Skip to main content
Glama
Connect IQ MCP

Connect IQ MCP

by idoo

Run app in simulator

sim_run

Runs a Connect IQ PRG or builds a project for a device in the simulator, starting it if needed; returns a session ID plus crash details and runs filtered unit tests with parsed reports.

Instructions

Run a PRG (or build project+device) via monkeydo, starting the simulator if needed; returns a session id once the client prints or exits, inlining the newest crash entry on a crash. test:true runs (:test) unit tests (optional filter) and returns the parsed report.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "device": "<device>"
    },
    "name": "sim_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNodeveloper key (.der) inside the root; default CIQ_MCP_KEY; needed when building
prgNoPRG inside the root; omit to build project
sdkNoinstalled SDK version or dir name; custom SDK only via CIQ_MCP_SDK
testNorun (:test) unit tests: build with -t or take a test PRG, run monkeydo -t, return the parsed report (exit code ignored)
deviceYesdevice id, e.g. fenix7
filterNowith test: run only this test name (letters, digits, _ . * : -; no leading -)
projectNoproject dir inside the root to build (default: root)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations it discloses meaningful behavior: the simulator is started if needed, a session id is returned only once the client prints or exits (i.e., blocking semantics), the newest crash entry is inlined on a crash, and in test mode the exit code is ignored and a parsed report returned. What is missing is timing/timeout behavior and what happens to an already-running simulator, but the added context is substantial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences, front-loaded with the primary action and with the test mode clearly separated by the 'test:true' clause. The semicolon-chained jargon (monkeydo, PRG, :test) is compact but slightly opaque to a newcomer; nothing is wasted though.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so: session id, inlined crash entry, parsed test report. For a 7-parameter, non-idempotent execution tool the remaining gaps are operational details (blocking duration, simulator lifecycle, log retrieval) rather than anything that would cause a wrong invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description goes further by explaining the interaction between parameters — prg omitted means build project+device, test:true switches to unit-test mode with an optional filter, and key is needed when building. It does not explain the sdk override path (CIQ_MCP_SDK only) beyond what the schema already says.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run a PRG ... via monkeydo') and covers both modes: plain run (prg or build project+device) and unit-test run with test:true. It is clearly distinct from sim_logs/sim_stop, but it never names sdk_build as the alternative for pure building, so sibling differentiation is only implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Guidance is internal to the tool: omit prg to build, set test:true to run unit tests, filter to narrow them. There is no explicit when-to-use-this-vs-alternative guidance (e.g., when to use sdk_build instead of the build path here, or when to follow up with sim_logs/sim_stop), so usage is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.