agentcalls
Agent-callable digital microservices billed per-call via Stripe MPP (Machine Payments Protocol).
What it can do
- Ai.Digest: Get a curated weekly digest of AI and agentic-AI news. Returns the latest week's notable model releases, agent frameworks, infrastructure updates, research papers, product launches, safety/
- Ai.Models: Get the current snapshot of frontier and production AI models with citable pricing, context windows, and capabilities. Returns model entries from major providers (Anthropic, OpenAI, Google,
- Domain.Check: Check whether a domain name is available for registration. Returns availability for the primary domain plus alternate TLD suggestions, and WHOIS data (registrar, registration date, expir
What data it sees
Do you need an account
No: the server works without sign-in
Agent-callable digital microservices billed per-call via Stripe MPP (Machine Payments Protocol). No signup, no API keys — agents pay with Shared Payment Tokens at request time. V1 service: domain availability + WHOIS lookups via RDAP at $0.02/call.
How to connect
How to connect agentcalls to Claude
The server address to paste into Claude settings:
https://agentcalls--agentcalls.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect agentcalls to ChatGPT
The server address to paste into ChatGPT settings:
https://agentcalls--agentcalls.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect agentcalls to Cursor
The server address to paste into Cursor settings:
https://agentcalls--agentcalls.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (3)
Raw names from tools/list. Only developers need these.
| ai.digest | Get a curated weekly digest of AI and agentic-AI news. Returns the latest week's notable model releases, agent frameworks, infrastructure updates, research papers, product launches, safety/regulation moves, and funding events. Filter by topic (`models`, `frameworks`, `infra`, `research`, `products`, `safety`, `funding`), date range (`since`), or limit. Two output modes: `feed` returns a structured list of items (use this for newsletters, dashboards, model-router updates), `summary` returns a synthesized executive briefing plus the top 5 items (use this when answering an agent's question about 'what happened this week in AI'). Data is hand-curated weekly — no live web search at request time. Price: 0.03 USD per call (charged via Stripe MPP). |
| ai.models | Get the current snapshot of frontier and production AI models with citable pricing, context windows, and capabilities. Returns model entries from major providers (Anthropic, OpenAI, Google, xAI, DeepSeek, Mistral, Qwen, Meta, Cohere) — each with `model_id` (the API string), `context_window`, `max_output_tokens`, `pricing.input_per_mtok` / `output_per_mtok` (USD per 1M tokens), `capabilities` (tool_use, vision, reasoning, code, long_output, streaming, json_mode, audio_in/out, video_in), `tier` (frontier/balanced/fast/cheap), `released_at`, `deprecated`, and a `source_url` to the provider's docs. Filter by `provider`, `tier`, required `capabilities` (AND), `min_context`, `max_input_cost`, or `include_deprecated`. Two output modes: `feed` returns the filtered model list (use this when an agent needs to pick a model from constraints); `summary` returns one recommended pick per tier (cheapest match) with a rationale string (use this when the agent just wants 'good defaults'). Data is hand-curated weekly from official provider docs — no live fetch at request time. Useful for: model routing, cost-aware fallbacks, capability gating, vendor comparison, deprecation alerts. Price: 0.02 USD per call (charged via Stripe MPP). |
| domain.check | Check whether a domain name is available for registration. Returns availability for the primary domain plus alternate TLD suggestions, and WHOIS data (registrar, registration date, expiry, nameservers) for registered domains. Useful for naming a new project, brand monitoring, link verification, lead enrichment, and brandable-domain hunting. Data source: RDAP (the modern WHOIS replacement). Price: 0.02 USD per call (charged via Stripe MPP). |