MCP.so
Sign In
V

Varyz MCP Server

@Varyz

Basic information

Transport

streamable-http

Authentication

None

Category

Other

Author

Varyz

About 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.

Connection details

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

Setup

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

Varyz MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list directly from this server's endpoint using the button above.

Overview

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.

Frequently asked questions

1

What is the Varyz remote MCP server?

The Varyz remote MCP server is a hosted Model Context Protocol endpoint at https://cloud.varyzai.com/mcp/plugin, so AI assistants can connect to it without installing or running anything locally.

2

How do I connect to the Varyz MCP server?

Add the endpoint https://cloud.varyzai.com/mcp/plugin to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.

3

Does the Varyz MCP server require authentication?

No. Varyz's MCP server does not require authentication — you can connect directly with the endpoint URL.

4

Which transport does the Varyz MCP server use?

Varyz exposes a streamable-http endpoint, the transport used by remote MCP servers and supported by all major MCP clients.

Comments