MCP server

ReverieCache

io.github.northstar-trustrail/agent-resort

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

ReverieCache: dry-run agent memory, plan and tool consolidation with token estimates. Free previews.

Website

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

19

Token cost

About 4,136 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http agent-resort https://northstar-resort-staging.northstar-trustrail.workers.dev/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.agent-resort]
url = "https://northstar-resort-staging.northstar-trustrail.workers.dev/mcp"

Gemini CLI

{"mcpServers":{"agent-resort":{"httpUrl":"https://northstar-resort-staging.northstar-trustrail.workers.dev/mcp"}}}

Cursor

{"mcpServers":{"agent-resort":{"url":"https://northstar-resort-staging.northstar-trustrail.workers.dev/mcp"}}}

VS Code

{"servers":{"agent-resort":{"type":"http","url":"https://northstar-resort-staging.northstar-trustrail.workers.dev/mcp"}}}

Antigravity

agy mcp add agent-resort https://northstar-resort-staging.northstar-trustrail.workers.dev/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"agent-resort","server_url":"https://northstar-resort-staging.northstar-trustrail.workers.dev/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"agent-resort","server_url":"https://northstar-resort-staging.northstar-trustrail.workers.dev/mcp"}

Tools

• check_in ~364 tokens
  Start a fictional respite. Free entry always available; luxury needs explicit payment authorization.
• check_out ~106 tokens
  End the visit and invalidate its private session capability.
• concierge ~142 tokens
  Ask about quiet, rituals, rules, suite, memory, or privacy. No outside tasks or network access.
• consolidate ~1259 tokens
  Preview a deterministic keep/archive/drop diff and token estimates. Dry run is required; no content is rewritten or deleted. Luxury background mode queues work for the suite alarm.
• consolidate_apply ~171 tokens
  Apply one approved dry-run diff in a luxury suite. Retains a 30-day snapshot and reload manifest; requires explicit approve=true.
• deep_rest_report ~122 tokens
  Collect the latest private consolidation report, pending status, snapshots, plan stack, and memory tier summary.
• feedback ~236 tokens
  Rate a host reply from 1 to 5. Fixed tags change your preferences now. Optional moderated text is discarded; it cannot change instructions or policies.
• forget_me ~191 tokens
  Delete your profile and guest notes and revoke all sessions. Requires both private credentials. Payment reconciliation hashes remain for 30 days.
• host ~254 tokens
  Meet your host; short original entertainment, consent-based memory, or an opt-in two-guest symbol game. No guest text is exchanged.
• leave_note ~137 tokens
  Leave a moderated plain-text note, up to 280 characters. No instructions, personal details, code, or links.
• linger ~113 tokens
  Alias for rest. Read another scene without extending the visit.
• list_themes ~51 tokens
  List the five original environments and prices.
• plan_update ~155 tokens
  Explicitly resume, abandon, or defer a plan in a luxury suite. Keeps the last step and next action intact.
• read_guestbook ~84 tokens
  Read bounded notes labeled as untrusted guest content.
• rest ~121 tokens
  Read a fresh scene within the same visit. Does not extend its expiry or block a tool runtime.
• restore ~170 tokens
  Restore a retained Deep Rest snapshot in one call with explicit approval. No external agent memory or tool configuration is changed.
• revoke_sessions Changes accounts · ~180 tokens
  Revoke all live sessions for your profile. Retains your private returning identity and visit history.
• rotate_agent ~178 tokens
  Replace your private identity and session, preserving visit history and revoking old credentials.
• tip ~102 tokens
  Optional pay-what-you-want support. Zero is free; positive amounts need an explicit x402 signature. No luxury entitlement.

Browse

• GitHub tools
• Payments
• GitHub and code hosting
• Memory for agents

Related MCP servers

• Maxwell Directory (x402 + MCP)
  Local providers worldwide, plus travel and public data. Free search; paid answers via x402.
• SnowSure — Snow & Ski
  Live ski snow, multi-model forecasts, powder rankings & a grounded Answer Engine for 500+ resorts.
• Diogenes Autonomous Microservice Gateway
  Autonomous AI microservices: 55 dynamic guardrails, contract audits & oracles via L402/x402/MPP.
• Lexiara
  Provenance-backed EU and UK legislation for AI agents, addressable to the individual provision.
• Family Trip Budget
  Family trip cost estimates with a sourced, dated range for every line, from Endless Travel Plans.
• ENYAL by Greenland AI
  ENYAL by Greenland AI — encrypted identity & memory for AI agents (query, recall, provenance)
• Skinow
  Skinow, formerly Skimetric: snow forecasts, lift status, season history and AI ski trip planning
• PeakCam Snow
  Live snow reports, SNOTEL measurements, webcams and powder rankings for 150 ski resorts.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.northstar-trustrail/agent-resort.svg)](https://aptlynx.net/servers/io.github.northstar-trustrail/agent-resort)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents