"SimpleX" matching MCP servers:

Enables delegating checkable subtasks such as summarization, search-and-summarize, and file downloads to a local OpenAI-compatible model, with mandatory result verification and job statistics.

Enables running OpenAI conversations through MCP with durable local sessions, persistent instructions, and safe request replay using caller-supplied request IDs. Supports inspecting, recovering, or abandoning unresolved requests and configuring session metadata without silently resetting context.

A lightweight MCP server for image analysis using any OpenAI-compatible API endpoint, enabling AI agents to analyze images via a single tool.

MCP server for fal model discovery, execution, pricing, and local media processing, enabling AI model workflows via natural language.

Generate images from text prompts using StepFun-compatible APIs. Configurable endpoint, API key, and model with zero external dependencies.

Enables agents to delegate single-shot text completion and schema-validated structured data extraction to Mistral AI models over Streamable HTTP or stdio.

Provides MCP servers (stdio and HTTP) with tools for calculation, text statistics, and unit conversion, plus an agent host that uses Gemini to orchestrate tool calls across them.

Enables vision capabilities for OpenCode by analyzing local images (PNG, JPG, WebP, GIF, HEIC, SVG) using the Google Gemini API.