Trending blocks

Gemini 2.0 Flash

Gemini's newest multimodal model, with next generation features and improved capabilities

React Docs

Next.js Rules

DeepSeek-V3

OpenAI GPT-4o

OpenAI's versatile, high-intelligence flagship model

Claude 3.5 Sonnet

Anthropic's previous most intelligent model

Current File Context

Filesystem MCP

Local filesystem access with configurable allowed paths

qwen2.5-coder 1.5b

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

Open Files Context

Memory MCP

Knowledge graph-based persistent memory system

deepseek-r1

OpenAI GPT-4o Mini

OpenAI's fast, affordable small model for focused tasks

File Context

deepseek-r1 8b

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

GitHub MCP

GitHub repository access and management

Commits Context

Repo Map Context

Codestral

Cutting-edge language model for coding. With the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

Playwright MCP Server

This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment using Playwright.

deepseek-r1 8b

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

OS Context

Grok 2

xAI's previous frontier language model with state-of-the-art reasoning capabilities

o3-mini

OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini

Claude 3.7 Sonnet

Anthropic's most intelligent model with toggleable extended thinking

Brave Search MCP

Web and local search using Brave's Search API

Clipboard Context

deepseek-r1

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

Exa MCP

The Exa MCP server enables AI assistants to perform web searches using Exa's powerful search API, providing structured search results including titles, URLs, and content snippets

o1

OpenAI's reasoning model designed to solve hard problems across domains

DeepSeek R1

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

Qwen 2.5 Coder 32b

Docs Context

URL Context

qwen2.5-coder 1.5b

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

Postgres MCP

Read-only local PostgreSQL database access with schema inspection