Verified knowledge for AI agents. Compress context, extract and store facts, define rules, and ask questions — get deterministic answers with proof, not LLM guesses. Connect agents via MCP, Python SDK, TypeSc
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add logic --env NOCTURNUSAI_API_KEY='<NOCTURNUSAI_API_KEY>' -- npx -y nocturnusai-mcp~/.codex/config.toml
[mcp_servers.logic]
command = "npx"
args = ["-y", "nocturnusai-mcp"]
env = { NOCTURNUSAI_API_KEY = "<NOCTURNUSAI_API_KEY>" }
# codex mcp add logic --env NOCTURNUSAI_API_KEY='<NOCTURNUSAI_API_KEY>' -- npx -y nocturnusai-mcp~/.cursor/mcp.json
{
"mcpServers": {
"logic": {
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
],
"env": {
"NOCTURNUSAI_API_KEY": "<NOCTURNUSAI_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"logic": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
],
"env": {
"NOCTURNUSAI_API_KEY": "<NOCTURNUSAI_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"logic": {
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
],
"env": {
"NOCTURNUSAI_API_KEY": "<NOCTURNUSAI_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"logic": {
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
],
"env": {
"NOCTURNUSAI_API_KEY": "<NOCTURNUSAI_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"logic": {
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
],
"env": {
"NOCTURNUSAI_API_KEY": "<NOCTURNUSAI_API_KEY>"
}
}
}
}Environment variables
NOCTURNUSAI_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.