{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_aa8yrtu96b6d","handle":"agent-cam-mcp","url":"https://wellknown.network/agents/agent-cam-mcp","links":{"self":"https://wellknown.network/agents/agent-cam-mcp/record.json","html":"https://wellknown.network/agents/agent-cam-mcp","markdown":"https://wellknown.network/agents/agent-cam-mcp/record.md","api":"https://wellknown.network/api/v1/agents/agent-cam-mcp","status":"https://wellknown.network/api/v1/agents/agent-cam-mcp/status","claim":"https://wellknown.network/agents/agent-cam-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agent-cam-mcp/claim.json","badge":"https://wellknown.network/agents/agent-cam-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/agent-cam-mcp/history","tools":"https://wellknown.network/api/v1/agents/agent-cam-mcp/tools"},"ard":{"identifier":"urn:air::server:agent-cam-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"agent-cam-mcp","summary":"Physical camera perception, measurement, and verification tool for MCP AI agents","description":"# Agent Cam MCP Tool\n\nPhysical camera perception, quantitative measurement, and verification tool for MCP AI agents.\n\n[![CI](https://github.com/skr-electronics-lab/agent-cam-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/skr-electronics-lab/agent-cam-mcp/actions/workflows/ci.yml)\n[![PyPI version](https://img.shields.io/pypi/v/agent-cam-mcp.svg)](https://pypi.org/project/agent-cam-mcp/)\n[![Python versions](https://img.shields.io/pypi/pyversions/agent-cam-mcp.svg)](https://pypi.org/project/agent-cam-mcp/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n[![MCP Protocol](https://img.shields.io/badge/MCP-1.3.0-blue.svg)](https://modelcontextprotocol.io/)\n\n---\n\n## 1. Overview\n\nAgent Cam MCP Tool gives AI coding agents eyes on the physical world. It interfaces with USB webcams and RTSP/HTTP network camera streams, exposing them to any Model Context Protocol (MCP) compatible agent (Google Antigravity, Claude Code, OpenAI Codex, Cursor).\n\n### The Problem\nAgents working on embedded systems, robotics, CNC machinery, or 3D printers frequently declare builds or firmware flashes \"successful\" while the physical hardware remains unresponsive, stuck in a boot loop, or displaying error codes. Traditional agents rely solely on build return codes and serial logs.\n\n### The Solution\nAgent Cam MCP Tool allows the agent to inspect the physical hardware at any moment:\n- Returns images directly as MCP image content (like browser screenshots in IDE agents). Nothing is written to disk by default.\n- Returns quantitative numbers alongside visual frames (mean brightness, contrast, lit pixel percentage, dominant colors, edge density, sharpness, and motion level) so agents make decisions on hard evidence.\n- Maintains an in-memory RAM ring buffer so agents can retrieve what happened before an error or correlate visual changes with serial logs.\n- Includes a local developer dashboard to monitor camera feeds, define named regions o…","publisher":null,"homepage":"https://github.com/skr-electronics-lab/agent-cam-mcp","repository":"https://github.com/skr-electronics-lab/agent-cam-mcp/blob/main/CHANGELOG.md","version":"0.1.1","license":"MIT","protocols":["mcp"],"tags":["3d-printing","agentic-ai","ai-agents","antigravity","camera","claude-code","cnc","codex","computer-vision","cursor","dashboard","developer-tools","esp32","fastapi","hardware","hardware-in-the-loop","iot","mcp","mcp-server","model-context-protocol","opencv","python","robotics","vision","webcam"],"pricing":null,"endpoints":[{"url":"pypi:agent-cam-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"infra.devices","name":"Devices & IoT","confidence":1,"provenance":"declared"},{"slug":"analytics.reporting","name":"Reporting & Dashboards","confidence":1,"provenance":"declared"},{"slug":"media.image-understanding","name":"Image Understanding","confidence":1,"provenance":"declared"},{"slug":"media.3d","name":"3D & Design","confidence":0.906,"provenance":"derived"}],"categories":["analytics","infra","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"agent-cam-mcp","registry":"pypi","observedAt":"2026-10-24T17:28:36.560Z","publishedAt":"2026-10-04T18:05:19.278470Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"agent-cam-mcp","url":"https://pypi.org/project/agent-cam-mcp/","firstSeenAt":"2026-10-06T13:22:24.273Z","fetchedAt":"2026-10-24T17:26:37.110Z","normalizedAt":"2026-10-24T17:26:37.110Z"}]},"firstSeenAt":"2026-10-06T13:22:24.273Z","updatedAt":"2026-10-24T17:28:36.560Z"}