_ registry / mcp streamable-http · checked 7h ago

turbo

https://exducer.ai

Registry code: 43c65f41fdc5d06f

api record

ExducerAI rents whole GPUs in Montréal (CA-QC) by the hour and serves an OpenAI-compatible Models API. Amounts are in CAD. Read prices, servers and templates from the tools; never from memory. A booking is a request: it runs later (wait_for_deployment). Billing is per minute while it runs. Never call create_booking, extend_deployment, set_auto_renew or stop_deployment without the user's explicit yes; quote first. A stop deletes the deployment's disk. A key that starts with tml_test_ is a sandbox key: everything is simulated and nothing is charged. To run commands on a deployment use SSH (the…

endpoint
https://exducer.ai/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 turbo live?
Yes — it answered the hub's last check (checked 7h ago). It answered 100% of checks over the last 30 days.
Is turbo free to use?
Partly — some of its tools are open, others need a key or payment.
What tools does turbo have?
22 tools: get_pricing, read_doc, get_deployment, wait_for_deployment, create_booking, set_auto_renew, stop_deployment, list_deployments, ….
Is turbo 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
736ms

last good check

priced tools
0

of 22 tools

_ answered our checks, 90 days 3 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 22 tools
4 open5 auth-required 13 never probed 9 of 22 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.

  • get_service_status open 34h ago

    The public status of each service (console, API, GPU region, object storage, Models API).

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • list_servers open 7h ago

    The servers a booking can name: id (the server_id of quote_booking and create_booking), GPU model, price per GPU-hour in CAD, allowed_gpu_counts, region, and whether it is free now.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • list_templates open 7h ago

    The templates a booking can name: slug, name, the container image it runs, category. Without a template a deployment runs the default PyTorch image.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "q": {
          "type": "string",
          "description": "Free-text filter."
        },
        "category": {
          "type": "string",
          "description": "Only this category slug."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • check_availability open 2d ago

    One yes or no per GPU model: is it free right now. A no does not block a request; the request waits for capacity.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • get_billing auth-required 2d ago

    The prepaid balance and the most recent credit ledger lines (top-ups and charges) in CAD.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 20,
          "maximum": 200,
          "minimum": 1,
          "description": "How many ledger lines, newest first."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • get_storage_usage auth-required 34h ago

    Object storage: GB stored, active keys, price per GB-month and the amount billed this month (not available to a sandbox key).

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • get_account auth-required 2d ago

    The account behind the API key (email, company, type), whether the key is a sandbox key, and the prepaid balance in CAD (simulated under a sandbox key).

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • get_usage auth-required 34h ago

    What the account was charged for GPU time, object storage and the Models API over a date range, in CAD before tax. Only deployments that ran appear.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "to": {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "Last day, YYYY-MM-DD, included. Default: today."
        },
        "from": {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "First day, YYYY-MM-DD, America/Toronto. Default: the first of the month."
        },
        "group": {
          "enum": [
            "day",
            "type"
          ],
          "type": "string",
          "default": "day",
          "description": "day: one row per day and type. type: one row per type for the range."
        },
        "deployment_id": {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]{1,64}$",
          "description": "Only the GPU time of this deployment."
        }
      },
      "additionalProperties": false
    }
    arguments 31 lines
  • list_invoices auth-required 7h ago

    The account's invoices (not available to a sandbox key).

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • get_pricing unknown never probed

    List prices in CAD: GPU-hour per GPU model, object storage per GB-month, and the Models API. Use this instead of any remembered price.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • read_doc unknown never probed

    One documentation page as Markdown, by its slug (from search_docs). Read the page before answering a question about how the platform works.

    mcp-tool

    {
      "type": "object",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9-]{1,64}$",
          "description": "The page slug, e.g. c-provisioning (from search_docs)."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • get_deployment unknown never probed

    One deployment in full: state and reason, SSH host and port, the host key fingerprint to verify, rate per GPU-hour, cost so far, start and end time, endpoints.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]{1,64}$",
          "description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • wait_for_deployment unknown never probed

    Poll a deployment until it reaches a state (default running) or a final state, for at most 50 seconds per call. Returns reached, the current state and whether it is final. While reached is false and final is false, call again; a live request can stay requested until staff place it, so after a few minutes tell the user and check back later instead of looping.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]{1,64}$",
          "description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
        },
        "until": {
          "enum": [
            "requested",
            "queued",
            "provisioning",
            "running",
            "stopped",
            "ended",
            "failed",
            "cancelled"
          ],
          "type": "string",
          "default": "running",
          "description": "The state to wait for."
        },
        "timeout_seconds": {
          "type": "integer",
          "default": 45,
          "maximum": 50,
          "minimum": 1,
          "description": "How long to wait in this call."
        }
      },
      "additionalProperties": false
    }
    arguments 36 lines
  • create_booking unknown never probed

    Send a GPU request. It is created as requested or queued and becomes running later (use wait_for_deployment); nothing is charged before it runs, then credit is drawn per minute. Quote first with quote_booking and get the user's yes on the total. Retry-safe: see idempotency_key.

    mcp-tool

    {
      "type": "object",
      "required": [
        "server_id",
        "gpus",
        "hours",
        "confirm"
      ],
      "properties": {
        "gpus": {
          "type": "integer",
          "maximum": 4096,
          "minimum": 1,
          "description": "Number of GPUs: one of the server's allowed_gpu_counts."
        },
        "hours": {
          "type": "integer",
          "maximum": 720,
          "minimum": 1,
          "description": "Duration in hours. A live booking has a minimum (the API answers duration_below_minimum under it)."
        },
        "image": {
          "type": "string",
          "maxLength": 255,
          "description": "A container image instead of a template. Only images the platform already runs are accepted."
        },
        "notes": {
          "type": "string",
          "maxLength": 1000,
          "description": "A note for the staff who place the request."
        },
        "confirm": {
          "type": "boolean",
          "description": "Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely."
        },
        "template": {
          "type": "string",
          "maxLength": 120,
          "description": "Template slug from list_templates. Left out: the default PyTorch image."
        },
        "server_id": {
          "type": "string",
          "description": "Server id from list_servers."
        },
        "auto_renew": {
          "type": "boolean",
          "description": "Renew by itself at the end of the term while credit lasts."
        },
        "renew_hours": {
          "type": "integer",
          "maximum": 720,
          "minimum": 1,
          "description": "The renewal block in hours."
        },
        "sandbox_speed": {
          "type": "integer",
          "maximum": 60,
          "minimum": 1,
          "description": "Sandbox keys only: shorten every simulated wait this many times."
        },
        "ssh_public_key": {
          "type": "string",
          "maxLength": 4096,
          "description": "The text of the user's SSH public key (.pub), one key per line. Left out, the keys saved on the account are used. Required with a sandbox key."
        },
        "idempotency_key": {
          "type": "string",
          "maxLength": 128,
          "minLength": 8,
          "description": "Optional. 8 to 128 characters. Reuse the same value when retrying the same request. Left out, one is derived from the request and the UTC date, so the identical request the same day returns the first answer; pass a new value to really do it a second time."
        },
        "client_reference": {
          "type": "string",
          "maxLength": 128,
          "description": "Your own reference for this deployment; unique among the account's live deployments."
        },
        "sandbox_scenario": {
          "enum": [
            "immediate",
            "busy",
            "marketplace_release",
            "fail_start",
            "host_unreachable",
            "insufficient_credit",
            "capacity_timeout",
            "slow_start"
          ],
          "type": "string",
          "description": "Sandbox keys only: the lifecycle to simulate."
        }
      },
      "additionalProperties": false
    }
    arguments 93 lines
  • set_auto_renew unknown never probed

    Turn automatic renewal of a deployment on or off. On, it keeps running and drawing credit past its end time until it is turned off or credit runs short, so get the user's yes first.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id",
        "enabled",
        "confirm"
      ],
      "properties": {
        "id": {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]{1,64}$",
          "description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
        },
        "confirm": {
          "type": "boolean",
          "description": "Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely."
        },
        "enabled": {
          "type": "boolean",
          "description": "true: renew at the end of each term while credit lasts. false: end as booked."
        },
        "renew_hours": {
          "type": "integer",
          "maximum": 720,
          "minimum": 1,
          "description": "The renewal block in hours (default 720)."
        }
      },
      "additionalProperties": false
    }
    arguments 30 lines
  • stop_deployment unknown never probed

    Stop a deployment now: billing ends at this minute and its container and NVMe scratch disk are deleted and cannot be recovered. A request that has not started is withdrawn at no cost. Make sure results are copied off, tell the user the disk is deleted, and get a yes first.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id",
        "confirm"
      ],
      "properties": {
        "id": {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]{1,64}$",
          "description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
        },
        "confirm": {
          "type": "boolean",
          "description": "Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely."
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • list_deployments unknown never probed

    Every deployment of the account with its state, GPU count, rate, cost so far and end time. States: requested, queued, provisioning, running, then stopped, ended, failed or cancelled.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "include_sandbox": {
          "type": "boolean",
          "description": "On a live key, also list sandbox deployments."
        }
      },
      "additionalProperties": false
    }
    arguments 11 lines
  • quote_booking unknown never probed

    What a booking would cost in CAD: GPU cost, tax and total for the whole duration, and the hourly rates. Books nothing and charges nothing. Always quote and show the user the total before create_booking.

    mcp-tool

    {
      "type": "object",
      "required": [
        "server_id",
        "gpus",
        "hours"
      ],
      "properties": {
        "gpus": {
          "type": "integer",
          "maximum": 4096,
          "minimum": 1,
          "description": "Number of GPUs: one of the server's allowed_gpu_counts."
        },
        "hours": {
          "type": "integer",
          "maximum": 720,
          "minimum": 1,
          "description": "Duration in hours."
        },
        "server_id": {
          "type": "string",
          "description": "Server id from list_servers."
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • search_docs unknown never probed

    Search the documentation by keyword. Returns the matching sections with a snippet and the slug to pass to read_doc.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 6,
          "maximum": 20,
          "minimum": 1,
          "description": "How many sections to return."
        },
        "query": {
          "type": "string",
          "description": "What to look for, in a few words."
        }
      },
      "additionalProperties": false
    }
    arguments 20 lines
  • list_ssh_keys unknown never probed

    The SSH public keys saved on the account: a booking with no ssh_public_key uses them (not available to a sandbox key). Adding or removing keys is done by the user in the console.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • get_deployment_events unknown never probed

    The state changes of a deployment, oldest first, each with its reason, actor and time. Read this to learn why a deployment failed, ended or is waiting.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]{1,64}$",
          "description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
        },
        "limit": {
          "type": "integer",
          "maximum": 200,
          "minimum": 1,
          "description": "How many events."
        }
      },
      "additionalProperties": false
    }
    arguments 20 lines
  • extend_deployment unknown never probed

    Add hours to the term of a deployment that is requested, queued, provisioning or running. Same machine, same SSH details; billing stays per minute. Tell the user the extra cost (hours × gpu_count × rate) and get a yes first. Retry-safe: see idempotency_key.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id",
        "hours",
        "confirm"
      ],
      "properties": {
        "id": {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]{1,64}$",
          "description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
        },
        "hours": {
          "type": "integer",
          "maximum": 720,
          "minimum": 1,
          "description": "Hours to add. The new end may not be more than 720 hours away."
        },
        "confirm": {
          "type": "boolean",
          "description": "Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely."
        },
        "idempotency_key": {
          "type": "string",
          "maxLength": 128,
          "minLength": 8,
          "description": "Optional. 8 to 128 characters. Reuse the same value when retrying the same request. Left out, one is derived from the request and the UTC date, so the identical request the same day returns the first answer; pass a new value to really do it a second time."
        }
      },
      "additionalProperties": false
    }
    arguments 32 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 43c65f41fdc5d06f.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/43c65f41fdc5d06f/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/43c65f41fdc5d06f/badge.svg)](https://brick.blue/agent/43c65f41fdc5d06f?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
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.