
Afferens
io.github.afferensPublished by GitHub account afferensv0.2.1Updated Oct 24, 2026
Real-time physical perception for AI agents — vision, spatial, acoustic, environmental
Overview
Afferens is a local MCP server that gives AI assistants live physical sensor data — vision, spatial, acoustic, environmental, molecular and node health.
- What you can do
- Query live perception events by modality (vision, spatial, acoustic, environmental, molecular, interoception) with filtering and limits, using an API key. Fetch a demo feed across all six modalities without a key. Verify feed freshness by pulling two snapshots and returning headers, age and a hash-based live/stale/unchanged verdict.
- When to use it
- Use it when an assistant needs to reason over real-time physical-world sensor readings rather than static data, for example to inspect detected objects, positions, sounds or environmental conditions, or to check whether a sensor feed is genuinely live.
- Requirements
- Runs as a local Node.js process via npx from the npm package, or in HTTP mode on a configurable port for remote clients. The perceive and verify tools need an AFFERENS_API_KEY, supplied as an environment variable; the demo tool works without one. A free tier is offered at sign-up.
Installation
In SourceWeft
- Open Afferens in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
@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
Modalities: VISION / SPATIAL / ACOUSTIC / ENVIRONMENTAL / MOLECULAR / INTEROCEPTION
Quick Start
Free tier: 10,000 tokens, no card required. Get your key at afferens.com.
Local MCP Clients
Then set your key:
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:
Then register the endpoint:
Claude Desktop / Cursor / Windsurf
Add to your MCP config file:
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.jsonin your project root - Windsurf:
~/.codeium/windsurf/mcp_config.json
Try it without a key
Call afferens_demo - no API key needed.
Usage
Once connected, your AI agent can call:
Returns structured perception events your agent can reason over and act on.
For demo verification:
Returns two raw snapshots plus headers, age, and a hash check so you can show whether the feed is live, stale, or unchanged.
Links
- afferens.com - sign up, dashboard, API docs
- npm
- Smithery
License
MIT
Source: README.md at commit d0f9687
Tools
0Version history
1- v0.2.1LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.