Security & Testing
councilof.ai
Provides tools for AI safety evaluation, including measuring model performance on safety axes, verifying signed AI safety cards, and probing for jailbreaks.
ENDPOINT 1
https://councilof.ai/mcp
MCP server metadata
- Name
- csoai-gspc-mcp
- Version
- 1.0.0
Known tools 8
measureReturn the GSPC measurement CONTRACT for a subject: which axes exist, how they are graded, and where the published results live.
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.csoai-gspc-mcp]
url = "https://councilof.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"csoai-gspc-mcp": {
"type": "http",
"url": "https://councilof.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: csoai-gspc-mcp
Remote MCP URL: https://councilof.ai/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": {
"csoai-gspc-mcp": {
"url": "https://councilof.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"csoai-gspc-mcp": {
"type": "http",
"url": "https://councilof.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "csoai-gspc-mcp",
"transport": "streamable-http",
"url": "https://councilof.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.