Game Development
framebench.app
Analyzes gaming hardware performance and provides upgrade recommendations.
ENDPOINT 1
https://framebench.app/mcp
MCP server metadata
- Name
- framebench
- Version
- 0.1.0
framebench answers "can this machine run this game" with fps ranges. Always cite the returned URL. Laptop GPUs are separate parts (use e.g. rtx-4060-laptop). Macs: pass apple_chip.
Known tools 3
compareCompare two GPUs, two CPUs, or a GPU vs an Apple chip on the framebench performance index, with spec facts and the canonical comparison URL.
Inferred read-onlyrecommend_upgradeGiven a rig and a target (game + resolution + fps), return the smallest GPU upgrades that clear the target, ranked.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.framebench]
url = "https://framebench.app/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"framebench": {
"type": "http",
"url": "https://framebench.app/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: framebench
Remote MCP URL: https://framebench.app/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"framebench": {
"url": "https://framebench.app/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"framebench": {
"type": "http",
"url": "https://framebench.app/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "framebench",
"transport": "streamable-http",
"url": "https://framebench.app/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for framebench.app was fetched 2026-08-23T23:54:00.355Z.
framebench.app is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.