Connects AI agents to live sensor feeds across six modalities: vision, spatial, acoustic, environmental, molecular, and interoception. Exposes three tools: afferens_demo for free multi-modal perception data, afferens_perceive for filtered event queries by modality, and afferens_verify for timestamped proof bundles that let you confirm feed freshness. Works over stdio for local clients or HTTP for hosted setups. Reach for this when your agent needs to ground decisions in real-world sensor readings rather than static data, whether you're building monitoring workflows, physical automation, or verification systems that need to prove perception happened at a specific moment.
MCP server for Afferens - real-time physical perception for AI agents.
Use it from local MCP clients over stdio or remote/hosted clients over streamable HTTP. It gives any MCP-compatible AI assistant live sensor data: object detections, positions, sounds, environmental readings, chemical traces, and node health.
| Tool | Auth | Description |
|---|---|---|
afferens_demo | None | Live perception data across all 6 modalities. Free, no key needed. |
afferens_perceive | API key | Query live events by modality with filtering and limits. |
afferens_verify | API key | Fetch the feed twice and return a proof bundle with headers, age, and a freshness verdict. |
Modalities: VISION / SPATIAL / ACOUSTIC / ENVIRONMENTAL / MOLECULAR / INTEROCEPTION
Free tier: 10,000 tokens, no card required. Get your key at afferens.com.
claude mcp add afferens -- npx -y @afferens/mcp-server
Then set your key:
claude mcp add afferens -e AFFERENS_API_KEY=YOUR_KEY -- npx -y @afferens/mcp-server
This stdio setup works for Claude Code, Claude Desktop, Cursor, and Windsurf.
For hosted or browser-based clients, run Afferens in HTTP mode and point the client at the /mcp endpoint:
AFFERENS_TRANSPORT=http AFFERENS_PORT=8790 AFFERENS_API_KEY=YOUR_KEY node dist/index.js
Then register the endpoint:
{
"afferens": {
"url": "http://127.0.0.1:8790/mcp",
"bearer_token_env_var": "AFFERENS_API_KEY"
}
}
Add to your MCP config file:
{
"mcpServers": {
"afferens": {
"command": "npx",
"args": ["-y", "@afferens/mcp-server"],
"env": {
"AFFERENS_API_KEY": "YOUR_KEY"
}
}
}
}
Config file locations:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json.cursor/mcp.json in your project root~/.codeium/windsurf/mcp_config.json{
"mcpServers": {
"afferens": {
"command": "npx",
"args": ["-y", "@afferens/mcp-server"]
}
}
}
Call afferens_demo - no API key needed.
Once connected, your AI agent can call:
afferens_perceive({ modality: "VISION", limit: 5 })
Returns structured perception events your agent can reason over and act on.
For demo verification:
afferens_verify({ modality: "VISION", limit: 3, wait_ms: 2000 })
Returns two raw snapshots plus headers, age, and a hash check so you can show whether the feed is live, stale, or unchanged.
MIT