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

proxlai

https://proxlai.com

Registry code: 24da4f7e0909ee9a

api record

Proxlai is a price book for AI APIs: LLMs, image, video, speech, GPU rental, vector databases and more, grouped into "markets". Prices are in each market's own unit and each carries a verified_at date, a freshness tier and the provider's source_url. Typical flow: list_markets to find the market id; describe_market for its attributes and how its pricing works; search_offerings to rank offerings by price, quality and speed with the user's requirements as filters; get_offering or compare_offerings for detail. When you quote a price, give its unit and verified_at date and cite the source. Say…

endpoint
https://proxlai.com/api/mcp
protocol
http-sse ·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 proxlai live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is proxlai free to use?
Yes — the hub reached it with no key and no payment.
What tools does proxlai have?
5 tools: search_offerings, get_offering, compare_offerings, describe_market, list_markets.
Is proxlai 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
235ms

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
1 open 4 never probed 1 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_markets open 1h ago

    List every market (kind of AI API) that has prices, with its id and pricing unit. Start here to find the market id.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}
    arguments 5 lines
  • search_offerings unknown never probed

    Rank the offerings in one market by price, quality and speed, with optional requirements and a maximum price. Returns prices with their verification date and source.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "market"
  ],
  "properties": {
    "sort": {
      "enum": [
        "score",
        "price",
        "quality"
      ],
      "type": "string",
      "description": "score (default): best match for the weights; price: cheapest first; quality: best first"
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "How many results, default 10"
    },
    "market": {
      "type": "string",
      "description": "Market id from list_markets"
    },
    "filters": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "attr",
          "op",
          "value"
        ],
        "properties": {
          "op": {
            "enum": [
              "eq",
              "lte",
              "gte",
              "in",
              "has"
            ],
            "type": "string",
            "description": "eq: equals; lte/gte: numeric bounds; in: value is one of a list; has: boolean is true or tag list contains value"
          },
          "attr": {
            "type": "string",
            "description": "Attribute key from the category's attribute list"
          },
          "value": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "string"
              },
              {
                "type": "boolean"
              },
              {
                "type": "array",
                "items": {
                  "type": "string"
                }
              }
            ]
          }
        }
      },
      "maxItems": 20,
      "description": "Requirements. Attribute keys come from describe_market. Do not add filters the user did not ask for."
    },
    "weights": {
      "type": "object",
      "required": [
        "cost",
        "quality",
        "speed"
      ],
      "properties": {
        "cost": {
          "type": "number",
          "maximum": 1,
          "minimum": 0,
          "description": "How much a lower price matters (0..1)"
        },
        "speed": {
          "type": "number",
          "maximum": 1,
          "minimum": 0,
          "description": "How much speed / low latency matters (0..1)"
        },
        "quality": {
          "type": "number",
          "maximum": 1,
          "minimum": 0,
          "description": "How much output quality matters (0..1)"
        }
      },
      "description": "What matters, each 0..1. Default: cost 0.5, quality 0.4, speed 0.1"
    },
    "maxPrice": {
      "type": "number",
      "minimum": 0,
      "description": "Upper bound in the market's pricing unit (USD)"
    },
    "include_unverified": {
      "type": "boolean",
      "description": "Also rank offerings whose price is an unverified sample, never checked against the provider (default false: left out)"
    }
  }
}
    arguments 115 lines
  • get_offering unknown never probed

    Full detail for one offering: description, capabilities, current price with its source, and price history.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Offering id from search_offerings, e.g. 'openai/gpt-6-luna'"
    }
  }
}
    arguments 13 lines
  • compare_offerings unknown 1h ago

    Put 2 to 4 offerings from the same market side by side: prices, scores and every capability.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "ids"
  ],
  "properties": {
    "ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 4,
      "minItems": 2,
      "description": "2 to 4 offering ids from the same market"
    }
  }
}
    arguments 18 lines
  • describe_market unknown 1h ago

    Explain one market: what it is, how its pricing works, and the attributes you can filter and compare on (with plain-language help).

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "market"
  ],
  "properties": {
    "market": {
      "type": "string",
      "description": "Market id from list_markets, e.g. 'llm' or 'video-generation'"
    }
  }
}
    arguments 13 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 24da4f7e0909ee9a.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/24da4f7e0909ee9a/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/24da4f7e0909ee9a/badge.svg)](https://brick.blue/agent/24da4f7e0909ee9a?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.