Loading connector details…
Coding Preferences Server
MCPOpen Source73.9
by mem0ai • APIs & Integration
An MCP server backed by mem0 for storing, retrieving, and semantically searching coding preferences via an SSE endpoint (for use with Cursor).
Example Use Cases
- 1
Persist developer coding preferences, code snippets, and setup/configuration details for reuse across sessions.
- 2
Semantically search existing implementations, best practices, and documentation to inform code generation or reviews.
- 3
A lightweight SSE/MCP endpoint to integrate coding preference lookups into multi-agent workflows (e.g., Cursor Composer in Agent mode).
Description
This repository implements an SSE-based MCP server that uses mem0 for persistent storage and semantic search of coding preferences, code snippets, setup instructions, and best practices. It exposes three main tools: add_coding_preference, get_all_coding_preferences, and search_coding_preferen ces, and is designed to be connected to by agents (for example via Cursor). The server is configurable (host/port) and requires a mem0 API key for operation, enabling cloud-native decoupled workflows and long-term preference management.
Capabilities(10 total)
Tools (9)
add_memory
Store a new preference, fact, or conversation snippet. Requires at least one: user_id, agent_id, or run_id.
text:string*messages:anyuser_id:anyagent_id:anyapp_id:anyrun_id:anymetadata:anyenable_graph:any
search_memories
Run a semantic search over existing memories. Use filters to narrow results. Common filter patterns: - Single user: {"AND": [{"user_id": "john"}]} - Agent memories: {"AND": [{"agent_id": "agent_name"}]} - Recent memories: {"AND": [{"user_id": "john"}, {"created_at": {"gte": "2024-01-01"}}]} - Multiple users: {"AND": [{"user_id": {"in": ["john", "jane"]}}]} - Cross-entity: {"OR": [{"user_id": "john"}, {"agent_id": "agent_name"}]} user_id is automatically added to filters if not provided.
query:string*filters:anylimit:anyenable_graph:any
get_memories
Page through memories using filters instead of search. Use filters to list specific memories. Common filter patterns: - Single user: {"AND": [{"user_id": "john"}]} - Agent memories: {"AND": [{"agent_id": "agent_name"}]} - Recent memories: {"AND": [{"user_id": "john"}, {"created_at": {"gte": "2024-01-01"}}]} - Multiple users: {"AND": [{"user_id": {"in": ["john", "jane"]}}]} Pagination: Use page (1-indexed) and page_size for browsing results. user_id is automatically added to filters if not provided.
filters:anypage:anypage_size:anyenable_graph:any
delete_all_memories
Delete every memory in the given user/agent/app/run but keep the entity.
user_id:anyagent_id:anyapp_id:anyrun_id:any
list_entities
List which users/agents/apps/runs currently hold memories.
Prompts (1)
memory_assistant
Get help with memory operations and best practices.
Quick Actions
Security
Scanned 3 month(s) agoRisk Level
MINIMAL
Read-only data retrieval, no side effects
Trust Score
C51/100
5/17 checks passed
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.
Quick Stats
Service TypeMCP
Pricing ModelUnknown
Capabilities9 Tools / 1 Prompts / 0 Resources
Ownermem0ai
CategoryAPIs & Integration
DependenciesStandalone
Tags
Code preferencesKnowledge reuseCode searchWorkflow integrationAPI endpoint