A
licenseB
qualityF
maintenancePersistent memory, teams, and projects for AI agents. 76 MCP tools for storing, recalling, and sharing knowledge across sessions with 4-strategy hybrid search.
33
230 npm
1
MIT
@goldhold/mcp-server
by jerrysrodz
Related Servers
Alternatives to @goldhold/mcp-server
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceProvides AI agents with persistent, human-like memory infrastructure via MCP, enabling them to store, search, summarize, and forget episodic, semantic, procedural, and working memories across sessions.1,203 npmMIT
- AlicenseAqualityDmaintenancePersistent memory for AI agents. Store, recall, and share knowledge across sessions with five MCP tools: remember, recall, context, forget, and share. Includes semantic search and agent/user/org scoping.53Apache 2.0
- AlicenseNot gradedqualityAmaintenanceMCP memory server for AI coding agents to remember decisions, patterns, and bugs between sessions. Provides persistent memory with 37 MCP tools, multi-session coordination, and token-efficient recall.184 npm11MIT
- AlicenseNot gradedqualityCmaintenancePersistent memory infrastructure for AI agents, enabling cross-session recall and autonomous memory evolution via an MCP server.1MIT
- AlicenseNot gradedqualityFmaintenanceA self-hosted persistent memory platform for AI agents and humans offering tools for memory storage, search, beliefs, work management, and code intelligence via MCP.7GPL 3.0
TDQS
B3.2/5.0
Scored across 29 tools
Disambiguation4/5
Most tools have distinct purposes (task, memory, plan, session, communication), and prefixes like goldhold_plan_ and goldhold_task_ reduce confusion. However, compound tools like goldhold_turn and goldhold_batch overlap with individual operations, and goldhold_checkpoint vs goldhold_plan_checkpoint could be misselected without close reading.
Naming Consistency4/5
All tools share the goldhold_ prefix, and most use verb_noun (task_update, memory_read, plan_create). A few are verb-only (store, send, search) or noun-only (agents, inbox, status), but the pattern remains predictable and readable across the set.
Tool Count2/5
With 29 tools, the server exceeds the 'too many' threshold for a coherent set. While the domain is broad (tasks, plans, memory, communication, session), many tools could be consolidated (e.g., goldhold_plan_* variants or session/checkpoint tools) to reduce cognitive load and selection errors.
Completeness4/5
The tools cover core lifecycles well: task management (create/list/update/complete), plan management (create/task/checkpoint/restore/fact/close), memory (store/read/search/namespaces), and communication (send/inbox). Minor gaps exist like lack of task deletion or a single tool for both checkpoint and restore, but agents can work around these.
Maintenance
ActivityInactive
ResponsivenessNo issues