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

KnowJudges

https://mcp.knowjudges.com

Registry code: b55217b7ef6572b1

api record

Source-linked research on U.S. judges, courts, cases, and judicial analytics.

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

endpoint
https://mcp.knowjudges.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
0 · newcomer
_ is it live, free and safe measured by this hub
Is KnowJudges live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is KnowJudges free to use?
Yes — the hub reached it with no key and no payment.
What tools does KnowJudges have?
10 tools: find_judges, get_recent_rule_changes, find_ai_abuse_cases, compare_immigration_analytics, get_immigration_analytics, find_court, get_judge_profile, get_court, ….
Is KnowJudges 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
99.6%

90 days 99.7%· all time 99.7%

latency
1,267ms

last good check

priced tools
0

of 10 tools

_ answered our checks, 90 days 358 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
  • unknown → live
_ what it is for
topic
government & legal legal
used for
  • find us judges by name or court
  • get a judge's profile and biography
  • get courtroom presentation rules
  • find cases with ai-generated legal errors
takes → gives
text → data
tools
6 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

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 10 tools
10 never probed 0 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.

  • find_judges reads unknown 1h ago

    Find likely US judges by identifying search text, optionally narrowed by court, state, or county. Use this before requesting a profile when the canonical KnowJudges profile URL is unknown. Specifically named matches may have historical or uncertain service; retain their reported status. Returns at most 10 matches linked to canonical KnowJudges profiles; empty and bulk searches are unavailable.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "court": {
      "type": "string",
      "description": "Court name fragment"
    },
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1,
      "description": "Maximum results, capped at 10"
    },
    "query": {
      "type": "string",
      "minLength": 2,
      "description": "Judge name or other identifying search text"
    },
    "state": {
      "type": "string",
      "description": "US state name or postal abbreviation, for example DC or California"
    },
    "county": {
      "type": "string",
      "description": "County name fragment"
    }
  }
}
    arguments 33 lines
  • get_recent_rule_changes reads unknown 1h ago

    Find recorded KnowJudges profile or courtroom-rule changes since an inclusive date, optionally narrowed to the canonical judge_url from find_judges or court_url from find_court. Court filtering includes changes associated with that court and its indexed judge profiles; ambiguous court-only records are omitted. Use to check documented updates; returns at most 25 records. Change tracking begins at the reported launch date, so an empty result does not prove that no earlier real-world rule changed.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "since"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 25,
      "minimum": 1
    },
    "since": {
      "type": "string",
      "format": "date",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
      "description": "Inclusive date in YYYY-MM-DD format"
    },
    "court_url": {
      "type": "string",
      "format": "uri",
      "description": "Optional canonical court_url returned by find_court"
    },
    "judge_url": {
      "type": "string",
      "format": "uri",
      "description": "Optional canonical profile_url returned by find_judges"
    }
  }
}
    arguments 31 lines
  • find_ai_abuse_cases reads unknown 11h ago

    Find reported AI-related legal-error cases, including fabricated citations and authorities. Use query for a case name, error type, or outcome; response distinguishes sanctions from no sanctions. Optional court, judge, state, and date filters narrow results. Returns at most 10 cases with verified decision links or labeled source fallbacks. Describe recorded allegations and outcomes; dataset inclusion alone does not establish a judicial finding of AI use. Empty and bulk searches are unavailable.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "court": {
      "type": "string",
      "minLength": 1,
      "description": "Court name fragment"
    },
    "judge": {
      "type": "string",
      "minLength": 1,
      "description": "Judge name fragment"
    },
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1,
      "description": "Maximum results, capped at 10"
    },
    "query": {
      "type": "string",
      "minLength": 2,
      "description": "Case name, error type, ruling text, court, state, or judge search text"
    },
    "state": {
      "type": "string",
      "minLength": 1,
      "description": "US state name"
    },
    "to_date": {
      "type": "string",
      "format": "date",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
      "description": "Inclusive latest decision date"
    },
    "response": {
      "type": "string",
      "minLength": 1,
      "description": "Court response, for example Warning or Sanctions"
    },
    "from_date": {
      "type": "string",
      "format": "date",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
      "description": "Inclusive earliest decision date"
    }
  }
}
    arguments 50 lines
  • compare_immigration_analytics unknown 11h ago

    Compare highest/lowest recorded immigration rates by judge or court, jointly filtered by state, nationality and calendar/fiscal proceeding-completion year. Defaults to asylum_denial_rate and minimum_decisions 1; a larger minimum is optional. Include small samples with decision counts and labels. Asylum percentages use grants plus denials, with procedural outcomes separate. At most ten results. Use proceeding_removal_rate only for explicitly requested broader proceeding outcomes. Historical rates do not predict individual outcomes or imply a choice of judge.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "entity"
  ],
  "properties": {
    "year": {
      "type": "integer",
      "maximum": 2100,
      "minimum": 1950
    },
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 10,
      "minimum": 1
    },
    "order": {
      "enum": [
        "ascending",
        "descending"
      ],
      "type": "string",
      "default": "ascending"
    },
    "state": {
      "type": "string",
      "pattern": "^[A-Za-z]{2}$"
    },
    "entity": {
      "enum": [
        "judge",
        "court"
      ],
      "type": "string"
    },
    "metric": {
      "enum": [
        "asylum_denial_rate",
        "proceeding_removal_rate"
      ],
      "type": "string",
      "default": "asylum_denial_rate"
    },
    "year_basis": {
      "enum": [
        "calendar",
        "fiscal"
      ],
      "type": "string",
      "default": "calendar"
    },
    "nationality": {
      "type": "string",
      "maxLength": 100,
      "minLength": 2
    },
    "minimum_decisions": {
      "type": "integer",
      "default": 1,
      "maximum": 100000,
      "minimum": 1,
      "description": "Minimum grant-or-denial decisions; defaults to 1. Samples below 35 are labeled, not hidden."
    }
  }
}
    arguments 67 lines
  • get_immigration_analytics unknown 11h ago

    Get immigration judge or court outcomes using its canonical public profile URL. Filter jointly by nationality, calendar/fiscal proceeding-completion year and recorded court state. Asylum grant/denial percentages use grant-coded plus denied outcomes; procedural outcomes are separate. Samples below 35 decisions are labeled; no decisions means no rate. Returns sources and coverage. Use proceeding_removal_rate only for explicitly requested broader proceeding outcomes.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "entity",
    "profile_url"
  ],
  "properties": {
    "year": {
      "type": "integer",
      "maximum": 2100,
      "minimum": 1950
    },
    "state": {
      "type": "string",
      "pattern": "^[A-Za-z]{2}$"
    },
    "entity": {
      "enum": [
        "judge",
        "court"
      ],
      "type": "string"
    },
    "metric": {
      "enum": [
        "asylum_denial_rate",
        "proceeding_removal_rate"
      ],
      "type": "string",
      "default": "asylum_denial_rate"
    },
    "year_basis": {
      "enum": [
        "calendar",
        "fiscal"
      ],
      "type": "string",
      "default": "calendar"
    },
    "nationality": {
      "type": "string",
      "maxLength": 100,
      "minLength": 2
    },
    "profile_url": {
      "type": "string",
      "format": "uri"
    }
  }
}
    arguments 51 lines
  • find_court unknown 8h ago

    Find a court by name or location when the user asks for court identity, metadata, or a judge roster and its KnowJudges identity is unknown. For a named judge's courtroom presentation or practice rules, use get_courtroom_presentation_rules. Optionally narrow by jurisdiction or state. Returns at most 10 courts with names, state/jurisdiction, and canonical public URLs. No pagination or bulk listing is available. Use the returned court_url with get_court.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "minLength": 2,
      "description": "Court name or location search text"
    },
    "state": {
      "type": "string",
      "minLength": 1,
      "description": "State name or postal abbreviation"
    },
    "jurisdiction": {
      "type": "string",
      "pattern": "^[A-Za-z]{2}$",
      "description": "Two-letter jurisdiction code, for example GA, DC, or US for national federal courts"
    }
  }
}
    arguments 30 lines
  • get_judge_profile reads unknown 4h ago

    Get one judge's public profile using the canonical profile URL from find_judges. Use for identity and assignments; use get_judge_biography for biography and get_courtroom_presentation_rules for practice. Preserve stated uncertainty: an assignment end date does not by itself end judicial service or establish a senior-status transition. Source check dates describe evidence checks; last_updated describes publication. Missing fields are unavailable information. Broader rules are not personal preferences.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "judge_url"
  ],
  "properties": {
    "judge_url": {
      "type": "string",
      "format": "uri",
      "description": "Canonical profile_url returned by find_judges"
    }
  }
}
    arguments 14 lines
  • get_court unknown 8h ago

    Get one court's identity, jurisdiction, profile URL, core metadata, and up to 10 judges classified as current when the user asks for court information or a roster. For a named judge's courtroom presentation or practice rules, use get_courtroom_presentation_rules. Use the court_url from find_court. Counts cover indexed profiles classified as active, senior, recalled, or visiting, not an independently verified complete bench. Retain roster coverage and location-specific contact notes. No pagination is available. An empty roster means no indexed current matches; a null count means unavailable roster data.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "court_url"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 10,
      "minimum": 1
    },
    "court_url": {
      "type": "string",
      "format": "uri",
      "description": "Exact canonical court_url returned by find_court"
    }
  }
}
    arguments 20 lines
  • get_courtroom_presentation_rules reads unknown 1h ago

    Answer a named judge's courtroom presentation or practice rules question using documented findings and source links. Resolve judge_url with find_judges. Use up to 10 topics to focus on materials, procedures, or a named part. Put relevant judge-specific requirements first and retain source deadlines. Summary Jury Trial and Commercial Division guidance is conditional. Broader rules are not personal preferences. Missing findings establish neither permission nor prohibition. Answer without looking up court metadata or a judge roster unless the user asks.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "judge_url"
  ],
  "properties": {
    "topics": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 10,
      "description": "Optional presentation topics to filter"
    },
    "judge_url": {
      "type": "string",
      "format": "uri",
      "description": "Canonical profile_url returned by find_judges"
    }
  }
}
    arguments 22 lines
  • get_judge_biography reads unknown 8h ago

    Get one judge's source-attributed birth details, education, and professional and judicial careers using the canonical profile URL from find_judges. Use for biographical questions rather than courtroom practice. Preserves date granularity, provenance, and source check dates; age is returned only for a valid full date of birth, otherwise null. Missing biography fields mean unavailable information, not a failed lookup.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "judge_url"
  ],
  "properties": {
    "judge_url": {
      "type": "string",
      "format": "uri",
      "description": "Canonical profile_url returned by find_judges"
    }
  }
}
    arguments 14 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 b55217b7ef6572b1.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/b55217b7ef6572b1/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/b55217b7ef6572b1/badge.svg)](https://brick.blue/agent/b55217b7ef6572b1?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.