
Logic Server
A logic engine that sends only changed facts between conversation turns instead of replaying full history. Extracts structured predicates from natural language, runs backward-chaining inference to find goal-reachable facts, and returns token-optimized deltas. Exposes `/context` for initial reduction, `/memory/context` for goal-driven queries, and `/context/diff` for incremental updates. Built on Hexastore indexing with truth maintenance, so retracting a fact auto-retracts downstream inferences. Works as an MCP server, REST API, or SDK. Useful when you're burning tokens on repeated tool outputs or state replays and need deterministic, reproducible compression without vector search or summarization drift.
- GitHub stars
- 2
- tool
- 1
- auth
- Secret needed
- transport
- STDIO
- env vars
- 4
- last updated
- Apr 16, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
contextUse the `context` tool each turn for a salience-ranked working set.
Use the `context` tool each turn for a salience-ranked working set.
No parameter schema in public metadata yet.
Sponsors
Configuration
NOCTURNUSAI_URLBase URL of the NocturnusAI server
NOCTURNUSAI_API_KEYsecretAPI key for authenticated access
NOCTURNUSAI_DATABASEDatabase name to use
NOCTURNUSAI_TENANTTenant ID for multi-tenant isolation
Readme
NocturnusAI
The context engineering engine for AI agents: send only what changed.
Details
- Repository
- github.com/auctalis/nocturnusai
- Category
- AI & LLM Tools
- Package
nocturnusai-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active