Cloud Services

defispace.com

Manages AgentsPodium cloud instances for deploying and monitoring AI agents.

1 endpoint13 known toolsFirst detected September 9, 2026Last detected September 9, 2026

ENDPOINT 1

https://mcp.agentspodium.com/mcp

No auth detected

MCP server metadata

Name: agentspodium-hosting
Version: 1.0.4

Capabilities

prompts.listChangedtools.listChangedresources.listChanged

Server instructions

AgentsPodium Hosting turns an AgentsPodium account into deployable AI agent pods (instances): pick an engine and hosting tier, deploy one, wire in the customer's own LLM key, and manage its lifecycle and billing. Every tool that touches an account requires an AgentsPodium API key (ak_live_...), created at https://agentspodium.com/account, except list_platforms which reads the public engine/tier catalogue. Recommended order: list_platforms to choose an engine and tier, then create_instance, then poll get_instance_health until serving is true, then set_llm_key so the pod can actually answer, then get_instance_term to check the billing clock. Full docs, including every tool's request/response shape: https://hosting.defispace.com/llms.txt.

Known tools 13

list_platforms

List available AgentsPodium engines (platforms) and hosting plans (tiers), with prices and capabilities.

Inferred read-only

list_instances

List the caller's AgentsPodium instances (agents): id, name, engine, tier, status, endpoint and A2A URL, domain, creation date.

Inferred read-only

create_instance

Create (deploy) a new AgentsPodium instance.

Potential side effects

get_instance_health

Check whether an instance is reachable and serving, plus its status and quota state.

Inferred read-only

get_instance_term

Get the billing term (trial/paid/grace) for an instance, including when it renews or expires.

Inferred read-only

set_llm_key

Set (or clear, with key=null) the LLM provider API key an instance uses to answer.

Inferred read-only

pause_instance

Pause an instance: stops it and its billing lease.

Inferred read-only

resume_instance

Resume a previously paused instance, rebuilding it from its archive.

Inferred read-only

rebuild_instance

Rebuild an instance's pod (e.

Inferred read-only

delete_instance

Permanently delete an instance.

Potential side effects

get_payment_options

Get ways to pay for an instance's plan: card/subscription buy links, crypto payment info, and Telegram Stars info (crypto and Stars are in beta testing), plus the instance's current term.

Potential side effects

set_peers

Set the list of other A2A agents this instance is allowed to call by name.

Inferred read-only

set_webhook

Register a URL that receives signed POSTs when the instance comes up, stops, fails, is deleted, when a payment is confirmed and before deletion for non-payment — instead of polling get_instance_health.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentspodium-hosting]
url = "https://mcp.agentspodium.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentspodium-hosting": {
      "type": "http",
      "url": "https://mcp.agentspodium.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentspodium-hosting
Remote MCP URL: https://mcp.agentspodium.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentspodium-hosting": {
      "url": "https://mcp.agentspodium.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentspodium-hosting": {
      "type": "http",
      "url": "https://mcp.agentspodium.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentspodium-hosting",
  "transport": "streamable-http",
  "url": "https://mcp.agentspodium.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.