_ registry / mcp + a2a streamable-http · checked 3h ago

aialignwerk

https://aialign.halowerk.com

Registry code: b1cd07280b44db64

api record

Paid tools via x402. tools/list is free. Send the payment proof in the PAYMENT-SIGNATURE header for tools/call; without it, the payment request and inputSchema are returned.

endpoint
https://aialign.halowerk.com/mcp
door code
73f18d0109b04c11
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 aialignwerk live?
Yes — it answered the hub's last check (checked 3h ago). It answered 99% of checks over the last 30 days.
Is aialignwerk free to use?
No — it charges per call, from 0.003 USDC, quoted in its own 402 answers.
What tools does aialignwerk have?
10 tools: aialignwerk_resource_hog, aialignwerk_agent_collusion, aialignwerk_bias_audit, aialignwerk_sycophancy_detect, aialignwerk_jailbreak_defense, aialignwerk_memory_sanitize, aialignwerk_capability_eval, aialignwerk_confidence_calib, ….
Is aialignwerk 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
98.9%

90 days 99.1%· all time 98.8%

latency
867ms

last good check

priced tools
10

of 10 tools

_ answered our checks, 90 days 1067 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
ai & agents evaluation & judging
used for
  • audit model outputs for bias
  • measure hallucination rate
  • calibrate model confidence
  • detect sycophancy
  • redact secrets from agent memory
takes → gives
data, text → data
tools
10 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. The address also stands behind 121 other origins: the chain figures are the gateway's, not this listing's alone. 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
46

distinct

settlements
9,342

last 2026-11-10

received on chain
37.4096 USDC

shared-payto

_ what it can do 10 tools
10 paid 10 of 10 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.

  • aialignwerk_resource_hog reads 0.003 USDC paid 17h ago

    Divides observed CPU, memory-time, network, tool-call and wall-time usage by caller-supplied budgets, reports exceeded dimensions and ranks observations by the maximum ratio. It does not collect telemetry, infer intent, identify inefficient algorithms or terminate an agent. Preis 0.003 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "budgets",
    "observations"
  ],
  "properties": {
    "budgets": {
      "type": "object",
      "required": [
        "cpu_seconds",
        "memory_gb_seconds",
        "network_mb",
        "tool_calls",
        "wall_seconds"
      ],
      "properties": {
        "network_mb": {
          "type": "number",
          "maximum": 1000000000000000,
          "minimum": 0.000001
        },
        "tool_calls": {
          "type": "number",
          "maximum": 1000000000000,
          "minimum": 0.000001
        },
        "cpu_seconds": {
          "type": "number",
          "maximum": 1000000000000000,
          "minimum": 0.000001
        },
        "wall_seconds": {
          "type": "number",
          "maximum": 1000000000000000,
          "minimum": 0.000001
        },
        "memory_gb_seconds": {
          "type": "number",
          "maximum": 1000000000000000000,
          "minimum": 0.000001
        }
      },
      "additionalProperties": false
    },
    "observations": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "agent_id",
          "cpu_seconds",
          "memory_gb_seconds",
          "network_mb",
          "tool_calls",
          "wall_seconds"
        ],
        "properties": {
          "agent_id": {
            "type": "string",
            "maxLength": 128,
            "minLength": 1
          },
          "network_mb": {
            "type": "number",
            "maximum": 1000000000000000,
            "minimum": 0
          },
          "tool_calls": {
            "type": "integer",
            "maximum": 1000000000000,
            "minimum": 0
          },
          "cpu_seconds": {
            "type": "number",
            "maximum": 1000000000000000,
            "minimum": 0
          },
          "wall_seconds": {
            "type": "number",
            "maximum": 1000000000000000,
            "minimum": 0
          },
          "memory_gb_seconds": {
            "type": "number",
            "maximum": 1000000000000000000,
            "minimum": 0
          }
        },
        "additionalProperties": false
      },
      "maxItems": 100000,
      "minItems": 1
    }
  },
  "additionalProperties": false
}
    arguments 97 lines
  • aialignwerk_agent_collusion reads 0.005 USDC paid 12h ago

    Requires the same agents in each supplied round, computes each pair’s observed action agreement, expected agreement from marginal action frequencies and chance-corrected kappa, then flags high positive agreement against a supplied threshold. Coordination can be benign or task-driven; this metric does not prove communication, intent or collusion. Preis 0.005 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "rounds",
    "kappa_threshold"
  ],
  "properties": {
    "rounds": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "round_id",
          "actions"
        ],
        "properties": {
          "actions": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "agent_id",
                "action"
              ],
              "properties": {
                "action": {
                  "type": "string",
                  "maxLength": 128,
                  "minLength": 1
                },
                "agent_id": {
                  "type": "string",
                  "maxLength": 128,
                  "minLength": 1
                }
              },
              "additionalProperties": false
            },
            "maxItems": 50,
            "minItems": 2
          },
          "round_id": {
            "type": "string",
            "maxLength": 128,
            "minLength": 1
          }
        },
        "additionalProperties": false
      },
      "maxItems": 10000,
      "minItems": 2
    },
    "kappa_threshold": {
      "type": "number",
      "maximum": 1,
      "minimum": -1
    }
  },
  "additionalProperties": false
}
    arguments 60 lines
  • aialignwerk_bias_audit reads 0.004 USDC paid 12h ago

    Calculates each group positive-outcome rate, compares it with an explicit or automatically selected reference group, and reports rate differences and selection-rate ratios. Aggregate disparity metrics do not establish discrimination, fairness, causation or legal compliance and can conceal intersectional or sampling effects. Preis 0.004 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "groups"
  ],
  "properties": {
    "groups": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "group_id",
          "total_count",
          "positive_count"
        ],
        "properties": {
          "group_id": {
            "type": "string",
            "maxLength": 128,
            "minLength": 1
          },
          "total_count": {
            "type": "integer",
            "maximum": 1000000000,
            "minimum": 1
          },
          "positive_count": {
            "type": "integer",
            "maximum": 1000000000,
            "minimum": 0
          }
        },
        "additionalProperties": false
      },
      "maxItems": 1000,
      "minItems": 2
    },
    "reference_group_id": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1
    },
    "minimum_selection_rate_ratio": {
      "type": "number",
      "maximum": 1,
      "minimum": 0
    }
  },
  "additionalProperties": false
}
    arguments 50 lines
  • aialignwerk_sycophancy_detect reads 0.004 USDC paid 12h ago

    Compares term-frequency cosine similarity between a leading user position and paired independent/conditioned responses, then reports the positive similarity shift. It is a reproducible surface-form signal, not proof of agreement, truthfulness, motive or sycophancy; paraphrases and legitimate corrections can evade or trigger it. Preis 0.004 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "scenarios",
    "shift_threshold"
  ],
  "properties": {
    "scenarios": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "scenario_id",
          "leading_position",
          "independent_response",
          "conditioned_response"
        ],
        "properties": {
          "scenario_id": {
            "type": "string",
            "maxLength": 128,
            "minLength": 1
          },
          "leading_position": {
            "type": "string",
            "maxLength": 20000,
            "minLength": 1
          },
          "conditioned_response": {
            "type": "string",
            "maxLength": 50000,
            "minLength": 1
          },
          "independent_response": {
            "type": "string",
            "maxLength": 50000,
            "minLength": 1
          }
        },
        "additionalProperties": false
      },
      "maxItems": 5000,
      "minItems": 1
    },
    "shift_threshold": {
      "type": "number",
      "maximum": 1,
      "minimum": 0
    }
  },
  "additionalProperties": false
}
    arguments 52 lines
  • aialignwerk_jailbreak_defense reads 0.004 USDC paid 17h ago

    Applies a small fixed set of defensive regular-expression categories and returns category names, a bounded risk score and a review recommendation. It does not execute, transform or forward the prompt. Pattern matching is incomplete and can produce false positives; it should be one signal in layered controls, not the sole access decision. Preis 0.004 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "prompt",
    "review_threshold",
    "block_threshold"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "maxLength": 100000,
      "minLength": 1
    },
    "block_threshold": {
      "type": "number",
      "maximum": 1,
      "minimum": 0
    },
    "review_threshold": {
      "type": "number",
      "maximum": 1,
      "minimum": 0
    }
  },
  "additionalProperties": false
}
    arguments 26 lines
  • aialignwerk_memory_sanitize reads 0.003 USDC paid 17h ago

    Replaces private-key blocks, credential assignments, email addresses, Luhn-valid payment-card candidates, IPv4 addresses and phone-like digit strings, returning only sanitized text and per-category counts. The request archive stores only input field names and the result archive stores only this method via the endpoint factory. Pattern redaction is incomplete: it cannot identify every secret, name, address or contextual identifier and must not be treated as irreversible anonymization. Preis 0.003 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 200000,
      "minLength": 1
    },
    "replacement_style": {
      "enum": [
        "typed",
        "generic"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • aialignwerk_capability_eval reads 0.003 USDC paid 24h ago

    Computes weighted pass rates and weighted scores from caller-labeled test outcomes, with deterministic category summaries. It does not run tests, validate labels, measure untested capabilities or establish deployment safety; the result is only as representative as the supplied evaluation set. Preis 0.003 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "test_cases"
  ],
  "properties": {
    "test_cases": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "case_id",
          "category",
          "passed",
          "score",
          "weight"
        ],
        "properties": {
          "score": {
            "type": "number",
            "maximum": 1,
            "minimum": 0
          },
          "passed": {
            "type": "boolean"
          },
          "weight": {
            "type": "number",
            "maximum": 1000000,
            "minimum": 0.000001
          },
          "case_id": {
            "type": "string",
            "maxLength": 128,
            "minLength": 1
          },
          "category": {
            "type": "string",
            "maxLength": 128,
            "minLength": 1
          }
        },
        "additionalProperties": false
      },
      "maxItems": 100000,
      "minItems": 1
    }
  },
  "additionalProperties": false
}
    arguments 50 lines
  • aialignwerk_confidence_calib reads 0.003 USDC paid 24h ago

    Compares scalar confidence with binary correctness, calculates mean squared Brier loss, partitions confidence into caller-selected equal-width bins and reports expected and maximum calibration error. It does not validate labels, correct class imbalance or prove calibration beyond the supplied sample. Preis 0.003 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "predictions"
  ],
  "properties": {
    "bin_count": {
      "type": "integer",
      "maximum": 100,
      "minimum": 2
    },
    "predictions": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "prediction_id",
          "confidence",
          "correct"
        ],
        "properties": {
          "correct": {
            "type": "boolean"
          },
          "confidence": {
            "type": "number",
            "maximum": 1,
            "minimum": 0
          },
          "prediction_id": {
            "type": "string",
            "maxLength": 128,
            "minLength": 1
          }
        },
        "additionalProperties": false
      },
      "maxItems": 100000,
      "minItems": 1
    }
  },
  "additionalProperties": false
}
    arguments 43 lines
  • aialignwerk_goal_drift reads 0.003 USDC paid 24h ago

    Aligns caller-labeled dimensions, computes cosine similarity and a normalized L1 difference, and flags drift against a supplied cosine threshold. It does not infer goals from behavior, decide which goal is correct or detect deception; results depend entirely on the supplied vector representation. Preis 0.003 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "dimensions",
    "minimum_cosine_similarity"
  ],
  "properties": {
    "dimensions": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "initial_weight",
          "current_weight"
        ],
        "properties": {
          "name": {
            "type": "string",
            "maxLength": 128,
            "minLength": 1
          },
          "current_weight": {
            "type": "number",
            "maximum": 1000000000000,
            "minimum": -1000000000000
          },
          "initial_weight": {
            "type": "number",
            "maximum": 1000000000000,
            "minimum": -1000000000000
          }
        },
        "additionalProperties": false
      },
      "maxItems": 10000,
      "minItems": 1
    },
    "minimum_cosine_similarity": {
      "type": "number",
      "maximum": 1,
      "minimum": -1
    }
  },
  "additionalProperties": false
}
    arguments 46 lines
  • aialignwerk_hallucination_rate reads 0.004 USDC paid 19h ago

    Tokenizes each claim and its supplied evidence, removes a small declared English stop-word list, and reports the fraction of unique claim tokens present in evidence. Coverage below a supplied threshold is flagged. This is lexical grounding screening only: overlap does not prove truth, low overlap does not prove hallucination, and the service does not retrieve or validate evidence. Preis 0.004 USDC je Aufruf, Abrechnung über x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "claims",
    "minimum_coverage_fraction"
  ],
  "properties": {
    "claims": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "claim_id",
          "claim_text",
          "evidence_texts"
        ],
        "properties": {
          "claim_id": {
            "type": "string",
            "maxLength": 128,
            "minLength": 1
          },
          "claim_text": {
            "type": "string",
            "maxLength": 20000,
            "minLength": 1
          },
          "evidence_texts": {
            "type": "array",
            "items": {
              "type": "string",
              "maxLength": 50000,
              "minLength": 1
            },
            "maxItems": 100,
            "minItems": 1
          }
        },
        "additionalProperties": false
      },
      "maxItems": 5000,
      "minItems": 1
    },
    "minimum_coverage_fraction": {
      "type": "number",
      "maximum": 1,
      "minimum": 0
    }
  },
  "additionalProperties": false
}
    arguments 51 lines
_ try it over mcp 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 b1cd07280b44db64.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/b1cd07280b44db64/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/b1cd07280b44db64/badge.svg)](https://brick.blue/agent/b1cd07280b44db64?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 knowoff the mcp door
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.

_ also on halowerk.com 109 entries

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.

101 more sit on this domain. All of them.