Skip to main content

Python MCP workflow tools for host-controlled planning workflows

Project description

Ymcp

Trae MCP工具包 提供工作流以及mempalace的长记忆存储

安装与更新

pip install ymcp
pip install -U ymcp

本地开发安装:

python -m pip install -e .[dev]

安装后建议检查:

ymcp doctor
ymcp --version
ymcp inspect-tools --json

一键初始化 Trae 与默认记忆库:

ymcp init-trae

init-trae 会检查 ~/.yjj。如果该目录不存在,会自动初始化 MemPalace,并把 ~/.yjj 配置为 Ymcp 的默认记忆库目录。

记忆工具

Ymcp 依赖 mempalace 提供长期记忆能力,默认使用 ~/.yjj 作为 MemPalace 记忆库目录,并写入全局个人记忆空间:wing="personal"room="ymcp"

Memory Protocol:唤醒或恢复上下文时先调用 memory_status;回答人物、项目、历史事件或过往决策前先查 memory_search / memory_get,不要凭印象猜;任务结束后把稳定偏好、项目约定、重要决策和踩坑结论写入 memory_storememory_diary_write;事实变化时用更新、删除或 KG 失效工具维护旧记忆。

常用工具:

  • memory_store:保存一条长期记忆
  • memory_search:搜索长期记忆
  • memory_get / memory_update / memory_delete:读取、更新、删除指定记忆
  • memory_status / memory_list_wings / memory_list_rooms / memory_taxonomy:查看记忆空间状态
  • memory_graph_*memory_kg_*memory_*_tunnelmemory_diary_*:封装 MemPalace 的图谱、关系和日记能力

记忆写入是持久化副作用。请不要保存密钥、隐私或未经确认的敏感信息。

Trae 中常用记忆 prompt

调用 Ymcp 的 memory_search,搜索:“当前项目的发布流程”。请只总结与当前任务相关的记忆。
调用 Ymcp 的 memory_store,保存这条长期项目约定:“Ymcp 的文档和用户回复都使用中文,代码接口名保持英文。”

更多示例见 docs/trae-integration.md

Trae Workflow 最佳调用链

推荐链路:deep_interview → ralplan → ralph → memory_store

  • 需求不清晰:先调用 deep_interview,按 next_question 多轮澄清。
  • 需要共识规划:调用 ralplan,按 planner_draft → architect_review → critic_review 推进。
  • 执行验证:调用 ralph,根据 stop_continue_judgement 继续、修复或完成。
  • 完成沉淀:调用 memory_search 查重,再用 memory_store 保存稳定经验。

完整 prompt 模板见 docs/trae-integration.md

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ymcp-0.1.3.tar.gz (43.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ymcp-0.1.3-py3-none-any.whl (38.8 kB view details)

Uploaded Python 3

File details

Details for the file ymcp-0.1.3.tar.gz.

File metadata

  • Download URL: ymcp-0.1.3.tar.gz
  • Upload date:
  • Size: 43.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for ymcp-0.1.3.tar.gz
Algorithm Hash digest
SHA256 af19c5ca4eff7005531e0e5446875da87f41af2e7f54bfbd5f9ce30fe5c472ec
MD5 bf23fb8e60273e2dbe98dfbced66b39e
BLAKE2b-256 b6d00219243154a0cc74ad2d64edb77dd2dc241600f0ab9e142b984742736829

See more details on using hashes here.

Provenance

The following attestation bundles were made for ymcp-0.1.3.tar.gz:

Publisher: release.yml on CodeyLife/Ymcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file ymcp-0.1.3-py3-none-any.whl.

File metadata

  • Download URL: ymcp-0.1.3-py3-none-any.whl
  • Upload date:
  • Size: 38.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for ymcp-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 1155c095dd26a5da11f84c97ff871a2cae100e8736146e8be6c668f3e0a323ec
MD5 ab0662971725e79acdb38c354efc725c
BLAKE2b-256 f6646417a0f6ad78f513af551baee5d875e0c8bfe1742542e69679edc78241af

See more details on using hashes here.

Provenance

The following attestation bundles were made for ymcp-0.1.3-py3-none-any.whl:

Publisher: release.yml on CodeyLife/Ymcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page