MCP.so
登录
V

Varyz MCP Server

@Varyz

基本信息

传输方式

streamable-http

认证方式

无需认证

分类

其他

作者

Varyz

关于 Varyz MCP Server

Local-first preference service for AI agents. Applies your confirmed rules and past decisions, asks you only the choices that matter, and searches approved project history. Works with Claude Code, Codex and other MCP clients.

连接信息

https://cloud.varyzai.com/mcp/plugin

接入方式

claude mcp add varyz --transport http https://cloud.varyzai.com/mcp/plugin

Varyz MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,直接连接服务器端点实时获取工具列表。

概览

What it is

Local-first preference service for AI agents. Applies your confirmed rules and past decisions, asks you only the choices that matter, and searches approved project history. Works with Claude Code, Codex and other MCP clients.

From the publisher's website: Varyz brings your experience to your AI: past decisions, project direction and the standards you care about. Free on your computer, with optional paid Cloud.

Connect

  • Endpoint: https://cloud.varyzai.com/mcp/plugin (Streamable HTTP)
  • Authentication: no authentication

Claude Code:

claude mcp add varyz --transport http https://cloud.varyzai.com/mcp/plugin

Other clients (mcpServers config):

{ "mcpServers": { "varyz": { "type": "http", "url": "https://cloud.varyzai.com/mcp/plugin" } } }

Tools

Read from the server's tools/list on 2026-11-08:

  • owner_questions — List pending owner questions
  • answer_owner_question — Record the owner answer to a pending question
  • away — Set or inspect task-scoped away state from owner instructions
  • start_task — Read confirmed rules, workflows and relevant approved task history
  • ask — Exact confirmed answer lookup
  • finish_check — Check applicable standards and supply actual check evidence; agent reports are distinguished from artifact verification
  • remember_owner_rule — Record an explicit owner rule (never infer confirmation)
  • remember_owner_workflow — Record explicitly stated owner steps
  • record_progress — Keep a compact work journal with record_progress: once the goal is clear, after each meaningful step (a change, decision, check, failure or blocker), and before your final answer
  • claim_work — Claim or renew an unfinished thread for 15 minutes before pickup
  • route_task — Coordinate local and hosted Varyz for one task
  • collaboration_status — Read the owner's shared projects, collaborators, reports and pending requests
  • collaboration_digest — Read a compact digest of the owner's shared project updates
  • collaboration_link_repository — Replace the repository URL and branch associated with one owned shared project
  • collaboration_report — Post one factual work report to collaborators on the owner's selected project
  • collaboration_record_repository_access — Record that the owner already granted a collaborator's requested GitHub access
  • collaboration_set_level — Change one collaborator's project permission level to consult, contribute or decide
  • collaboration_review — Apply the owner's explicit keep, overrule, adopt or dismiss decision to one collaboration review item; may replace a project preference or partner answer
  • collaboration_ask_partner — Send one project question to a Decide collaborator
  • collaboration_invite — Invite the specified Varyz username to one owned project, sharing its confirmed preferences at the chosen access level
  • collaboration_remove — Remove one collaborator from the owner's shared project and revoke that membership's access
  • collaboration_draft_context — Save a private draft project explanation and dated story for owner review
  • public_standards_review_link — Return the owner's Share page for a topic with the public page option ticked
  • rule_pack_review_link — Share rules described in the person's words, such as design or automation, with people by username or email (to)
  • public_standards_status — Read the owner's published public standards, topics and usage counts
  • following_list — Read the public creators this account follows and its chosen creators per topic
  • following_add — Follow one creator's public standards by Varyz username
  • following_remove — Unfollow one public creator and remove this account's topic selections for them
  • following_pick_topic — Choose one public creator's standards for a topic, replacing the existing choice and following that creator if needed
  • following_read_standards — Read a bounded page of a creator's published public standards
  • following_read_pack — Read a bounded page of a rule pack someone sent this account, by pack_id from following_list
  • search — Find source passages in approved Cloud project history; filter dates explicitly
  • fetch — Read a source record with original context, author provenance and sync date
  • session_history — Find work reports from separately approved Cloud projects
  • context — Read confirmed preferences and latest dated evidence for a project
  • timeline — Read project evidence chronologically, with dates and source citations
  • compare — Compare earliest retained synced version with current source; earlier local versions may be unavailable

Notes

  • Description above is the publisher's own summary from their submission; check the website for plans, pricing and limits.
  • The endpoint answered a standard MCP initialize request when checked on 2026-11-08.

Sources: Website, Submission.

常见问题

1

Varyz 远程 MCP 服务器是什么?

Varyz 的远程 MCP 服务器是一个托管的 Model Context Protocol 端点,地址是 https://cloud.varyzai.com/mcp/plugin,AI 助手无需在本地安装或运行任何东西即可连接。

2

怎么连接 Varyz 的 MCP 服务器?

把端点 https://cloud.varyzai.com/mcp/plugin 添加到任意支持 MCP 的客户端,比如 Claude Code、Cursor 或 VS Code。本页的接入代码块可以一步配置好每个客户端。

3

Varyz 的 MCP 服务器需要认证吗?

不需要。Varyz 的 MCP 服务器不需要认证——直接用端点地址连接即可。

4

Varyz 的 MCP 服务器用的是哪种传输方式?

Varyz 暴露的是 streamable-http 端点,这是远程 MCP 服务器普遍使用、主流客户端都支持的传输方式。

评论