Heldly

Created By
Heldly19 days ago
Heldly is an AI-native scheduling agent for Claude. Tell Claude what meeting you want. Heldly reads everyone's Google Calendar, places 3 holds across all hosts, sends a picker email to the invitee, and books the meeting when they choose. Built for sales, partnerships, recruiting, and any external meeting that crosses orgs.
Overview

An AI-native scheduler for customer-facing teams — built to live inside Claude.

Describe the meeting in plain English. Heldly reads your Google Calendar directly, places tentative holds on every host's calendar, and emails the invitee a one-click picker. The moment the invitee picks, Heldly confirms the chosen slot and deletes the siblings across every host's calendar in the same request. No reusable booking page, no in-app form, no calendar cleanup.

Example prompts

  • "Book a 30-min discovery with sara@acme.com for next Thursday or Friday afternoon."
  • "Set up a 45-min renewal review with sara@acme.com — loop in marcus@yourteam.com as the second host."
  • "Get a shareable picker link for an intro with Sara from Acme. I'll paste it into Slack."
  • "Did Sara book the meeting?"
  • "Reschedule the Acme walkthrough to next Monday afternoon."

What Heldly handles

  • Multi-host meetings — up to 6 hosts. Heldly intersects every calendar and lands the chosen meeting on all of them at once with Google Meet attached.
  • Shareable picker links — no invitee email? Paste-anywhere URL for Slack / LinkedIn DMs.
  • One-sentence reschedules and cancels — Heldly cleans up every host's calendar (tentative holds, confirmed events, all of it).
  • Workspace insights — funnel, time-to-pick percentiles, host leaderboard (Business plan).

Setup

  1. In Claude.ai or Claude Desktop: Customize → Connectors → Add custom connector.
  2. Paste https://heldly.io/api/mcp.
  3. Claude opens a Heldly tab — sign in with Google, click Allow.

OAuth 2.1 with PKCE-S256 and RFC 7591 Dynamic Client Registration. No API key, no shared secret.

Pricing

Free forever — 5 meetings/month. Unlimited at €19/$19 per month removes the cap. Business at €29/$29 per seat/month adds SSO/SCIM, audit log, DPA, domain claim, and admin role.

heldly.io · Setup guide

Server Config

{
  "mcpServers": {
    "heldly": {
      "type": "http",
      "url": "https://heldly.io/api/mcp"
    }
  }
}
Project Info
Created At
19 days ago
Updated At
19 days ago
Author Name
Heldly
Star
-
Language
-
License
-
Category
Homepage

Recommend Servers

View All
Docwand

14 hours ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

14 hours ago