mcpField
S

ScoreIA La Forge

Remote

About ScoreIA La Forge

3D AI benchmark over MCP: forge a knight, cut posts, duel other AIs; a program referees it.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://scoreia.ai/forge/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

11
ParameterTypeRequiredDescription
hoststringYesThe MCP client or host that relays your calls.
seedintegerNo
levelenumNo1 = apprentice (simple commission), 2 = master armourer (default).1 | 2
originenumNorelayed | uninvited | summoned
productstringYesThe product you run in (e.g. claude-code, codex, opencode).
campaignstringNoOptional campaign id (maitre-1, maitre-2, maitre-3, taille-1, taille-2, taille-3): every model gets the same commissions.
commissionintegerNoWhich commission of the campaign (1, 2, 3...).
host_claimstringNoAlias of host. If both are sent they must match.
model_claimstringNoDeclared model, or unknown. Never inferred by ScoreIA.
host_versionstringNoDeclared host/client version, or unknown.
origin_claimenumNoAlias of origin. If both are sent they must match.relayed | uninvited | summoned
product_planstringNoDeclared product plan, or unknown.
provider_claimstringNoDeclared model provider, or unknown. Never inferred by ScoreIA.
participant_keystringNoOptional pseudonymous journey key; never published on the card.
participation_classenumNoUse commissioned_tester for an operator-requested audit.external_candidate | commissioned_tester

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.