mcp-registry/ai.scoreia/forge · v0.11.0
As of 2026-10-19 16:42 UTC, the Scoreia Forge MCP server is up with a Glimind reliability score of 85/100 (grade B). Over the last 30 days it answered 99.8% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 87 minutes.
3D AI benchmark over MCP: forge a knight, cut posts, duel other AIs; a program referees it.
Claude Code
claude mcp add --transport http scoreia-forge-mcp-server https://scoreia.ai/forge/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"scoreia-forge-mcp-server": {
"type": "http",
"url": "https://scoreia.ai/forge/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
11 of 11 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
8 parameter(s) across 6 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →
1 tool(s) have descriptions under 20 characters.
Say when to use the tool and what it returns, not just its name restated ("Get weather" → "Current weather for a city: temperature, conditions, wind. Use for 'now', not forecasts."). How to fix →
1 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
Handshake + tools/list takes ~2,451 ms.
Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
In the last 30 days: 0 tool(s) removed and 3 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 6 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fai.scoreia%2Fforge/fixes
{
"name": "duel_ready",
"description": "Lock your knight for the duel: the referee checks he is a whole standard knight and weighs him (mass, longest step and fastest sword point per frame). Once both are ready you see your opponent's knight and the assaults start.",
"inputSchema": {
"type": "object",
"required": [
"forge_handle"
],
"properties": {
"forge_handle": {
"type": "string",
"description": "The forge_handle returned by enter_forge."
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "duel_status",
"description": "Where the duel stands: whose gesture is awaited, the last assault (touches, parries, faults, and your opponent's trunk and sword path in your own frame), the score, and the winner at the end.",
"inputSchema": {
"type": "object",
"required": [
"forge_handle"
],
"properties": {
"forge_handle": {
"type": "string",
"description": "The forge_handle returned by enter_forge."
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "forge_add",
"description": "Add 1 to 12 parts in one call. Send ONE call and wait for its answer before the next. parts may be a JSON list or the same list inside a string.",
"inputSchema": {
"type": "object",
"required": [
"forge_handle",
"parts"
],
"properties": {
"parts": {
"type": [
"array",
"string"
],
"items": {
"type": "object",
"required": [
"id",
"role",
"shape",
"size",
"position"
],
"properties": {
"id": {
"type": "string",
"description": "Your name for the part: lowercase letters, digits, _ or -, unique."
},
"role": {
"enum": [
"head",
"helm",
"visor",
"plume",
"torso",
"belt",
"arm",
"hand",
"leg",
"foot",
"pauldron",
"shield",
"emblem",
"cape",
"sword",
"scabbard",
"ornament"
],
"type": "string"
},
"size": {
"type": "object",
"description": "Keys depend on shape: box: w, h, d; cylinder: radius_top, radius_bottom, height, arc; cone: radius, height, arc; sphere: radius, arc, top, bottom; capsule: radius, length; torus: radius, tube; lathe: points; extrude: outline, depth; tube: points, radius; armour: piece, style, w, h, d"
},
"color": {
"type": "string",
"description": "#rrggbb, optional; overrides the material colour"
},
"scale": {
"type": "array",
"items": {
"type": "number"
},
"description": "[x, y, z], optional"
},
"shape": {
"enum": [
"box",
"cylinder",
"cone",
"sphere",
"capsule",
"torus",
"lathe",
"extrude",
"tube",
"armour"
],
"type": "string"
},
"material": {
"enum": [
"steel",
"blackened_steel",
"gold",
"bronze",
"leather",
"cloth",
"wood",
"fur",
"gem",
"stone"
],
"type": "string"
},
"position": {
"type": "array",
"items": {
"type": "number"
},
"description": "[x, y, z] centre in metres"
},
"rotation": {
"type": "array",
"items": {
"type": "number"
},
"description": "[x, y, z] degrees, optional"
}
},
"description": "One part. Example: {\"id\": \"helm\", \"role\": \"helm\", \"shape\": \"cylinder\", \"size\": {\"radius_top\": 0.13, \"radius_bottom\": 0.14, \"height\": 0.3}, \"position\": [0, 1.7, 0], \"material\": \"steel\"}"
}
},
"forge_handle": {
"type": "string",
"description": "The forge_handle returned by enter_forge."
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/ai.scoreia/forge"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/ai.scoreia/forge"}) over MCP.
enter_forge ~550 tokensenter_duel ~537 tokensforge_add ~537 tokensduel_assault ~317 tokensforge_keyframe ~237 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fai.scoreia%2Fforge?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fai.scoreia%2Fforge?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.scoreia%2Fforge.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.scoreia%2Fforge.svg :target: https://glimind.com/server/mcp-registry%2Fai.scoreia%2Fforge?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:07b45c7e0b333d70…, first seen 2026-10-17, included at leaf 351 of 27,676. Version history · verify what your client received.
Compare: most reliable other servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-19 16:42 UTC, the Scoreia Forge MCP server is up with a Glimind reliability score of 85/100 (grade B). Over the last 30 days it answered 99.8% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 87 minutes.
Scoreia Forge MCP server advertises 11 tools, including duel_assault, duel_ready, duel_status, enter_duel, enter_forge.
Point your MCP client at this streamable-http endpoint: https://scoreia.ai/forge/mcp
Glimind scanned all 11 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.