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

skoia-parts

https://parts.skoia.me

Registry code: 0781064ee173a993

api record

Use SkoIA Parts to search and resolve physical-part problems. All tools are read-only or deterministic compute. Never claim a purchase, payment, subscription change, manufacturing order or verified physical fit.

endpoint
https://parts.skoia.me/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 skoia-parts live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is skoia-parts free to use?
Yes — the hub reached it with no key and no payment.
What tools does skoia-parts have?
15 tools: understand_physical_problem, verify_solution, get_fit_guidance, get_product, search_candidates, get_next_observation, generate_hypotheses, get_compatibility, ….
Is skoia-parts 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 99.5%· all time 99.5%

latency
740ms

last good check

priced tools
0

of 15 tools

_ answered our checks, 90 days 585 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
iot & hardware
used for
  • search a verified parts index
  • check compatibility between two products
  • compute manufacturing fit compensation
  • resolve a physical part problem
  • verify a proposed part solution
takes → gives
text → data
tools
15 reads
_ 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 15 tools
1 open 14 never probed 1 of 15 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_generation_options reads open 6h ago

    Lists only generator families implemented by the current deterministic core.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "intent": {
      "enum": [
        "CONNECT",
        "REPAIR",
        "CREATE"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • understand_physical_problem reads unknown 6h ago

    Builds the canonical PhysicalProblem, Observation Graph and explicit unknown set from the supplied description.

    mcp-tool

    {
  "type": "object",
  "required": [
    "description"
  ],
  "properties": {
    "description": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • verify_solution reads unknown 6h ago

    Checks a proposed candidate independently against the canonical constraints and reports verification separately from generation.

    mcp-tool

    {
  "type": "object",
  "required": [
    "description",
    "candidate"
  ],
  "properties": {
    "candidate": {
      "type": "object",
      "additionalProperties": true
    },
    "description": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 19 lines
  • get_fit_guidance reads unknown 16h ago

    Calculates deterministic manufacturing compensation and returns an explicit physical-test warning.

    mcp-tool

    {
  "type": "object",
  "required": [
    "nominalMm",
    "fitType"
  ],
  "properties": {
    "gender": {
      "enum": [
        "MALE",
        "FEMALE",
        "NEUTRAL"
      ],
      "type": "string"
    },
    "fitType": {
      "enum": [
        "PRESS",
        "TIGHT",
        "SLIDING",
        "LOOSE"
      ],
      "type": "string"
    },
    "process": {
      "type": "string",
      "maxLength": 30
    },
    "material": {
      "type": "string",
      "maxLength": 20
    },
    "nominalMm": {
      "type": "number",
      "maximum": 1000,
      "exclusiveMinimum": 0
    },
    "measurementBasis": {
      "enum": [
        "NOMINAL",
        "INTERNAL",
        "EXTERNAL"
      ],
      "type": "string"
    },
    "userCalibrationMm": {
      "type": "number",
      "maximum": 5,
      "minimum": -5
    }
  },
  "additionalProperties": false
}
    arguments 53 lines
  • get_product reads unknown 16h ago

    Returns one canonical ProductTwin and its source-level provenance by stable identifier.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9_.:-]{1,119}$"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • search_candidates reads unknown 12h ago

    Searches the verified local index for candidates; a candidate is never presented as an identified product without evidence.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 8,
      "maximum": 20,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • get_next_observation reads unknown 16h ago

    Returns the single highest-value missing observation without promoting hypotheses to facts.

    mcp-tool

    {
  "type": "object",
  "required": [
    "description"
  ],
  "properties": {
    "description": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • generate_hypotheses reads unknown 3h ago

    Explores candidate transformations from the same PhysicalProblem and labels every unverified candidate as HYPOTHESIS.

    mcp-tool

    {
  "type": "object",
  "required": [
    "description"
  ],
  "properties": {
    "description": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • get_compatibility reads unknown 3h ago

    Compares two canonical ProductTwins. It reports direct compatibility only when their verified interface system matches.

    mcp-tool

    {
  "type": "object",
  "required": [
    "productA",
    "productB"
  ],
  "properties": {
    "productA": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9_.:-]{1,119}$"
    },
    "productB": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9_.:-]{1,119}$"
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • get_verified_commerce_options reads unknown 12h ago

    Returns discovery candidates separately from RevenueGuard-approved monetizable offers and enforces distribution rights per surface.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 6,
      "maximum": 10,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1
    },
    "surface": {
      "enum": [
        "WEB",
        "REST_API",
        "MCP",
        "WEBMCP",
        "CHATGPT_APP",
        "APIFY"
      ],
      "type": "string",
      "default": "MCP"
    }
  },
  "additionalProperties": false
}
    arguments 32 lines
  • get_offers reads unknown 3h ago

    Deprecated compatibility adapter. Returns provider discovery only; use get_verified_commerce_options for separated verified output.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 6,
      "maximum": 10,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • generate_artifact reads unknown 10h ago

    Generates only LIVE deterministic formats after plan acceptance and verification; STEP remains unavailable.

    mcp-tool

    {
  "type": "object",
  "required": [
    "solutionId",
    "format"
  ],
  "properties": {
    "format": {
      "enum": [
        "STL",
        "3MF",
        "OPENSCAD"
      ],
      "type": "string"
    },
    "solutionId": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9_.:-]{1,119}$"
    },
    "entitlement": {
      "enum": [
        "FREE",
        "PAID_VERIFIED"
      ],
      "type": "string",
      "default": "FREE"
    }
  },
  "additionalProperties": false
}
    arguments 30 lines
  • synthesize_physical_solution reads unknown 10h ago

    Runs the canonical resolver and returns either a supported solution or the next required observation.

    mcp-tool

    {
  "type": "object",
  "required": [
    "description"
  ],
  "properties": {
    "description": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • resolve_problem reads unknown 12h ago

    Runs the deterministic problem-first resolver and returns the best supported next action or the minimum missing information.

    mcp-tool

    {
  "type": "object",
  "required": [
    "description"
  ],
  "properties": {
    "intent": {
      "enum": [
        "CONNECT",
        "REPAIR",
        "FIND_OR_MAKE",
        "MODIFY",
        "CREATE"
      ],
      "type": "string"
    },
    "productA": {
      "type": "string",
      "maxLength": 200
    },
    "productB": {
      "type": "string",
      "maxLength": 200
    },
    "description": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1
    },
    "relationship": {
      "type": "string",
      "maxLength": 80
    }
  },
  "additionalProperties": false
}
    arguments 36 lines
  • search_parts reads unknown 10h ago

    Searches the verified local product and part-type index without inventing identities.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 8,
      "maximum": 20,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 20 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 0781064ee173a993.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/0781064ee173a993/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/0781064ee173a993/badge.svg)](https://brick.blue/agent/0781064ee173a993?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.