MCP Titan
未认领This tool is a cutting-edge memory engine that blends real-time learning, persistent three-tier context awareness, and seamless plug-n-play LLM integration to continuously evolve and enrich your AI’s intelligence.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'mcp-titan' -- 'npx' '-y' '@henryhawke/mcp-titan'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
18 个工具中显示 18 个
文档中列出的工具 (18)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
add_training_sample
Feed training data
bootstrap_memory
Quick-load context from text or URL
forward_pass
Query memory and get prediction
get_hierarchical_metrics
Memory tier distribution
get_learner_stats
Monitor learning metrics
get_memory_state
Inspect current memory contents
get_token_flow_metrics
Sequence pattern analysis
health_check
System health & performance
help
List all available tools with descriptions
init_learner
Start background learning service
init_model
Initialize or reconfigure memory system
load_checkpoint
Restore from checkpoint
memory_stats
Get statistical summary
pause_learner
/ resumelearner - Control learning
prune_memory
Clean up low-value memories
reset_gradients
Clear training state
save_checkpoint
Save memory to file
train_step
Explicit learning from example pair