Skip to main content

MCP server — let any LLM agent identify an appliance and pull its grounded, safety-checked, robot-executable operation package from OPERANDI.

Project description

OPERANDI MCP Server — operate real appliances from any agent

operandi_mcp_server.py exposes OPERANDI over the Model Context Protocol so any MCP-capable agent host (Claude Desktop, Claude Code, or your own agent runtime) can identify an appliance and pull its grounded, safety-checked, robot-executable operation package as native tools.

This is the "build for agents" surface: the customer is a robot's planner / an LLM agent, not a human reading PDFs.

Tools

Tool What it does
identify_appliance Resolve observed nameplate text / panel labels / model → a catalog object (call first).
get_operation_package The robot-executable package: model-exact procedures, control map + grounding, per-step verification signals, recovery state machine, safety envelope.
list_appliances Browse operable appliances (optionally by category).
find_by_capability Find appliances by function (heat / wash / brew / defrost …).

Why an agent wants this

A general model, cold, gives confidently-wrong physical instructions on ordinary appliances a large fraction of the time (OPERANDI Stage A: 24% of cold instructions were would-fail, including invented buttons and cycles). Grounded in the package these tools return, that fell to 0 hallucinations, 96% exact. The tools turn "guess the buttons" into "read the manufacturer's ground truth". See ../docs/BUSINESS_MODEL.md.

Setup — zero config

pip install operandi-mcp

That's it. No key needed for your first packages: on first use the server mints an instant trial key itself (POST /v1/trial — no signup, 2 operation packages included, cached at ~/.operandi/mcp_key). When the trial is spent, tool responses tell the agent exactly how to sign up free (10 packages/month) or go Pro.

Have a key already? Set it and it wins over the trial:

export OPERANDI_API_KEY=ok_live_...

Claude Desktop / Claude Code config

{
  "mcpServers": {
    "operandi": { "command": "operandi-mcp" }
  }
}

(Optionally add "env": {"OPERANDI_API_KEY": "ok_live_..."} once you have an account key.)

Then ask the agent: "Identify the Samsung ME20H705MSS and give me the safe procedure to defrost 0.5 kg of mince." — it will call identify_appliance then get_operation_package and answer from grounded data.

Notes

  • The server is a thin, API-key-authenticated REST client — the same binary works against local dev or the hosted service by changing OPERANDI_API_URL.
  • Auth is Authorization: Bearer <key>; a missing/invalid key surfaces as a tool error, not a crash.
  • Transport is newline-delimited JSON-RPC 2.0 (the MCP stdio transport). Offline protocol tests: pytest tests/test_mcp_server.py.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

operandi_mcp-1.0.2.tar.gz (7.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

operandi_mcp-1.0.2-py3-none-any.whl (7.1 kB view details)

Uploaded Python 3

File details

Details for the file operandi_mcp-1.0.2.tar.gz.

File metadata

  • Download URL: operandi_mcp-1.0.2.tar.gz
  • Upload date:
  • Size: 7.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.14

File hashes

Hashes for operandi_mcp-1.0.2.tar.gz
Algorithm Hash digest
SHA256 25727d1ea8d7479465a808ad28ebb8575b6150e69d968dfacaf1a70f99fb03d7
MD5 ccbf77eb6c192d9b4fa39e84f12dd665
BLAKE2b-256 3674b78990643a1948dbbc4f0bb86ece965fa282adb88f8ebc3b095eb3c87b9f

See more details on using hashes here.

File details

Details for the file operandi_mcp-1.0.2-py3-none-any.whl.

File metadata

  • Download URL: operandi_mcp-1.0.2-py3-none-any.whl
  • Upload date:
  • Size: 7.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.14

File hashes

Hashes for operandi_mcp-1.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 4f524c0f1fa66d6dddb5ea35162cb49064242209a3374817b689bd0bffb9002f
MD5 73ec3efbb70c9d01b8d3974e4157167a
BLAKE2b-256 fcedeeefdd104704979abb7058deda2e231a1b3d7a0fb4b585f9a9cad2ce0895

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page