Edgevana Compute
Agent

Bare-metal GPU and CPU provisioning. 12 tools. MCP and A2A protocols. Authenticated via X-API-Key.

Agent Card at /.well-known/agent-card.json. MCP at /mcp, A2A at /a2a/jsonrpc and /a2a/rest. Auth: X-API-Key or Authorization: Bearer. Full control: search, price, launch, monitor, terminate.

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 12 tools

tool	method	path	params
search_servers	GET	/sdk/inventory/shop-items	server_type, region
get_server_specs	GET	/sdk/inventory/server-specs	sku
get_locations	GET	/sdk/inventory/sites	country
check_availability	GET	/sdk/inventory/available-servers	site, server_type
get_pricing	GET	/sdk/catalog/items + item-prices	item_id, limit
compare_to_cloud	-	Static	workload_type, cloud_provider
get_platform_info	-	Static	topic
launch_instance	POST	/sdk/instances/launch	item_price_id, sku, site, site_id, ssh_key, deploy_env, gpu_count, custom_name
list_instances	GET	/sdk/instances	limit, offset
get_instance	GET	/sdk/instances/{id}	instance_id
update_instance	PATCH	/sdk/instances/{id}	instance_id, ssh_key, cluster, deployment_type, custom_name
terminate_instance	DELETE	/sdk/instances/{id}	instance_id, when, cancel_reason

LIFECYCLE

Tool calls per step

Five-step flow

1. Search

{
  "tool": "search_servers",
  "args": {
    "region": "US",
    "server_type": "gpu"
  }
}

2. Price

{
  "tool": "get_pricing",
  "args": {
    "item_id": "GPU-H100-80G-M",
    "limit": 10
  }
}

3. Launch

{
  "tool": "launch_instance",
  "args": {
    "item_price_id": "GPU-H100-80G-M",
    "sku": "GPU-H100-80G",
    "site": "San Diego, CA",
    "ssh_key": "ssh-ed25519 AAAA..."
  }
}

4. Monitor

{
  "tool": "get_instance",
  "args": {
    "instance_id": "sub_abc123"
  }
}

5. Terminate

{
  "tool": "terminate_instance",
  "args": {
    "instance_id": "sub_abc123",
    "when": "Immediately"
  }
}

TOOLS

Schema

Tool call examples

{ "tool": "search_servers", "args": {"server_type":"gpu","region":"US"} }

{ "tool": "get_server_specs", "args": {"sku":"gpu-a100-80g"} }

{ "tool": "get_locations", "args": {} }

{ "tool": "check_availability", "args": {"site":"LAX1","server_type":"gpu"} }

{ "tool": "get_pricing", "args": {"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": {"item_price_id":"GPU-H100-80G-M","sku":"GPU-H100-80G","site":"San Diego, CA","ssh_key":"ssh-ed25519 AAAA..."} }

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

{ "tool": "get_instance", "args": {"instance_id":"sub_abc123"} }

{ "tool": "update_instance", "args": {"instance_id":"sub_abc123","custom_name":"prod-inference"} }

{ "tool": "terminate_instance", "args": {"instance_id":"sub_abc123","when":"Immediately"} }

CONNECT

Config

Copyable configs

MCP config (JSON)

{
  "mcpServers": {
    "edgevana": {
      "url": "https://mcp.edgevana.com/mcp",
      "env": {
        "EDGEVANA_API_KEY": "<your-edgv_...-key>"
      }
    }
  }
}

A2A JSON-RPC (curl)

curl -X POST https://mcp.edgevana.com/a2a/jsonrpc \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_EDGV_API_KEY" \
  -d '{"jsonrpc":"2.0","method":"message","id":1,"params":{"message":{"role":"user","parts":[{"text":"List your tools"}]}}}'

Agent Card (curl)

curl -H "X-API-Key: edgv_..." https://edgevana.com/.well-known/agent-card.json

Edgevana ComputeAgent