MCP Server Setup

YantrikDB MCP gives any MCP-compatible AI agent persistent cognitive memory across sessions. Install once, add 3 lines of config, and your agent auto-recalls context, auto-remembers decisions, and auto-detects contradictions — no prompting needed.

Installation

pip install yantrikdb-mcp

Configuration

Add to your MCP client’s configuration:

Claude Code (~/.claude/mcp.json)

{
  "mcpServers": {
    "yantrikdb": {
      "command": "yantrikdb-mcp"
    }
  }
}

Cursor / Windsurf / Copilot / Kilo Code

Same format — add the yantrikdb server to your MCP settings. The server communicates via stdio, compatible with any MCP client.

Environment Variables

Variable	Default	Description
YANTRIKDB_DB_PATH	~/.yantrikdb/memory.db	Database file path
YANTRIKDB_EMBEDDING_MODEL	all-MiniLM-L6-v2	Sentence-transformers model
YANTRIKDB_EMBEDDING_DIM	384	Embedding dimensions

Available Tools

The MCP server exposes 17 cognitive memory tools:

Core Memory

Tool	Description
remember	Store a memory with importance, domain, valence, and certainty
recall	Search memories by semantic similarity with filters (domain, source, type)
recall_refine	Refine a low-confidence recall with a follow-up query
bulk_remember	Store multiple memories at once (efficient for summaries)
get_memory	Retrieve a specific memory by ID
forget	Tombstone a memory permanently
correct	Fix an incorrect memory (preserves history, transfers relationships)
update_importance	Adjust a memory’s importance score

Knowledge Graph

Tool	Description
relate	Create entity relationships (e.g., “Alice manages backend team”)
entity_edges	Get all relationships for an entity
search_entities	Find entities by name pattern

Cognition

Tool	Description
think	Run consolidation + conflict detection + pattern mining
conflicts	List detected contradictions
conflict_resolve	Resolve a contradiction (keep_a, keep_b, merge, keep_both)
recall_feedback	Improve retrieval quality over time
triggers	Get proactive insights, warnings, and suggestions

System

Tool	Description
health_check	Verify the server is operational
stats	Get memory engine statistics

How It Works

The server includes built-in instructions that teach the agent when and how to use memory:

1. Auto-recall — at conversation start, the agent searches memory for relevant context
2. Auto-remember — decisions, preferences, people, and project context are stored automatically
3. Auto-relate — entity relationships are created as they’re discovered
4. Consolidation — think() merges redundant memories, detects contradictions, mines patterns
5. Correction — when the user corrects a fact, the old memory is tombstoned and a corrected version created

Why Not File-Based Memory?

File-based approaches (CLAUDE.md, memory files) load everything into context every conversation. YantrikDB recalls only what’s relevant.

Memories	File-Based	YantrikDB	Savings
100	1,770 tokens	69 tokens	96%
500	9,807 tokens	72 tokens	99.3%
1,000	19,988 tokens	72 tokens	99.6%
5,000	101,739 tokens	53 tokens	99.9%

Selective recall cost is O(1). File-based is O(n). At 500 memories, file-based exceeds 32K context windows. At 5,000, it doesn’t fit anywhere. YantrikDB stays at ~70 tokens with precision that improves as you add more memories.

Run the benchmark: python benchmarks/bench_token_savings.py