Schema | r3 (Recall)

r3 (Recall)

Describes the environment variables required to run the server.

Name	Required	Description
`LOG_LEVEL`	No	Verbosity of the server logs (e.g., info, debug, warn, error).
`REDIS_URL`	No	Redis connection URL (e.g., redis://localhost:6379). If not provided, the server uses an embedded Redis instance.
`MEM0_API_KEY`	No	API key for cloud backup and synchronization from mem0.ai. While the server can run locally without it, cloud features require this key.
`MEM0_USER_ID`	No	Default user identifier for stored memories.
`CACHE_STRATEGY`	No	Cache management strategy. Options typically include: aggressive, balanced, or conservative.
`MAX_CONNECTIONS`	No	Maximum number of connections in the pool.

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
add_memoryB	Add memory with async processing and intelligent caching. Returns immediately while processing in background.
search_memoryC	Hybrid search with intelligent cache/cloud routing and relevance scoring
get_all_memoriesB	Get all memories with hybrid cloud/cache intelligence and pagination support
delete_memoryB	Delete memory with automatic cache invalidation
deduplicate_memoriesC	Find and merge duplicate memories
optimize_cacheC	Optimize cache with intelligent memory promotion and cleanup
cache_statsA	Get detailed cache performance statistics and health metrics
sync_statusB	Check background sync and job queue status
extract_entitiesB	Extract entities and relationships from text using NLP
get_knowledge_graphB	Get memories organized as a knowledge graph with entities and relationships
find_connectionsC	Find connections between entities in the knowledge graph
import_memoriesB	Bulk import memories from mem0 API or JSON file

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/n3wth/r3'

If you have feedback or need assistance with the MCP directory API, please join our Discord server