Sandbox
13 repos for openai · Connectors · DocsClear
shinpr/
mcp-image

MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Supports Nano Banana (Gemini), OpenAI GPT Image, and BytePlus Seedream.

161
sammcj/
mcp-llm
sammcj/mcp-llmConnectors

An MCP server that provides LLMs access to other LLMs

78
kocakli/
Trello-Desktop-MCP

Trello integration for Claude Desktop via Model Context Protocol (MCP) - 19 tools for comprehensive board, card, and list management

38

A third-party Perplexity MCP/REST API implementation that leverages Pro account Pool to provide unlimited quota for ask and deep search capabilities.

165
lansespirit/
image-gen-mcp

An MCP server that integrates with gpt-image-1 & Gemini imagen4 model for text-to-image generation services

69

A Model Context Protocol (MCP) server implementation that integrates with the Nutrient Document Web Service (DWS) Processor API, providing powerful PDF processing capabilities for AI assistants.

70
joshuaswarren/
remnic

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

198
caura-ai/
caura
caura-ai/cauraConnectors

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

497
PiaoyangGuohai1/
cli-anything-zotero

CLI server for Zotero 7/8/9 — let AI manage your library. 70+ CLI commands for search, import, PDF, BibTeX, notes, and more. Works with Claude, Cursor, ChatGPT.

132

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.

413
firish/
webfetch
firish/webfetchConnectors

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with query-dependant TTL that no API offers.

55