Token导航 LogoToken导航TokenDH.com
CO
搜索检索HTTP官方级别未说明来源级核验

cogmemai (0e40f0)

MCP Server

Persistent cloud memory for Ai coding assistants. 33 MCP tools, 85% accuracy on LoCoMo benchmark. Semantic search,

工具数

公开资料未说明
JavaScriptSession认证HTTP搜索

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

最后核验

2026/5/18 00:04

运行时

Node.js

快速接入

先看主来源和安装命令,再打开仓库或文档;下面只保留这个条目的关键接入事实。

命令预览

npx -y smithery mcp add hifriendbot/cogmemai

详细介绍

cogmemai

Persistent cloud memory for Ai coding assistants. 33 MCP tools, 85% accuracy on LoCoMo benchmark. Semantic search,

Quick Start

# Connect this server (installs CLI if needed)
npx -y smithery mcp add hifriendbot/cogmemai

# Browse available tools
npx -y smithery tool list hifriendbot/cogmemai

# Get full schema for a tool
npx -y smithery tool get hifriendbot/cogmemai save_memory

# Call a tool
npx -y smithery tool call hifriendbot/cogmemai save_memory '{}'

Direct MCP Connection

Endpoint: https://cogmemai--hifriendbot.run.tools

Tools (33)

  • save_memory — Store a developer memory (fact, preference, decision, architecture detail). Memories persist across all Claude Code ses…
  • save_rule — Save a mandatory rule that will ALWAYS be followed in every session. Rules bypass scoring and decay — they are injected…
  • list_rules — List all mandatory rules for the current project and/or globally. Rules are always-on memories that surface in every se…
  • delete_rule — Delete a mandatory rule by its memory ID. Use list_rules to find the ID first.
  • recall_memories — Search stored memories using semantic search. Returns memories ranked by relevance, importance, and recency. Use this t…
  • extract_memories — Extract memories from a conversation exchange using AI. Send the developer message and assistant response, and the serv…
  • get_project_context — Load top memories for the current project plus relevant global memories. Use at the start of a session to get full cont…
  • list_memories — List stored memories with optional filters by type, category, scope, or project.
  • delete_memory — Delete a specific memory by its ID. This is permanent.
  • update_memory — Update an existing memory's content, importance, or scope.
  • bulk_delete — Delete multiple memories at once by their IDs. Maximum 100 IDs per call. This is permanent.
  • bulk_update — Update multiple memories at once. Each item needs a memory_id and fields to update. Maximum 50 items per call.
  • get_usage — Get current usage statistics — memory count, extractions this month, tier info, projects.
  • export_memories — Export all memories as JSON. Use this to back up memories or transfer them to another project.
  • import_memories — Bulk import memories from a JSON array. Each memory needs at minimum a content field. Deduplication is applied automati…
  • ingest_document — Extract memories from a document by splitting it into chunks and processing each one. Great for onboarding — feed in RE…
  • save_session_summary — Save a summary of the current coding session. Captures what was accomplished, decisions made, and next steps. Stored as…
  • list_tags — List all tags in use across your memories, with counts. Use this to see what threads/groups exist and find related memo…
  • link_memories — Connect two related memories with a named relationship. Use this to build a knowledge graph — e.g., linking a bug fix t…
  • get_memory_links — View all memories linked to a specific memory. Returns the relationship type and full memory details for each connectio…
  • get_memory_versions — View the edit history of a memory. Shows all previous versions with timestamps and what changed. Useful for understandi…
  • get_analytics — Get a memory health dashboard with insights: most recalled memories, never-recalled memories, stale memories, growth tr…
  • promote_memory — Promote a project-scoped memory to global scope so it applies across all projects. Use this when you discover a prefere…
  • consolidate_memories — Consolidate related memories into fewer, richer memories. Finds clusters of memories sharing the same subject (3+ memor…
  • save_task — Create a task that persists across sessions. Tasks are tracked with status (pending, in_progress, done, blocked) and pr…
  • get_tasks — Get tasks for the current project. Returns tasks filtered by status — defaults to showing pending and in_progress tasks…
  • update_task — Update a task's status, title, description, or priority. Use this to mark tasks as in_progress, done, or blocked as you…
  • save_correction — Save a correction pattern — what went wrong and what the right approach is. These are surfaced automatically when simil…
  • set_reminder — Set a reminder that surfaces automatically at the start of your next session. Use for follow-ups, things to check, or d…
  • get_stale_memories — Find memories that may be outdated based on age and access patterns. Returns memories that haven't been recalled or upd…
  • get_file_changes — Show what files changed since your last session. Compares the current git state to a snapshot saved when your previous …
  • feedback_memory — Signal whether a recalled memory was useful or irrelevant. Helps improve future recall quality over time. Use after rec…
  • generate_skills — Manually trigger skill generation from your corrections, preferences, and patterns. Skills are behavioral directives th…
# Get full input/output schema for a tool
npx -y smithery tool get hifriendbot/cogmemai 

目录标签

目录标签

JavaScriptSession认证HTTP搜索

接入字段

传输方式(transport,传输协议)

HTTP

鉴权方式(authType,认证方式)

session

运行时(runtime,运行环境)

Node.js

权限和风险

HTTPsession部署方式未说明

接入前请确认传输方式、认证方式和部署位置,并根据实际工具能力限制访问范围。

安装前确认

不要直接授予不必要的文件、网络或账号权限;先核对安装命令和配置内容。

仍需确认:category

来源信息

继续浏览同类 MCP