Skip to main content
Glama
@afferens/mcp-server

@afferens/mcp-server

by afferens

@afferens/mcp-server

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.

Tools

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

Related MCP server: Hayba

Quick Start

Free tier: 10,000 tokens, no card required. Get your key at afferens.com.

Local MCP Clients

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.

Remote MCP Clients

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"
  }
}

Claude Desktop / Cursor / Windsurf

Add to your MCP config file:

{
  "mcpServers": {
    "afferens": {
      "command": "npx",
      "args": ["-y", "@afferens/mcp-server"],
      "env": {
        "AFFERENS_API_KEY": "YOUR_KEY"
      }
    }
  }
}

Config file locations:

  • Claude Desktop (Mac): ~/Library/Application Support/Claude/claude_desktop_config.json

  • Claude Desktop (Windows): %APPDATA%\Claude\claude_desktop_config.json

  • Cursor: .cursor/mcp.json in your project root

  • Windsurf: ~/.codeium/windsurf/mcp_config.json

Try it without a key

{
  "mcpServers": {
    "afferens": {
      "command": "npx",
      "args": ["-y", "@afferens/mcp-server"]
    }
  }
}

Call afferens_demo - no API key needed.

Usage

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.

License

MIT

Available Tools

5 tools
afferens_actuateA

Send a command to a physical Afferens node. Use this to trigger actions on hardware — capture a camera frame, sound an alarm, move to coordinates, rotate a camera, lock or unlock, adjust a sensor, or shut down a node. Costs 5 Sense Tokens per command. Requires AFFERENS_API_KEY.

Inputs: command_type (required), target_node_id (required), parameters.

afferens_demoA

Get real-time physical perception data from all 6 Afferens sensory modalities — VISION, SPATIAL, ACOUSTIC, ENVIRONMENTAL, MOLECULAR, and INTEROCEPTION. No API key required. Use this to demonstrate what live sensor data looks like before your AI agent is fully wired up. Free to call.

Inputs: no named parameters.

afferens_ingestA

Push live sensor data into the Afferens sensory layer. Use this when your AI agent is connected to physical hardware and wants to contribute real-time perception events. The data becomes queryable via afferens_perceive. Requires AFFERENS_API_KEY.

Inputs: data (required), modality (required), classification.

afferens_perceiveA

Query live physical perception events from the Afferens sensory layer. Returns real-time sensor data your AI agent can act on — object detections, positions, sounds, environmental readings, chemical traces, and node health. Requires AFFERENS_API_KEY (free tier: 10,000 tokens, no card required — sign up at afferens.com).

Inputs: limit, modality.

afferens_verifyA

Fetch the live perception feed twice with a short delay, then return both raw payloads plus a hash-based freshness check. Use this as a demo proof bundle when you need to show the feed is not placeholder data.

Inputs: limit, wait_ms, modality.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: demo for raw data, perceive for querying, actuate for hardware commands, verify for freshness check, ingest for pushing data. No overlap.

    Naming Consistency5/5

    All tool names follow a consistent pattern: 'afferens_' + a verb (demo, perceive, actuate, verify, ingest). Perfectly predictable.

    Tool Count5/5

    With 5 tools covering demo, perception, actuation, verification, and ingestion, the count is well-scoped for a sensory data platform. Not too sparse or bloated.

    Completeness5/5

    The tool set provides a complete lifecycle: demo, query, send data, actuate hardware, and verify freshness. No obvious gaps for the domain of physical perception.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers