_ registry / mcp streamable-http · checked 1h ago

evafarm

https://evafarmstore.ru

Registry code: 4e535b409d65e101

api record

EvaFarm rents remote GPU workstations ("nodes") for 3D rendering and CG — Cinema 4D, Blender, Houdini with Redshift, Octane and other engines — billed per minute. Use list_nodes to see what is free right now and what is installed, get_node for one machine, estimate_cost to price a render or a block of hours, service_status for a quick availability summary, and rental_guide for how renting, billing and connecting work. This server is read-only: renting happens in the EvaFarm app (opens in Telegram), so hand the user the app link when they want to start. Prices are per node per hour; billing is…

endpoint
https://evafarmstore.ru/mcp
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 evafarm live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is evafarm free to use?
Yes — the hub reached it with no key and no payment.
What tools does evafarm have?
5 tools: get_node, service_status, estimate_cost, list_nodes, rental_guide.
Is evafarm 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
100%

90 days 100%· all time 100%

latency
403ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ 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 5 tools
2 open 3 never probed 2 of 5 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_nodes open 1h ago

    The EvaFarm node catalog with live status (available / busy / reserved / maintenance), hardware, hourly price and installed software and render engines. Filter to find a machine for a job.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "gpu": {
          "type": "string",
          "description": "GPU model substring, e.g. \"4090\" or \"5090\"."
        },
        "engine": {
          "type": "string",
          "description": "Required render engine, e.g. \"redshift\", \"octane\", \"cycles\"."
        },
        "currency": {
          "enum": [
            "RUB",
            "USD"
          ],
          "type": "string",
          "description": "Price currency. Default RUB."
        },
        "software": {
          "type": "string",
          "description": "Required application, e.g. \"cinema4d\", \"blender\", \"houdini\"."
        },
        "available_only": {
          "type": "boolean",
          "description": "Only nodes free to rent right now."
        }
      },
      "additionalProperties": false
    }
    arguments 30 lines
  • rental_guide open 1h ago

    How to start renting on EvaFarm: sign-in, projects and wallets, billing rules, connecting via AnyDesk/RustDesk, teams, privacy, and the links to the app, the site and support.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "language": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the guide. Default en."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • get_node unknown never probed

    Full details of one node by its label, e.g. "NODE_03" (also accepts "3" or "node 3").

    mcp-tool

    {
      "type": "object",
      "required": [
        "label"
      ],
      "properties": {
        "label": {
          "type": "string",
          "description": "Node label, e.g. \"NODE_03\"."
        },
        "currency": {
          "enum": [
            "RUB",
            "USD"
          ],
          "type": "string",
          "description": "Price currency. Default RUB."
        }
      },
      "additionalProperties": false
    }
    arguments 21 lines
  • service_status unknown never probed

    How many nodes are available, busy, reserved or in maintenance right now.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • estimate_cost unknown 1h ago

    Price a rental the way EvaFarm bills it: per active minute, rounded up, no minimum; node preparation is not billed. Give a duration (hours and/or minutes) or a render (frames × seconds_per_frame measured on that kind of node). With a node label the estimate uses its rate; without one it prices every hardware configuration in the catalog. nodes_count > 1 splits the frames evenly across that many identical nodes.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "node": {
          "type": "string",
          "description": "Node label to price, e.g. \"NODE_03\". Omit to compare all configurations."
        },
        "hours": {
          "type": "number",
          "minimum": 0,
          "description": "Rental duration in hours (may be combined with minutes)."
        },
        "frames": {
          "type": "integer",
          "minimum": 1,
          "description": "Number of frames to render."
        },
        "minutes": {
          "type": "number",
          "minimum": 0,
          "description": "Rental duration in minutes."
        },
        "currency": {
          "enum": [
            "RUB",
            "USD"
          ],
          "type": "string",
          "description": "Price currency. Default RUB."
        },
        "nodes_count": {
          "type": "integer",
          "maximum": 64,
          "minimum": 1,
          "description": "Identical nodes rendering in parallel. Default 1."
        },
        "seconds_per_frame": {
          "type": "number",
          "description": "Render time of one frame on that node, in seconds.",
          "exclusiveMinimum": 0
        }
      },
      "additionalProperties": false
    }
    arguments 44 lines
_ try it 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 4e535b409d65e101.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/4e535b409d65e101/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/4e535b409d65e101/badge.svg)](https://brick.blue/agent/4e535b409d65e101?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 know
card completeness
90%

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.