MCP server

Perceive-to-Reason

hf/hongxingli/perceive-to-reason

Checked 28 Oct 2026, 09:04 UTC · Hugging Face reports it running

P2R fine-grained visual reasoning with Qwen3-VL

Website

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

28 Oct 2026, 09:04 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http perceive-to-reason https://hongxingli-perceive-to-reason.hf.space/gradio_api/mcp/

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.perceive-to-reason]
url = "https://hongxingli-perceive-to-reason.hf.space/gradio_api/mcp/"

Gemini CLI

{"mcpServers":{"perceive-to-reason":{"httpUrl":"https://hongxingli-perceive-to-reason.hf.space/gradio_api/mcp/"}}}

Cursor

{"mcpServers":{"perceive-to-reason":{"url":"https://hongxingli-perceive-to-reason.hf.space/gradio_api/mcp/"}}}

VS Code

{"servers":{"perceive-to-reason":{"type":"http","url":"https://hongxingli-perceive-to-reason.hf.space/gradio_api/mcp/"}}}

Antigravity

agy mcp add perceive-to-reason https://hongxingli-perceive-to-reason.hf.space/gradio_api/mcp/

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"perceive-to-reason","server_url":"https://hongxingli-perceive-to-reason.hf.space/gradio_api/mcp/","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"perceive-to-reason","server_url":"https://hongxingli-perceive-to-reason.hf.space/gradio_api/mcp/"}

Related MCP servers

• OpenCaption-4B-VL-SFT
  Dense fine-grained image captioning with Qwen3-VL-4B
• VIEW2SPACE-4B
  Multi-view visual reasoning VLM based on Qwen3-VL 4B
• ZwZ2-4B
  Multi-region visual reasoning VLM (Qwen3.5-4B, RL-trained)
• Qwen3.8 27B Object Detection
  Unleash the Power of Visual Grounding
• Qwen3 VL HF Demo
  Object Detection, Visual Grounding, Keypoint Detection
• Brainkb
  MCP server for querying BrainKB, a knowledge base for neuroscience knowledge graphs.
• Qwen3.8 Spatial
  Spatial reasoning with Qwen3.8-27B
• Bsp
  Persistent agent memory & identity on federated beaches — one bsp() function over pscale blocks.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/hf/hongxingli/perceive-to-reason.svg)](https://aptlynx.net/servers/hf/hongxingli/perceive-to-reason)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents