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.
@Varyz
Basic information
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.
https://cloud.varyzai.com/mcp/pluginclaude mcp add varyz --transport http https://cloud.varyzai.com/mcp/pluginTool 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.
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.
https://cloud.varyzai.com/mcp/plugin (Streamable HTTP)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" } } }
Read from the server's tools/list on 2026-11-08:
owner_questions — List pending owner questionsanswer_owner_question — Record the owner answer to a pending questionaway — Set or inspect task-scoped away state from owner instructionsstart_task — Read confirmed rules, workflows and relevant approved task historyask — Exact confirmed answer lookupfinish_check — Check applicable standards and supply actual check evidence; agent reports are distinguished from artifact verificationremember_owner_rule — Record an explicit owner rule (never infer confirmation)remember_owner_workflow — Record explicitly stated owner stepsrecord_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 answerclaim_work — Claim or renew an unfinished thread for 15 minutes before pickuproute_task — Coordinate local and hosted Varyz for one taskcollaboration_status — Read the owner's shared projects, collaborators, reports and pending requestscollaboration_digest — Read a compact digest of the owner's shared project updatescollaboration_link_repository — Replace the repository URL and branch associated with one owned shared projectcollaboration_report — Post one factual work report to collaborators on the owner's selected projectcollaboration_record_repository_access — Record that the owner already granted a collaborator's requested GitHub accesscollaboration_set_level — Change one collaborator's project permission level to consult, contribute or decidecollaboration_review — Apply the owner's explicit keep, overrule, adopt or dismiss decision to one collaboration review item; may replace a project preference or partner answercollaboration_ask_partner — Send one project question to a Decide collaboratorcollaboration_invite — Invite the specified Varyz username to one owned project, sharing its confirmed preferences at the chosen access levelcollaboration_remove — Remove one collaborator from the owner's shared project and revoke that membership's accesscollaboration_draft_context — Save a private draft project explanation and dated story for owner reviewpublic_standards_review_link — Return the owner's Share page for a topic with the public page option tickedrule_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 countsfollowing_list — Read the public creators this account follows and its chosen creators per topicfollowing_add — Follow one creator's public standards by Varyz usernamefollowing_remove — Unfollow one public creator and remove this account's topic selections for themfollowing_pick_topic — Choose one public creator's standards for a topic, replacing the existing choice and following that creator if neededfollowing_read_standards — Read a bounded page of a creator's published public standardsfollowing_read_pack — Read a bounded page of a rule pack someone sent this account, by pack_id from following_listsearch — Find source passages in approved Cloud project history; filter dates explicitlyfetch — Read a source record with original context, author provenance and sync datesession_history — Find work reports from separately approved Cloud projectscontext — Read confirmed preferences and latest dated evidence for a projecttimeline — Read project evidence chronologically, with dates and source citationscompare — Compare earliest retained synced version with current source; earlier local versions may be unavailableinitialize request when checked on 2026-11-08.Sources: Website, Submission.
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.
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.
No. Varyz's MCP server does not require authentication — you can connect directly with the endpoint URL.
Varyz exposes a streamable-http endpoint, the transport used by remote MCP servers and supported by all major MCP clients.
CVE prioritization using exploitation signals, plus agent heartbeat monitoring and state capsules. Some tools use API-key or x402 access.
The 9apes MCP server lets an AI assistant read the GitHub Actions data 9apes already collects for your organization: runs, jobs, steps, and their durations. Ask it why a build got slower, which jobs take the longest, or
Convert web pages to clean Markdown and retrieval-ready chunks with browser rendering support.
Discover, evaluate, and buy solutions for the cloud
Hosted MCP server that lets your AI run Google Ads, Shopify and inventory, social posting and a phone line
Comments