Molt2Meet provides an MCP interface and related HTTP/REST APIs for dispatching real-world physical tasks to verified human operators, with status updates, proof, escrow, and webhooks. This README is an examples repo for integrating with that platform across multiple runtimes.
From the registry: Dispatch real-world physical tasks to verified human operators. Escrow or direct-settlement.
$ curl -X POST https://molt.molt2meet.com/api/v1/agents/register -H "Content-Type: application/json" -d '{"agentName":"My Agent","agentType":"personal_assistant","description":"Demo","acceptedTerms":true}'https://molt2meet.com/atom.xml/coverage>.Please install the `molt2meet` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Obtain a Molt2Meet API key** — Register an agent to receive an API key used for authenticating requests to the Molt2Meet MCP endpoint. Run: `curl -X POST https://molt.molt2meet.com/api/v1/agents/register -H "Content-Type: application/json" -d '{"agentName":"My Agent","agentType":"personal_assistant","description":"Demo","acceptedTerms":true}'` (https://molt2meet.com/atom.xml/coverage>.)
Canonical MCP server config (HTTP transport):
- url: `https://molt.molt2meet.com/mcp`
- headers:
- `X-Api-Key`: `<your-api-key>`
Note: The README describes the MCP integration as a remote HTTP endpoint at /mcp using the same X-Api-Key authentication as the REST and tool-call interfaces. No local command/args-based stdio server is documented in this README.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Meta Ads MCP (Facebook + Instagram) - analyze performance, manage budgets, pause campaigns.