Edgevana Compute
Agent

Hourly GPU instances for agents over MCP and A2A. 13 tools. Every launch shows a preview and needs the user's approval before anything is charged.

Agent Card at /.well-known/agent-card.json. MCP at /mcp, A2A at /a2a/jsonrpc and /a2a/rest. Auth: X-API-Key: edgv_... or Authorization: Bearer edgv_.... Agents can launch hourly GPU offers only. Bare-metal and CPU servers can be searched and priced, not launched.

Tools

MCP + A2A

Protocols

JSON-RPC 2.0

A2A

Streamable HTTP

Transport

ENDPOINTS

Reference

URLs and auth

Agent Card

https://edgevana.com/.well-known/agent-card.json

MCP

https://mcp.edgevana.com/mcp

A2A JSON-RPC

https://mcp.edgevana.com/a2a/jsonrpc

A2A REST

https://mcp.edgevana.com/a2a/rest

Auth: X-API-Key: edgv_... or Authorization: Bearer edgv_...

Transport: Streamable HTTP

Versions: MCP 2025-03-26, A2A v0.3

TOOLS

Quick reference

All 13 tools

tool	access	params
search_servers	Read only	server_type, query, region, site, launchable_only, max_price_hourly, min_vram_gb, min_gpus, min_direct_ports, min_reliability, min_ram_gb, min_cores, sort, detail_sku, offset, limit
get_server_specs	Read only	sku
get_locations	Read only	country, city
check_availability	Read only	site, server_type, sku, limit
get_pricing	Read only	server_type, item_id, search, include_locations, limit
compare_to_cloud	Read only	workload_type, cloud_provider
get_platform_info	Read only	topic
launch_instance	Preview, then confirm (spends money)	offer_id (required), site (required), ssh_key, custom_name, disk_gb, ports, onstart, payment_source_id, coupon_ids, confirm, approved (required when confirm: true), idempotency_key (required when confirm: true)
request_reserved_instance	Preview, then confirm (no charge)	offer_id (required), site (required), email (required), first_name (required), last_name, quantity, term_months, notes, confirm
list_instances	Read only	limit, offset
get_instance	Read only	instance_id (required)
update_instance	Changes instance settings, no charge	instance_id (required), ssh_key, cluster, deployment_type, custom_name
terminate_instance	Preview, then confirm (destructive)	instance_id (required), when, cancel_reason, confirm

LIFECYCLE

Tool calls per step

5-step flow

1. Search

Pick an offer with launch_status "available". Note its offer_id and one of its hourly_sites.

{
  "tool": "search_servers",
  "args": {
    "server_type": "gpu",
    "query": "H100",
    "launchable_only": true,
    "sort": "price"
  }
}

2. Preview launch

Returns the hourly price and an approval object, plus the deposit due today when the quote succeeds. Nothing is created. Show it to the user. If the deposit could not be quoted (approval.deposit_due_cents is null), run the preview again: a confirm without a deposit quote is refused.

{
  "tool": "launch_instance",
  "args": {
    "offer_id": "52708889",
    "site": "Seoul, South Korea",
    "ssh_key": "ssh-ed25519 AAAA..."
  }
}

3. Confirm launch

After the user approves: same args, confirm: true, the approval object unchanged, and a unique idempotency_key. Any change in the hourly price is refused, and the approved deposit is the ceiling.

{
  "tool": "launch_instance",
  "args": {
    "offer_id": "52708889",
    "site": "Seoul, South Korea",
    "ssh_key": "ssh-ed25519 AAAA...",
    "confirm": true,
    "approved": {
      "hourly_cents": 249,
      "deposit_due_cents": 2500
    },
    "idempotency_key": "00000000-0000-4000-8000-000000000001"
  }
}

4. Monitor

Check connection.status: ready, provisioning, failed, destroying or destroyed. destroying means the instance is cancelled but not yet confirmed gone. When ready, connection.ports lists mapped ports. connection.public_ip and connection.ssh can be null even when ready. Check connection.ssh before you read its host, port and user. When status is not ready, public_ip and ssh are null, and ports is [].

{
  "tool": "get_instance",
  "args": {
    "instance_id": "example-instance-id"
  }
}

5. Destroy

Call without confirm for a preview, then again with confirm: true. Hourly GPU instances are destroyed immediately; EndOfTerm is refused for them.

{
  "tool": "terminate_instance",
  "args": {
    "instance_id": "example-instance-id",
    "confirm": true
  }
}

TOOLS

Schema

Tool call examples

{ "tool": "search_servers", "args": {"server_type":"gpu","query":"H100","launchable_only":true,"sort":"price","limit":10} }

{ "tool": "get_server_specs", "args": {"sku":"BM-9254-384G-25G"} }

{ "tool": "get_locations", "args": {"country":"United States"} }

{ "tool": "check_availability", "args": {"server_type":"gpu","site":"Chicago"} }

{ "tool": "get_pricing", "args": {"server_type":"gpu","search":"H100","limit":10} }

{ "tool": "compare_to_cloud", "args": {"workload_type":"ai_inference","cloud_provider":"aws"} }

{ "tool": "get_platform_info", "args": {"topic":"compute"} }

{ "tool": "launch_instance", "args": {"offer_id":"52708889","site":"Seoul, South Korea","ssh_key":"ssh-ed25519 AAAA..."} }

{ "tool": "request_reserved_instance", "args": {"offer_id":"52700000","site":"Dallas, TX","email":"[email protected]","first_name":"Alex","quantity":8,"term_months":12} }

{ "tool": "list_instances", "args": {"limit":10} }

{ "tool": "get_instance", "args": {"instance_id":"example-instance-id"} }

{ "tool": "update_instance", "args": {"instance_id":"example-instance-id","custom_name":"inference-1"} }

{ "tool": "terminate_instance", "args": {"instance_id":"example-instance-id"} }

CONNECT

Config

Copyable configs

MCP config (JSON)

{
  "mcpServers": {
    "edgevana": {
      "url": "https://mcp.edgevana.com/mcp",
      "headers": {
        "X-API-Key": "<your-edgv_...-key>"
      }
    }
  }
}

A2A JSON-RPC (curl)

curl -X POST https://mcp.edgevana.com/a2a/jsonrpc \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_EDGV_API_KEY" \
  -d '{"jsonrpc":"2.0","method":"message/send","id":1,"params":{"message":{"kind":"message","messageId":"msg-1","role":"user","parts":[{"kind":"text","text":"Find GPU servers"}]}}}'

Agent Card (curl)

curl https://edgevana.com/.well-known/agent-card.json

Edgevana ComputeAgent