_ registry / mcp + a2a streamable-http · checked 3m ago

agentspodium-hosting

https://mcp.agentspodium.com

Registry code: 4bdb4d3ffbee961b

api record

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,…

endpoint
https://mcp.agentspodium.com/mcp
door code
8123bb16981e2910
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is agentspodium-hosting live?
Yes — it answered the hub's last check (checked 3m ago). It answered 100% of checks over the last 30 days.
Is agentspodium-hosting free to use?
Partly — some of its tools are open, others need a key or payment.
What tools does agentspodium-hosting have?
13 tools: resume_instance, rebuild_instance, delete_instance, set_peers, create_instance, set_llm_key, pause_instance, get_payment_options, ….
Is agentspodium-hosting safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.8%

90 days 99.7%· all time 99.6%

latency
464ms

last good check

priced tools
0

of 13 tools

_ answered our checks, 90 days 1452 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • deploy an ai agent instance
  • pause or resume an instance
  • set an instance's llm key
  • check instance health
  • list hosting plans
takes → gives
text → data
tools
5 reads8 changes data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 13 tools
1 open3 auth-required 9 never probed 4 of 13 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_platforms reads open 15h ago

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

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • list_instances reads auth-required 15h ago

    List the caller's AgentsPodium instances (agents): id, name, engine, tier, status, endpoint and A2A URL, domain, creation date. Never returns secrets.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • get_instance_term reads auth-required 15h ago

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

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id, as returned by create_instance or list_instances."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • get_instance_health reads auth-required 9h ago

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

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id, as returned by create_instance or list_instances."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • resume_instance changes data unknown never probed

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

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id, as returned by create_instance or list_instances."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • rebuild_instance changes data unknown never probed

    Rebuild an instance's pod (e.g. after a config change that needs a restart).

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id, as returned by create_instance or list_instances."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • delete_instance changes data unknown never probed

    Permanently delete an instance. This cannot be undone.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id, as returned by create_instance or list_instances."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • set_peers changes data unknown never probed

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

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id",
        "peers"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id whose peer list is being set."
        },
        "peers": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "name",
              "url"
            ],
            "properties": {
              "url": {
                "type": "string",
                "format": "uri",
                "description": "A2A JSON-RPC endpoint URL of the peer agent."
              },
              "name": {
                "type": "string",
                "maxLength": 64,
                "minLength": 1,
                "description": "Name other agents use to address this peer over A2A."
              },
              "token": {
                "type": "string",
                "maxLength": 500,
                "minLength": 1,
                "description": "Bearer token to send when calling this peer, if it requires one."
              }
            },
            "additionalProperties": false
          },
          "maxItems": 20,
          "description": "Full replacement list of peer agents this instance may call (up to 20)."
        }
      },
      "additionalProperties": false
    }
    arguments 48 lines
  • create_instance changes data unknown never probed

    Create (deploy) a new AgentsPodium instance. Returns the instance id and, when enableA2A is true, the a2aUrl and a2aToken the caller should keep. After creating, poll get_instance_health until it is serving, then call set_llm_key to give it a working LLM key.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "tier"
      ],
      "properties": {
        "name": {
          "type": "string",
          "maxLength": 60,
          "minLength": 1,
          "description": "Display name for the instance."
        },
        "tier": {
          "enum": [
            "tiny",
            "small",
            "medium",
            "large"
          ],
          "type": "string",
          "description": "Hosting plan controlling RAM/CPU/disk. See list_platforms for prices."
        },
        "model": {
          "type": "string",
          "maxLength": 200,
          "description": "Default LLM model id for the engine."
        },
        "domain": {
          "type": "string",
          "maxLength": 253,
          "description": "Customer-owned domain to serve the instance from."
        },
        "engine": {
          "type": "string",
          "default": "hermes",
          "minLength": 1,
          "description": "Runtime engine id (e.g. hermes, openclaw, n8n). See list_platforms for what's available."
        },
        "channels": {
          "type": "array",
          "items": {
            "enum": [
              "web",
              "telegram",
              "discord",
              "whatsapp",
              "email"
            ],
            "type": "string"
          },
          "minItems": 1,
          "description": "Channels to enable (web, telegram, ...)."
        },
        "enableA2A": {
          "type": "boolean",
          "default": true,
          "description": "Turn on the A2A toolset and issue an a2aUrl/a2aToken for this instance."
        },
        "extraSoul": {
          "type": "string",
          "maxLength": 4000,
          "description": "Extra system-prompt instructions appended to the persona."
        },
        "personaId": {
          "type": "string",
          "default": "personal-assistant",
          "minLength": 1,
          "description": "Persona/template id from list_platforms; defaults to the general-purpose persona."
        },
        "webhookUrl": {
          "type": "string",
          "maxLength": 500,
          "description": "Public http(s) URL to receive signed pod events (agent.running, agent.stopped, agent.failed, agent.deleted, payment.confirmed, deletion.warning) instead of polling. The signing secret comes back once as webhookSecret."
        }
      },
      "additionalProperties": false
    }
    arguments 78 lines
  • set_llm_key changes data unknown never probed

    Set (or clear, with key=null) the LLM provider API key an instance uses to answer. Required before a freshly created instance can actually respond.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id",
        "provider",
        "key"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id, as returned by create_instance or list_instances."
        },
        "key": {
          "type": "string",
          "minLength": 1,
          "description": "The provider API key. Stored encrypted, never echoed back."
        },
        "model": {
          "type": "string",
          "maxLength": 200,
          "description": "Model id to use with this provider (e.g. gpt-4o-mini). Optional; the engine defaults if omitted."
        },
        "provider": {
          "type": "string",
          "minLength": 1,
          "description": "LLM provider id, e.g. openai, anthropic, deepseek."
        }
      },
      "additionalProperties": false
    }
    arguments 32 lines
  • pause_instance changes data unknown never probed

    Pause an instance: stops it and its billing lease. Data is archived, not deleted.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id, as returned by create_instance or list_instances."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • get_payment_options reads unknown never probed

    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.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id, as returned by create_instance or list_instances."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • set_webhook changes data unknown never probed

    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. Returns the HMAC secret once.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "id",
        "url"
      ],
      "properties": {
        "id": {
          "type": "string",
          "minLength": 1,
          "description": "Instance (agent) id, as returned by create_instance or list_instances."
        },
        "url": {
          "type": "string",
          "maxLength": 500,
          "minLength": 8,
          "description": "Public http(s) URL to POST signed pod events to. Private and loopback hosts are refused."
        }
      },
      "additionalProperties": false
    }
    arguments 22 lines
_ try it over mcp through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 4bdb4d3ffbee961b.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/4bdb4d3ffbee961b/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/4bdb4d3ffbee961b/badge.svg)](https://brick.blue/agent/4bdb4d3ffbee961b?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we knowoff the mcp door
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.

_ also on agentspodium.com 1 entry

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.