Skip to main content
AllMCPs
BrowseBestCategoriesStackCompareToolsGuidesBlog
Log in Submit MCP

Stay in the loop

Get new MCP servers and top picks in your inbox.

AllMCPs

The open directory for discovering and installing Model Context Protocol servers.

AllMCPs on GitHub (opens in a new tab)
Launched onTiny Startupstinystartups.com
Explore
  • Browse servers
  • Best MCP servers
  • Categories
  • MCP clients
  • Agent prompts
  • Stack Builder
  • Compare servers
  • Random discovery New
  • Submit a server
  • Pricing & Boost Boost
Learn
  • Guides hub
  • What is MCP?
  • Install guide
  • Build an MCP server
  • Deploy an MCP server
  • Security guide
  • Troubleshooting
  • MCP for SEO & AEO
  • Protocol versioning
  • Blog & updates
Tools
  • All developer tools
  • Config generator
  • Config validator
  • Config auditor
  • MCP playground
  • Token calculator
  • OpenAPI → MCP
  • Badge generator
For agents
  • REST API docs
  • Trust & traffic Live
  • Remote MCP server SSE ↗ (opens in a new tab)
  • llms.txt ↗ (opens in a new tab)
  • Catalog JSON ↗ (opens in a new tab)
Company
  • About
  • Advertise Sponsor
  • Contact
  • GitHub ↗ (opens in a new tab)
  • Terms
  • Privacy
AllMCPs VerifiedAllMCPs VerifiedFeatured on Nick LaunchesFeatured on Nick LaunchesLaunch Llama NewsletterLaunch Llama NewsletterVerified DR - allmcps.comVerified DR - allmcps.comFeatured on SaaSGrowFeatured on SaaSGrowFeatured on Twelve ToolsFeatured on Twelve ToolsFeatured on Saaspa.geFeatured on Saaspa.geFeatured on Findly.toolsFeatured on Findly.toolsFeatured on Startup FameFeatured on Startup FameFeatured on LaunchKiwiFeatured on LaunchKiwiFeatured on ScrollLaunchFeatured on ScrollLaunchFeatured on DailyPingsFeatured on DailyPingsFazier badgeFazier badgeFeatured on NewTool.siteFeatured on NewTool.siteFeatured on saasfame.comFeatured on saasfame.comDR Checker - Domain RatingDR Checker - Domain RatingListed on Turbo0Listed on Turbo0Launched on LaunchBoard - Product Launch PlatformLaunched on LaunchBoard - Product Launch PlatformList on SimilarlabsList on Similarlabshttps://codetrendy.comhttps://codetrendy.comListed on DevTool.ioFeatured on BuildlistFeatured on BuildlistLaunched on Tiny StartupsFeatured on ShowMeBestAIFeatured on ShowMeBestAIFind us on LaunchZoneFind us on LaunchZoneAllMCPs VerifiedAllMCPs VerifiedFeatured on Nick LaunchesFeatured on Nick LaunchesLaunch Llama NewsletterLaunch Llama NewsletterVerified DR - allmcps.comVerified DR - allmcps.comFeatured on SaaSGrowFeatured on SaaSGrowFeatured on Twelve ToolsFeatured on Twelve ToolsFeatured on Saaspa.geFeatured on Saaspa.geFeatured on Findly.toolsFeatured on Findly.toolsFeatured on Startup FameFeatured on Startup FameFeatured on LaunchKiwiFeatured on LaunchKiwiFeatured on ScrollLaunchFeatured on ScrollLaunchFeatured on DailyPingsFeatured on DailyPingsFazier badgeFazier badgeFeatured on NewTool.siteFeatured on NewTool.siteFeatured on saasfame.comFeatured on saasfame.comDR Checker - Domain RatingDR Checker - Domain RatingListed on Turbo0Listed on Turbo0Launched on LaunchBoard - Product Launch PlatformLaunched on LaunchBoard - Product Launch PlatformList on SimilarlabsList on Similarlabshttps://codetrendy.comhttps://codetrendy.comListed on DevTool.ioFeatured on BuildlistFeatured on BuildlistLaunched on Tiny StartupsFeatured on ShowMeBestAIFeatured on ShowMeBestAIFind us on LaunchZoneFind us on LaunchZone
© 2026 Jackalope Digital LLC. All rights reserved.
  1. Home
  2. 🗄️ Databases
  3. TeamMemory
TeamMemory logo
Health: ActiveRecent health check succeeded.Last checked 9/8/2026, 11:31:40 PM

TeamMemory

User RatingsBe the first to rate and review this MCP server! Enrichment pendingWe haven’t run our AI enrichment pass on this listing yet, so the overview, use cases, and FAQ below may be sparse or missing. We work through the catalog over time — check back soon.
View Repository1 GitHub StarsTotal stargazers on GitHub for the source repository (1 stars).Visit Website

Team experience database - let AI accumulate, retrieve and apply team knowledge across chats.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to CursorAdd to VS Code
Not yet automatically verified

We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment
Target File:~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "teammemory": {
      "command": "uvx",
      "args": [
        "team_memory"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Install Directory Badge Claim listing Alternatives🗄️ More in Databases

Documentation Overview

TeamMemory

mcp-name: io.github.ysydhc/team-memory

让 AI 拥有团队记忆 — 跨会话积累经验,像资深成员一样理解你的项目。

这是我学 AI 时萌生的一个想法。市面上已有类似产品,但总觉得不太贴合自己的使用习惯。做这个项目,既想通过和 AI 一起写代码来加深对大模型的理解,也希望能按自己的工作流,打磨出真正顺手的功能。

给 Agent / 贡献者:AGENTS.md · docs/README.md · MCP 实现 src/team_memory/server.py · 分层约束见 scripts/harness_import_check.py(LAYER_MAP)

为什么需要 TeamMemory?

用 Cursor、Claude 等 AI 助手写代码时,往往会遇到三个问题:

盲区现象
无记忆上周刚帮你修过的 Bug,这周遇到类似的,它完全不记得
只见代码,不懂决策能看懂「是什么」,却不知道「为什么这么写」「上次踩过什么坑」
静态知识不够用Rules、Skills 管得了规范,管不住每天冒出来的隐性经验(接口坑、故障根因、被否掉的方案)

TeamMemory 就是冲着这三个问题来的。 通过 MCP 把语义可搜索的经验库接进 AI:遇到问题自动查历史方案,解决后自动提炼并存下来,下次谁遇到同类问题,直接就能命中。既适合 3–10 人的技术团队共享,也适合部署在本地个人使用,配合 Cursor / Claude Desktop。

快速开始(4 条命令 + 1 项配置)

环境:Docker Desktop、Python 3.11+、Make

server.ts
# 1. 初始化(Docker + 依赖 + 数据库)
make setup

# 2. 设置 API Key(唯一必改项;与 Web 签发的原始密钥同为 64 位十六进制,见 docs/decision/auth-api-key-design.md)
export TEAM_MEMORY_API_KEY=$(openssl rand -hex 32)
echo "API Key: $TEAM_MEMORY_API_KEY"

# 3. 拉取 Embedding 模型(仅首次需要)
ollama pull qwen3-embedding:0.6b

# 4. 启动
make web

浏览器访问 http://localhost:9111 ,用上面的 API Key 登录即可。更完整的部署与用户流程见下文 按角色导航 与 快速开始。

CLI 工具 / CLI Tools

除 MCP 外,所有 memory_* 工具也可通过 tm-cli 命令行调用:

bash
# 搜索团队知识 / Search team knowledge
tm-cli recall --query "如何配置"

# 保存经验 / Save experience
tm-cli save --title "Bug fix" --problem "连接超时" --solution "增加重试"

# 获取上下文 / Get context
tm-cli context --file-paths "src/server.py"

# 查看所有命令 / Show all commands
tm-cli --help

配置命令 / Configuration Commands

bash
# 显示当前生效配置及值来源 / Show effective config with source annotations
tm-cli config show

# 交互式生成 ~/.config/tm/config.toml / Interactive config init
tm-cli config init

# 一键配置平台 Hook / One-command hook setup
tm-cli setup --platform claude-code
tm-cli setup --platform cursor
tm-cli setup --platform hermes
tm-cli setup --platform all

# 仅检查当前状态 / Check status only
tm-cli setup --platform all --check

前提:make dev 启动服务 + TEAM_MEMORY_API_KEY 环境变量已设置(或已在 ~/.config/tm/config.toml 中配置)。

MCP 接入(Cursor / Claude)

本仓库(克隆源码)推荐:不要把 API Key 写进 mcp.json。在仓库根维护 **.env(从 example/env.team-memory.example 复制),其中至少设置 **TEAM_MEMORY_API_KEY**;MCP 配置为 **bash** + **scripts/run_mcp_with_dotenv.sh** + **cwd= 仓库根。详见 docs/guide/mcp-server.md。Cursor 一般用 .cursor/mcp.json,Claude Code 可用根目录 .mcp.json,两处内容建议保持一致。

项目名零配置:在项目根放置 .tm.toml(见 配置说明),或系统自动从 git 仓库名推断,无需传 --project 或设 TEAM_MEMORY_PROJECT。

仅 pip install team_memory、无本地仓库目录时,可在 .cursor/mcp.json 里用本机 Python 与环境变量(数据库与 Key 仍需提供):

config.json
{
  "mcpServers": {
    "team_memory": {
      "command": "python3",
      "args": ["-m", "team_memory.server"],
      "env": {
        "TEAM_MEMORY_DB_URL": "postgresql+asyncpg://developer:devpass@localhost:5433/team_memory",
        "TEAM_MEMORY_API_KEY": "你的 API Key"
      }
    }
  }
}

也可使用客户端配置 ~/.config/tm/config.toml(tm-cli config init 生成),避免在 JSON 中写入密钥。

(MCP 未注册 Resources / Prompts;**memory_* 七工具**:memory_save、memory_recall、memory_context、memory_get_archive、memory_archive_upsert、memory_feedback、memory_submit_response。详情见下文 MCP 工具列表(当前) 与 docs/guide/mcp-server.md。)

本机直连数据库时需要配 TEAM_MEMORY_DB_URL(或通过 config);从源码跑且项目里已有 config 的,可不单独设 DB_URL。

架构可视化(现状)

Web 内「架构」导航与 /api/v1/architecture/* 已移除(实现见 src/team_memory/web/static/js/pages.js)。若需要代码库图谱,请在本机单独使用 GitNexus(CLI / Bridge 等),与当前 TM Web 无集成。


按角色导航

角色目标入口
初次部署者跑起 Web、拿到 API Key快速开始 → 一、初次部署者
初级使用者在 Cursor/Claude 里接入快速开始 → 二、初级使用者
贡献者改代码、提 PR开发

目录

  • 功能概览 · 快速开始 · CLI 工具 · MCP 接入 · Web 管理 · 配置 · 运维 · FAQ · 开发

安装与获取

  • PyPI:pip install team_memory(推荐用于部署或本地 MCP 客户端)。
  • MCP 官方注册表:在 MCP Registry 或 Cursor / Claude Desktop 的 MCP 市场中搜索「TeamMemory」或「team-memory」,可一键发现并安装(安装后仍需配置数据库连接与 API Key,见下文)。

TeamMemory 在 AI 知识体系中的位置

AI 助手在项目中可用的知识分为三层,每一层解决不同的问题:

Code
┌─────────────────────────────────────────────────────────┐
│  Rules / Skills(静态层)                                │
│  已确定的规范和成熟的工作流,手动维护,变化频率低            │
│  例:代码风格规范、部署流程、API 用法                      │
├─────────────────────────────────────────────────────────┤
│  TeamMemory(动态层)          ← 本项目                  │
│  从日常开发中自动积累的团队经验,语义可搜索,持续演化         │
│  例:Bug 根因分析、架构决策背景、接口的隐藏坑               │
├─────────────────────────────────────────────────────────┤
│  代码 + 文档(基础层)                                    │
│  项目源码和文档,AI 可直接读取                              │
│  例:函数定义、README、注释                                │
└─────────────────────────────────────────────────────────┘

三层之间存在自然的知识生命周期:

Code
日常开发会话
    │
    ▼
AI 自动提取经验 ──→ TeamMemory(动态积累)
    │                      │
    │                      ▼ 模式稳定后
    │               固化为 Rules / Skills
    │                      │
    └──── 新问题 / 新变化 ←─┘

Rules/Skills 无法覆盖的知识,正是 TeamMemory 的价值所在:那些太碎、太多、变化太快,不适合写成规则,但恰恰是团队"老手"和"新手"之间最大差距的经验。

术语表

术语说明
经验单条问题-方案对,可被检索和复用
经验库经验的集合
scope作用域:global(全局)、team(团队)、personal(个人)
Embedding向量嵌入,用于语义搜索;配置项为 embedding
MCPModel Context Protocol,让 AI 客户端调用 memory_recall、memory_save 等工具

功能概览

自动学习

AI 从对话和文档中自动提取结构化经验,无需手动录入:

  • 对话提取:通过 MCP **memory_save(content=...)** 走 LLM 解析,从长对话中识别问题、方案、标签并写入(含质量门控);Web 上亦支持粘贴文档或 URL 解析
  • 文档解析:上传文档或输入 URL,AI 自动解析为标题、问题描述、解决方案、标签
  • 经验组:保存时可选 **group_key**(MCP / HTTP)将相关经验归组;复杂编排可在 Web 完成
  • 默认草稿模式:AI 提取的内容默认为草稿,经人工审核后发布,保证质量

智能检索

多层检索管线,确保 AI 找到最相关的历史方案:

  • 语义搜索:基于向量嵌入(Ollama / OpenAI / 本地模型),理解查询意图
  • 混合检索:向量搜索 + 全文检索 + RRF 融合排序
  • 查询优化:同义词扩展(config.tag_synonyms)、短查询自动降低 min_similarity(0.45);FTS 使用 simple 分词器 + jieba 中文分词 + hybrid AND/OR 策略(前 2 词 AND 保证精度,其余 OR 提升召回)
  • Reranker:支持服务端 LLM 精排,或客户端 AI 自行判断结果相关性
  • Token 预算控制:自动裁剪输出长度,避免经验库增大后撑爆 AI 上下文
  • 记忆压缩与摘要:经验支持 summary 字段,LLM 可生成简短摘要;单条(POST /experiences/{id}/summarize)与批量(POST /experiences/batch-summarize)生成;MCP 搜索结果中每条经验可包含 summary,便于节省 Token
  • PageIndex-Lite:长文档自动分块建立节点索引,支持节点级精准检索
  • 个人扩写:per-user tag_synonyms 在检索前生效(词表替换 + LLM 扩写),MCP 搜索返回后自动维护;Web 设置 → 个人扩写
  • 个人记忆 / 用户画像:按 user_id 隔离;Lite 下由 **memory_save(..., content=...)** 解析等路径可写入;**memory_context** 返回 profile.static / profile.dynamic(字符串列表)。Web 设置 → 用户画像 可分组查看、过滤 static/dynamic 并 删除 错误条目(还可调 HTTP API profile_kind)。
  • 文件位置绑定:保存经验时可传 file_locations(路径 + 行范围,可选 snippet/file_mtime/file_content_hash);检索时可传 current_file_locations,与当前编辑位置匹配的经验会获得 location 加分,详见 src/team_memory/server.py 工具参数与 docs/guide/mcp-server.md。

三层作用域

  • global:全局共享知识
  • team:团队/项目级经验
  • personal:个人笔记与草稿

经验类型自动分类

保存时可根据内容自动推荐经验类型(general/feature/bugfix/tech_design/incident/best_practice/learning),减少手动选择。

经验质量打分系统

自动评估经验的活跃度和价值,让高质量经验脱颖而出:

  • 阶梯衰减:新经验 100 分起步,10 天保护期后未被引用每天 -1 分(低于 50 分后 -0.5/天)
  • 引用加分:每次被检索命中(含 memory_recall / Web 搜索管线)+2 分,获 4 星以上评价 +1 分
  • 质量等级:Gold (≥120) / Silver (≥60) / Bronze (≥20) / Outdated (≤0)
  • 置顶免衰:手动置顶的经验永不衰减(年度发布流程等长期有效经验)
  • Outdated 管理:分值归零的经验仍可搜索到,但在管理面板提示处理(恢复/删除/置顶)
  • 规则可配:初始分值、衰减速率、加分幅度、等级阈值均可在设置页调整

结构化管理

不是随意堆放的笔记,而是有类型、有层级、有评分的经验体系:

  • 7 种经验类型:通用、需求、Bug、技术方案、故障、最佳实践、学习笔记,每种类型有专属结构化字段
  • 父子层级存储:支持将相关经验组织为经验组(如:一个需求从评审到上线的全过程)
  • 完整度评分:0-100 分自动评分,鼓励团队逐步完善经验
  • 生命周期管理:草稿 → 审核 → 发布 → 过期检测 → 去重合并

团队协作

多人共建共享的团队知识库:

  • RBAC 权限:admin / editor / viewer 三级角色
  • 反馈评分:1-5 星评分影响搜索排序,低分经验自动降权
  • 版本历史:就地编辑 + 版本快照,支持回滚
  • 去重检测:保存前自动检测相似经验,避免重复录入
  • 合并建议:设置页标记建议合并的相似经验对,三栏 Git-Conflict 风格 diff 对比 + 合并预览
  • 多项目隔离:通过 project 参数隔离不同项目的经验,避免跨项目污染

无缝集成

原生 MCP 协议支持,AI 助手通过 stdio 接入:

  • MCP 工具(7 个):memory_context、memory_recall、memory_get_archive、memory_archive_upsert、memory_save、memory_feedback、memory_submit_response(见 MCP 工具列表)
  • 当前 MCP 未注册 Resources / Prompts;补齐体验以 Web、/docs HTTP API 为准
  • Web 管理界面:浏览、搜索、审核、档案馆、配置等

旧文若仍写 **tm_*** MCP 或任务看板等已下线能力,以 本文、AGENTS.md 与 src/team_memory/server.py 为准。

TM Daemon(自动采集与精炼)

后台守护进程,自动从 Obsidian vault 和 Agent 对话中采集经验:

  • Obsidian Watcher:监听 vault 文件变更,自动创建 draft(同文件去重,更新而非重复创建)
  • RefinementWorker:每 30 秒扫描 pending draft,调用 LLM(GLM-5-Turbo)提取结构化字段(title/problem/solution/tags),自动发布
  • 学习卡片跳过:识别学习类内容(卡片-、主题-、Layer 等),直接发布不走 LLM 抽取
  • 入口命令:tm-daemon(即 python -m team_memory.daemon),make daemon-start / make daemon-stop(launchd 托管),日志 /tmp/tm-daemon.log
  • 代码位置:src/team_memory/daemon/(原 scripts/daemon/)

Faithfulness 评估系统

基于 RAGAS 思路,用 LLM Judge 评估搜索结果是否被 Agent 真实使用:

Read the full README →View source on GitHub →

Related MCP Servers

View all in Databases View all alternatives
  • Genai Toolbox logoGenai Toolbox

    Open source MCP server specializing in easy, fast, and secure tools for Databases.

    🗄️ Databases5 views
    Compare vs Genai Toolbox →
  • V
    Vidlens MCP

    YouTube as a queryable database for AI agents. 41 tools, zero config.

    🗄️ Databases0 views
    Compare vs Vidlens MCP →
  • Mysql MCP Server logoMysql MCP Server

    MySQL database integration with configurable access controls, schema inspection, and comprehensive security guidelines

    🗄️ Databases3 views
    Compare vs Mysql MCP Server →
  • MCP Server Mysql logoMCP Server Mysql

    MySQL database integration in NodeJS with configurable access controls and schema inspection

    🗄️ Databases3 views
    Compare vs MCP Server Mysql →

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about TeamMemory

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "teammemory": { "command": "uvx", "args": ["team_memory"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewTeamMemory AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/teammemory?style=directory)](https://allmcps.com/mcp/teammemory)
HTML Embed
<a href="https://allmcps.com/mcp/teammemory"><img src="https://allmcps.com/api/badge/teammemory?style=directory" alt="TeamMemory on AllMCPs" /></a>

Technical Specs & Signals

Category🗄️Databases
More technical detailsExpand ▾
TransportSTDIO
RuntimePython
Last updatedSep 7, 2026
Views0
Unique ViewsTotal visits recorded for this listing page on AllMCPs.
Installs0
Installs & Copy ActionsTotal times users copied install commands or configuration snippets for this server.
GitHub stars1
GitHub Star CountTotal stargazers on GitHub representing community popularity (1 stars).
36Quality signal: Fair · 36/100How this signal is calculated ▾
Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20
Documentation & tools16/30
Adoption & activity1/15
Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

★ FeaturedMoxie Docs MCP logo

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🗄️ Databases →Best MCP servers for Databases →Alternatives to TeamMemory →Install in Claude DesktopInstall in CursorInstall in VS Code