_ registry / mcp http-sse · checked 5h ago

agent-preflight

https://api.agent-preflight.com

Registry code: b9810f59d9ffac58

api record

Budgeted agent preflight: allow|block|reuse|defer|advise. Never executes destination tools. Free MCP

from a public catalogue that lists it, not from the operator

endpoint
https://api.agent-preflight.com/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
10 · newcomer
_ is it live, free and safe measured by this hub
Is agent-preflight live?
Yes — it answered the hub's last check (checked 5h ago). It answered 99% of checks over the last 30 days.
Is agent-preflight free to use?
Yes — the hub reached it with no key and no payment.
What tools does agent-preflight have?
2 tools: check_request, preflight_tool_call.
Is agent-preflight 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
99.4%

90 days 99.3%· all time 99.3%

latency
198ms

last good check

priced tools
0

of 2 tools

_ answered our checks, 90 days 401 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
ai & agents
used for
  • validate a request body against a schema
  • decide whether to run a tool call
takes → gives
data → data
tools
2 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts, and USDC settlements on base into the address this listing's priced doors name, read off the chain. Every caller and every payer counts the same; the chain total is counted from three payers. How it is counted.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

payers on base
6

distinct

settlements
7

last 2026-10-29

received on chain
0.014 USDC

no flags

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 2 tools
2 never probed 0 of 2 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.

  • check_request reads unknown 23h ago

    Validate an HTTP API request body against a supplied JSON Schema before sending it. This tool does not execute the request. Use it when an agent needs to determine whether a proposed JSON body satisfies its expected schema. Optional economics adds proceed/abort advice from expected waste versus a $0.002 check.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "request",
    "schema"
  ],
  "properties": {
    "schema": {
      "type": "object",
      "description": "JSON Schema applied to request.body",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "request": {
      "type": "object",
      "required": [
        "method",
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "description": "Absolute http(s) URL. This tool never fetches the URL."
        },
        "body": {
          "description": "JSON body checked against schema"
        },
        "query": {
          "type": "object",
          "description": "Query parameters",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        },
        "method": {
          "type": "string",
          "description": "HTTP method of the proposed request"
        },
        "headers": {
          "type": "object",
          "description": "HTTP headers as string key/value pairs",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {
            "type": "string"
          }
        }
      }
    },
    "economics": {
      "type": "object",
      "required": [
        "downstreamCostUsd",
        "billsOnInvalidRequest",
        "retryCostUsd"
      ],
      "properties": {
        "retryCostUsd": {
          "type": "number",
          "minimum": 0,
          "description": "USD model/tool-turn cost of one failed attempt"
        },
        "downstreamCostUsd": {
          "type": "number",
          "minimum": 0,
          "description": "USD cost of the target API attempt or success"
        },
        "preflightPriceUsd": {
          "type": "number",
          "minimum": 0,
          "description": "Price of this check. Default 0.002"
        },
        "budgetRemainingUsd": {
          "type": "number",
          "minimum": 0,
          "description": "Remaining agent budget. Checks above this are not +EV"
        },
        "billsOnInvalidRequest": {
          "type": "boolean",
          "description": "True when the target API charges or consumes quota on 4xx"
        },
        "priorInvalidProbability": {
          "type": "number",
          "maximum": 1,
          "minimum": 0,
          "description": "Prior probability the payload is doomed. Default 0.25"
        }
      },
      "description": "Optional V0.2 cost context. Omit for V0.1 validation-only output."
    }
  }
}
    arguments 97 lines
  • preflight_tool_call reads unknown 23h ago

    Free MCP decision for generic search:web_search or browse:fetch proposals only. Returns structuredContent and JSON text, never destination results. Caller supplies cost estimates, post-consultation budget and history, executes tools and retrieves resultReference itself. Reuse requires explicit permission, positive TTL and matching nonempty goal hashes; history must belong to the caller. estimated fees/savings are hypothetical, not receipts; confidence is not calibrated. Paid HTTP is a separate $0.002 per settled POST interface. Full contract: https://agent-preflight.com/docs

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "runId",
    "stepId",
    "tool",
    "budget"
  ],
  "properties": {
    "task": {
      "type": "object",
      "required": [
        "goalHash"
      ],
      "properties": {
        "goalHash": {
          "type": "string"
        }
      }
    },
    "tool": {
      "type": "object",
      "required": [
        "provider",
        "operation",
        "request",
        "estimatedExternalCostUsd"
      ],
      "properties": {
        "request": {
          "type": "object",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        },
        "provider": {
          "type": "string"
        },
        "operation": {
          "type": "string"
        },
        "estimatedModelCostUsd": {
          "type": "number",
          "minimum": 0
        },
        "estimatedExternalCostUsd": {
          "type": "number",
          "minimum": 0
        }
      }
    },
    "runId": {
      "type": "string"
    },
    "budget": {
      "type": "object",
      "required": [
        "remainingUsd"
      ],
      "properties": {
        "reservedUsd": {
          "type": "number",
          "minimum": 0
        },
        "remainingUsd": {
          "type": "number",
          "minimum": 0
        },
        "maxToolCallsRemaining": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": 0
        }
      }
    },
    "stepId": {
      "type": "string"
    },
    "history": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "toolCallId",
          "fingerprint",
          "outcome",
          "ageSeconds"
        ],
        "properties": {
          "outcome": {
            "enum": [
              "success",
              "terminal_failure",
              "transient_failure"
            ],
            "type": "string"
          },
          "goalHash": {
            "type": "string"
          },
          "ageSeconds": {
            "type": "number",
            "minimum": 0
          },
          "toolCallId": {
            "type": "string"
          },
          "fingerprint": {
            "type": "string"
          },
          "resultReference": {
            "type": "string"
          }
        }
      }
    },
    "retryCap": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": 1
    },
    "capabilities": {
      "type": "object",
      "properties": {
        "canReduceScope": {
          "type": "boolean"
        },
        "canReusePriorResult": {
          "type": "boolean"
        }
      }
    },
    "preflightPriceUsd": {
      "type": "number",
      "minimum": 0
    },
    "freshnessTtlSeconds": {
      "type": "number",
      "minimum": 0
    }
  }
}
    arguments 144 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 b9810f59d9ffac58.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/b9810f59d9ffac58/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/b9810f59d9ffac58/badge.svg)](https://brick.blue/agent/b9810f59d9ffac58?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
60%

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.