MCP server

PerceptionDLM Region Captioning

hf/hugging-apps/perception-dlm

Checked 26 Oct 2026, 08:30 UTC · Hugging Face reports it running

Parallel region captioning with multimodal diffusion LLM

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

26 Oct 2026, 08:30 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 perception-dlm https://hugging-apps-perception-dlm.hf.space/gradio_api/mcp/

Claude Desktop

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

Codex (config.toml)

[mcp_servers.perception-dlm]
url = "https://hugging-apps-perception-dlm.hf.space/gradio_api/mcp/"

Gemini CLI

{"mcpServers":{"perception-dlm":{"httpUrl":"https://hugging-apps-perception-dlm.hf.space/gradio_api/mcp/"}}}

Cursor

{"mcpServers":{"perception-dlm":{"url":"https://hugging-apps-perception-dlm.hf.space/gradio_api/mcp/"}}}

VS Code

{"servers":{"perception-dlm":{"type":"http","url":"https://hugging-apps-perception-dlm.hf.space/gradio_api/mcp/"}}}

Antigravity

agy mcp add perception-dlm https://hugging-apps-perception-dlm.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":"perception-dlm","server_url":"https://hugging-apps-perception-dlm.hf.space/gradio_api/mcp/","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"perception-dlm","server_url":"https://hugging-apps-perception-dlm.hf.space/gradio_api/mcp/"}

Browse

• Calling other AI models

Related MCP servers

• Omni-Diffusion
  Any-to-any multimodal masked discrete diffusion model
• OneEmo Affective Reasoning
  Unified multimodal reasoning for emotion perception
• Gestalt
  Gestalt unified multimodal discrete diffusion, text-to-image
• AgentBazaar: Beyond Obvious
  Answers past the generic one, A2A agent invoke, and free public Data APIs as compact rows.
• DiffusionGemma 26B A4B FP8 Demo
  Multimodal block-diffusion text generation demo
• RTI - Elastic Token Compression
  Pixel-space t2i with a region-token budget dial
• Geiant Perception
  Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance
• ViewsMeet Pick + Predict
  Read frozen Atlas cells, answer private quizzes, score Mini-IPIP vectors, and cast enum ballots.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/hf/hugging-apps/perception-dlm.svg)](https://aptlynx.net/servers/hf/hugging-apps/perception-dlm)

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