Schema | game-agent-harness

game-agent-harness

Describes the environment variables required to run the server.

Name	Required	Description	Default
`workspace-root`	Yes	Absolute path to the workspace root. Passed to the MCP server as the --workspace-root argument.

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
list_scenariosA	List scenario files allowed within this workspace.
run_scenarioA	Run one allowlisted scenario path relative to the scenarios directory.
soak_scenarioB	Repeat an allowlisted scenario within the server's hard run limit.
read_reportA	Read report.json from one direct child of the workspace artifacts directory.
run_visual_scenarioB	Run one allowlisted scenario containing VisualProbe steps.
read_visual_reportB	Read VisualProbe JSON reports from one direct artifact directory.
list_visual_artifactsB	List safe PNG files directly inside an artifact directory's visual folder.
read_visual_artifactB	Read one safe PNG as an MCP image content block.
compare_visual_runsC	Return the VisualProbe reports for two confined artifact directories.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TheBulaDev/game-agent-harness'

If you have feedback or need assistance with the MCP directory API, please join our Discord server