{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_72na5w56utau","handle":"mcp-spatial-perception","url":"https://wellknown.network/agents/mcp-spatial-perception","links":{"self":"https://wellknown.network/agents/mcp-spatial-perception/record.json","html":"https://wellknown.network/agents/mcp-spatial-perception","markdown":"https://wellknown.network/agents/mcp-spatial-perception/record.md","api":"https://wellknown.network/api/v1/agents/mcp-spatial-perception","status":"https://wellknown.network/api/v1/agents/mcp-spatial-perception/status","claim":"https://wellknown.network/agents/mcp-spatial-perception/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-spatial-perception/claim.json","badge":"https://wellknown.network/agents/mcp-spatial-perception/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-spatial-perception/history","tools":"https://wellknown.network/api/v1/agents/mcp-spatial-perception/tools"},"ard":{"identifier":"urn:air::server:mcp-spatial-perception","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-spatial-perception","summary":"Give your AI agent eyes on the physical world — an MCP server for real-time DePIN edge-vision queries.","description":"# mcp-spatial-perception\n\n[![CI](https://github.com/jamie643/mcp-spatial-perception/actions/workflows/ci.yml/badge.svg)](https://github.com/jamie643/mcp-spatial-perception/actions/workflows/ci.yml)\n[![Publish](https://github.com/jamie643/mcp-spatial-perception/actions/workflows/publish.yml/badge.svg)](https://github.com/jamie643/mcp-spatial-perception/actions/workflows/publish.yml)\n[![PyPI version](https://img.shields.io/pypi/v/mcp-spatial-perception.svg?label=PyPI&color=blue)](https://pypi.org/project/mcp-spatial-perception/)\n[![Python versions](https://img.shields.io/pypi/pyversions/mcp-spatial-perception.svg)](https://pypi.org/project/mcp-spatial-perception/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)\n\n> **Give your AI agent eyes on the physical world.**\n>\n> An [MCP](https://modelcontextprotocol.io) server that exposes real-time spatial perception queries from DePIN edge-vision nodes to any LLM that speaks the Model Context Protocol — Claude Desktop, Cursor, Claude Code, or a custom agent framework.\n\n---\n\n## The problem\n\nLLM agents can read files, browse the web, and call APIs — but they're blind to the physical world. They can't answer questions like:\n\n- *\"Is there foot traffic at location X right now?\"*\n- *\"What is the live visual state of camera node #402?\"*\n- *\"Is the loading dock clear before I dispatch the truck?\"*\n\nThere's no standard way for an agent to ask those questions.\n\n## The solution\n\n`mcp-spatial-perception` is a small, dependency-free MCP server that sits between your agent and a DePIN network of edge-vision nodes. The agent calls a tool, the server queries the network, and structured JSON describing the scene comes back — detections, bounding boxes, confidence scores, environmental state, geolocation.\n\n```\n┌─────────────┐   MC…","publisher":null,"homepage":"https://github.com/jamie643/mcp-spatial-perception","repository":"https://github.com/jamie643/mcp-spatial-perception","version":"0.1.4","license":"MIT","protocols":["mcp"],"tags":["agents","depin","json-rpc","llm","mcp","spatial","vision"],"pricing":null,"endpoints":[{"url":"pypi:mcp-spatial-perception","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":"media.image-understanding","name":"Image Understanding","confidence":1,"provenance":"declared"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.802,"provenance":"derived"}],"categories":["dev","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":"mcp-spatial-perception","registry":"pypi","observedAt":"2026-10-24T17:29:23.066Z","publishedAt":"2026-10-05T23:35:15.456815Z","latestVersion":"0.1.4"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-spatial-perception","url":"https://pypi.org/project/mcp-spatial-perception/","firstSeenAt":"2026-10-06T13:23:19.903Z","fetchedAt":"2026-10-24T17:28:16.627Z","normalizedAt":"2026-10-24T17:28:16.627Z"}]},"firstSeenAt":"2026-10-06T13:23:19.903Z","updatedAt":"2026-10-24T17:29:23.066Z"}