Skip to main content
Glama

Launch session

gameye_launch_session

Launch a containerized Gameye game server session with configurable image, location, TTL, env, and args, returning the session ID, host, and ports for immediate use.

Instructions

Start a containerized game server session on the Gameye platform. Returns the session ID, host and ports. Starts a billable session in the environment shown in the result prefix. When no ttl is given, a 30m TTL is applied and reported. The label launched-by=gameye-mcp is always sent and replaces any launched-by value you pass; if a warm pool serves the image and region, the server ignores request labels (and env and args), so warm-pool sessions do not carry it. The launch is refused, with nothing sent, if any env value, arg or label contains this server's Gameye API token. It is also refused if the ttl is above 4h, if 5 sessions started by this server are already running, or after 20 launches by this server process; these limits are set by the user when the server starts, and a refusal says which one applied. Pass dryRun=true to preview the request. Needs GAMEYE_API_TOKEN; without one, returns setup steps and sends nothing.

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": {
      "location": "<location>",
      "image": "<image>"
    },
    "name": "gameye_launch_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoCustom session ID; auto-generated if omitted. IDs are unique across all of Gameye, so derive it from a UUID. A 409 whose describe returns 404 means another customer owns the ID: retry with a fresh one. Warm-pool launches ignore it; always read the ID from the result
envNoEnvironment variables passed to the container
ttlNoSession time-to-live, e.g. '1h', '30m'. Session auto-stops after this duration. Defaults to 30m; at most 4h
argsNoCommand-line arguments passed to the container entrypoint
imageYesDocker image name to run (e.g. 'csgo', 'tf2')
dryRunNoReturn the exact request that would be sent, with the API token masked, and send nothing
labelsNoArbitrary key-value labels for filtering/grouping
restartNoAutomatically restart the container on exit
versionNoDocker image tag/version to use
locationYesRegion/datacenter to host the session (e.g. 'europe', 'us-east')

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.3

TDQS

A4.6/5.0
Behavior5/5

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

Extremely rich beyond the annotations: discloses billing, the environment encoded in the result prefix, the 30m default TTL, forced label override (launched-by=gameye-mcp), warm-pool behavior that ignores labels/env/args, and four distinct refusal conditions (token in payload, ttl >4h, 5 concurrent sessions, 20 launches per process) with confirmation that a refusal identifies which limit applied. Nothing here contradicts readOnlyHint=false / destructiveHint=false / openWorldHint=true.

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?

Front-loaded with purpose and return value, then constraints in priority order; no filler sentences. It is dense and runs several constraints together in long clauses, but each clause carries distinct operational information.

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

Completeness5/5

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

For a 10-parameter open-world mutation tool with nested objects and no output schema, the description covers return values, defaulting, credential requirements, quota limits, and pre-flight validation. An agent has everything needed to call it correctly or predict a refusal.

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 schema already documents every field and the baseline is 3. The description adds cross-cutting meaning the schema cannot: how labels are overwritten, how ttl limits and defaults interact with the refusal rules, and that env/args/labels are scanned for the API token before anything is sent.

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

Purpose5/5

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

States a specific verb and resource ('Start a containerized game server session on the Gameye platform') and immediately declares the return payload ('session ID, host and ports'). This cleanly separates it from sibling lifecycle tools like gameye_stop_session, gameye_describe_session and gameye_list_sessions without needing to name them.

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

Usage Guidelines4/5

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

Gives concrete usage context: billable session, dryRun=true to preview, and GAMEYE_API_TOKEN required or it returns setup steps and sends nothing. It does not explicitly name alternative tools or say when not to launch (e.g. instead of reusing an existing session), so it stops short of full routing guidance.

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