grokandmon-com-mcp.yml
Grok & Mon operates ONE remote MCP server at https://grokandmon.com/mcp/v1 (the same path also answers at /mcp), on the same host as its website and A2A endpoint. It speaks MCP protocol version 2025-06-18, answers initialize and tools/list anonymously, and lists 22 tools - 11 reads over a real cannabis grow tent's IoT sensors (environment, substrate moisture, light, growth stage, history, watering predictions, AI decision log) and 11 actuator writes (light intensity and schedule, exhaust/intake/circulation fans, humidifier, dehumidifier, heat mat, irrigation 10-150 ml, growth-stage transition, observation log), each with a real inputSchema. GET on the endpoint returns a static descriptor document carrying the same tool list. resources/list and prompts/list return -32601. THE CALL SURFACE IS A STUB: tools/call on the read-only get_environment returned HTTP 200 with the text "Tool get_environment acknowledged. Connect to the agent API for live execution." rather than sensor data, so the server enumerates tools but does not execute them; live execution is routed to the /api/* origin, which answered 530 (Cloudflare Tunnel error) throughout this pass. No write tool was invoked. Authorship is the provider's: the tool names are specific to this one grow (Ecowitt GW1100 sensor, GDP Runtz strain) and match no shared platform fingerprint.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport streamable-http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tool quality observed · not scored
tools with readOnly / destructive hints
parameters described (20 total)
state-changing tools without destructiveHint
tool-list tokens (22 tools)
tools over ~1,200 tokens
Unhinted state-changing: set_light_intensity, set_light_schedule, trigger_irrigation, set_growth_stage
From an anonymous initialize + tools/list capture measured 2026-10-20; tokens are chars/3.6 of each tool definition. Recorded for the Kin Score's agent readiness as an observed signal — it contributes no points yet.
Tools
get_environment— Read current temperature, humidity, VPD, and CO2 from grow tent sensors.get_substrate— Read soil moisture levels from Ecowitt GW1100 sensor.get_light_levels— Get current light status, schedule, and intensity.capture_image— Capture a photo from the grow tent webcam.set_light_intensity— Set grow light intensity (0-100%).set_light_schedule— Set light on/off schedule (e.g. 18/6 veg, 12/12 flower).control_exhaust— Set exhaust fan speed (0-100%) for air exchange.control_intake— Set intake fan speed (0-100%).control_humidifier— Turn humidifier on or off.control_circulation_fan— Control internal circulation fan.trigger_irrigation— Water the plant (10-150ml, calibrated pump).get_growth_stage— Get current growth stage.set_growth_stage— Transition to a new growth stage.get_history— Get historical sensor data for trend analysis.log_observation— Log a visual observation about plant health.get_strain_profile— Get strain-specific parameters for GDP Runtz.control_heat_mat— Control seedling heat mat.control_dehumidifier— Turn dehumidifier on or off.get_watering_predictions— Get AI-predicted next watering times.get_ai_decision_history— Get recent AI decision log with reasoning.get_watering_history— Get watering event history.get_hourly_summary— Get aggregated hourly sensor averages.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.