API required

FullMention gives you structured visibility data from ChatGPT and Gemini in one single API call per keyword. Pull brands, websites, and products simultaneously without running 20+ separate query loops. Save massive API costs while unlocking complete market dominance insights.

Open-source AI Agent for VS Code and JetBrains that autonomously solves coding tasks end-to-end.

MCP (Model Context Protocol) Server for Sychev Lab - provides access to products, articles, tutorials, and e-commerce features located in https://lab.sychve.xyz

Gateway connector between LLM agents and world data. Official Model Context Protocol server for the Sugra API, backed by a bundled endpoint catalog and operation_id calls. Works with Anthropic Claude, OpenAI GPT, Google Gemini, xAI, and any MCP-enabled IDE. Client details: Anthropic Claude: Claude Desktop, Claude Code (CLI), claude.ai (web) OpenAI GPT: ChatGPT (via MCP connector) Google Gemini: Gemini CLI, Gemini Code Assist (VS Code + JetBrains) xAI: Remote MCP Tools in xAI SDK and Responses API IDEs: VS Code (native), Cursor, Zed, Cline, Continue.dev, Windsurf Custom agents: anything built on the Python or TypeScript MCP SDK

Advanced multimodal AI music generator with realistic vocals and pro-level arrangements.

**Myriade** is the AI-native data platform for exploring, cataloging, and governing data warehouses. This MCP server exposes Myriade's data analyst capabilities to any compliant client (Claude Desktop, Cursor, VS Code, Copilot, etc.). Once connected, your AI client can: - **Discover** — `list_databases`, `list_tables`, `get_table_schema`, `get_database_info` - **Sample & query** — `sample_data`, `query` (read-only, governance-enforced) - **Browse the catalog** — `search_catalog`, `read_asset`, `update_asset` (descriptions, tags, status) - **Ask the analyst** — `ask` runs Myriade's data analyst agent end-to-end on a natural-language question, returning a synthesized answer with deep links into the Myriade UI for queries, charts, and documents All requests are scoped to the authenticated user's organization, run in read-only mode, and respect Myriade's governance policies (PII masking, table-level ACLs). **Auth:** OAuth 2.1 with Dynamic Client Registration. Sign in once with your Myriade account; tokens are scoped to your org. **Self-host:** Available — see https://github.com/myriade-ai/myriade-private for setup. The hosted version at `app.myriade.ai` is the easiest way to try it.

Local MCP server exposing iGPSport cycling data to LLM clients. Computes training metrics (NP/IF/TSS/CTL/ATL/TSB) server-side, supports 17 tools including activity analysis, segment leaderboards, workout generation, and threshold estimation.

The AI Code Editor

One hosted MCP endpoint for a large catalog of production integrations—CRM, billing, data, dev tools, and more. Connect OAuth or API keys in the dashboard, then use one MCP URL (Hub or per-bundle) in Cursor, Claude, or other MCP clients. Includes workspace-scoped credentials, the open-source mcpbundles CLI on PyPI, and optional code-execution tools on the Hub.

devops-mcp lets AI assistants (Claude Desktop, Cursor, Windsurf) connect, scan, plan, and deploy on real Linux servers — without handing the model the keys to the kingdom. Reading is always allowed; anything that changes state on a production-like server is refused unless the user pastes a secret elevation token the model never sees. Three modes (SAFE / PROVISION / FULL) with auto-expiry, a production write-gate that demands backup confirmation for irrecoverable ops, shell-quoted arguments, prompt-injection-tagged output, and a full JSON-lines audit log. 32 tools, TypeScript, MIT.

SEO research tools for AI agents: keyword research and metrics, SERP and local SERP results, domain and backlink analysis, rank tracking, and Google Search Console performance.

Overreach catches AI-agent scope creep. You give it the prompt you gave your coding agent and the diff it produced; it flags every part of the diff the prompt didn't authorize — unauthorized dependencies, env vars, endpoints, cron jobs, files, and features. Every finding is deterministic set arithmetic (actual − authorized), not a probabilistic opinion. Ships a GitHub Action that fails PRs on scope_creep_score=HIGH. MIT, free to use.

Visual Studio Code

E2Easy is a codeless end-to-end testing platform that lets non-technical users and founders create, manage, and run automated browser tests without writing a single line of code. It combines a browser extension for manual recording with an AI-powered Claude Connector that lets you describe tests in plain English.

Enables cloud-based AI services to access local Stdio based MCP servers via HTTP requests