Analytics
vivekjoshy.com
An MCP server for updating and comparing Weng-Lin skill ratings and predicting match win probabilities.
ENDPOINT 1
https://vivekjoshy.com/api/mcp
MCP server metadata
- Name
- openskill
- Version
- 1.0.0
Bayesian rating for asymmetric multi-team, multiplayer matches, implementing the Weng-Lin models. Same implementation as vivekjoshy.com/openskill, checked against openskill.py on every deploy.
Known tools 4
compare_modelsRate the same match under all three Weng-Lin models at once, to see where they diverge.
Inferred read-onlyordinalConservative single-number skill for display or sorting: mu - z*sigma, z=3 by default.
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.openskill]
url = "https://vivekjoshy.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"openskill": {
"type": "http",
"url": "https://vivekjoshy.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: openskill
Remote MCP URL: https://vivekjoshy.com/api/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": {
"openskill": {
"url": "https://vivekjoshy.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"openskill": {
"type": "http",
"url": "https://vivekjoshy.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "openskill",
"transport": "streamable-http",
"url": "https://vivekjoshy.com/api/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 vivekjoshy.com was fetched 2026-10-03T10:11:46.291Z.
vivekjoshy.com is assessed as Trusted: Domain has an established technology history spanning over a year.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.