Guardrails for LLM answers. GroundLens checks an LLM answer against its sources without a model, decides PASS, REVIEW or FAIL under your policy, and keeps a signed record.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add groundlens -- uvx groundlens~/.codex/config.toml
[mcp_servers.groundlens]
command = "uvx"
args = ["groundlens"]
# codex mcp add groundlens -- uvx groundlens~/.cursor/mcp.json
{
"mcpServers": {
"groundlens": {
"command": "uvx",
"args": [
"groundlens"
]
}
}
}.vscode/mcp.json
{
"servers": {
"groundlens": {
"type": "stdio",
"command": "uvx",
"args": [
"groundlens"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"groundlens": {
"command": "uvx",
"args": [
"groundlens"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"groundlens": {
"command": "uvx",
"args": [
"groundlens"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"groundlens": {
"command": "uvx",
"args": [
"groundlens"
]
}
}
}