protogrid

Search / io.github.dalenz50010/lipe-court-record

Lipe Court Record

R0· no sign-in

Search page-cited evidence from the public court record in Lipe v. Lupus Superior.

v0.3.0 · active · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality96strong
Trust77of 100
Uptime, 30 days100%
Latency p50222 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "lipe-court-record": {
      "type": "http",
      "url": "https://lipe-api-production.up.railway.app/mcp"
    }
  }
}
claude mcp add --transport http lipe-court-record https://lipe-api-production.up.railway.app/mcp
[mcp_servers.lipe-court-record]
url = "https://lipe-api-production.up.railway.app/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lipe-court-record": {
      "type": "remote",
      "url": "https://lipe-api-production.up.railway.app/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "lipe-court-record": {
      "type": "http",
      "url": "https://lipe-api-production.up.railway.app/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=lipe-court-record&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbGlwZS1hcGktcHJvZHVjdGlvbi51cC5yYWlsd2F5LmFwcC9tY3AifQ%3D%3D"
}
{
  "servers": {
    "lipe-court-record": {
      "type": "http",
      "url": "https://lipe-api-production.up.railway.app/mcp"
    }
  }
}
{
  "mcpServers": {
    "lipe-court-record": {
      "httpUrl": "https://lipe-api-production.up.railway.app/mcp"
    }
  }
}
extensions:
  "lipe-court-record":
    enabled: true
    name: "lipe-court-record"
    type: streamable_http
    uri: "https://lipe-api-production.up.railway.app/mcp"
    timeout: 300

Quality 96 / 100strong

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene100 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations7 of 7 tools declare readOnlyHint or destructiveHint
  • pass
    tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
  • pass
    tools.token_costabout 1,107 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changes1 tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

7 tools, about 1,107 tokens to load them all · tool set 3d1823edccf0 · tools last changed 2026-10-05 · checked 2026-10-20 18:06 UTC

Tool changes

  • grepadded

    Find every page whose extracted text contains an exact phrase, whole word or regular expression - for a quotation, a dollar figure, a cause or exhibit number, a name or a defined term, where search ranks by meaning and may miss the exact words. Returns the total count, counts per filing, and each match's page id, citation and snippet. Case-insensitive unless case_sensitive; curly quotes, dashes, ligatures and line breaks are normalized. `document` filters by filename substring. Matches are automatically extracted text, not verified: fetch the page before quoting it. Zero matches means zero in the extracted text, not that the record lacks the words.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 77 / 100

no-repository
provenance45
liveness100
freshness85
hygiene80

+website +reachable +uptime-100% ~updated-48d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://lipe-api-production.up.railway.app/mcp streamable-httpnoneyes100%222 ms2026-07-282026-10-20

Tools (7)

fetchread-onlyFetch one search result's exact physical PDF page, reviewed evidence, provenance, and permanent citation URL. Use the returned classification and filename/page citation in the answer.
get_case_overviewread-onlyReturn a concise, reviewed orientation to one case with evidence classifications and page citations. Use for first-time users, then search and fetch before answering detailed questions. `case` is a case id from list_cases.
grepread-onlyFind every page whose extracted text contains an exact phrase, whole word or regular expression - for a quotation, a dollar figure, a cause or exhibit number, a name or a defined term, where search ranks by meaning and may miss the exact words. Returns the total count, counts per filing, and each match's page id, citation and snippet. Case-insensitive unless case_sensitive; curly quotes, dashes, ligatures and line breaks are normalized. `document` filters by filename substring. Matches are automatically extracted text, not verified: fetch the page before quoting it. Zero matches means zero in the extracted text, not that the record lacks the words.
list_casesread-onlyList the court cases this connector holds: id, caption, cause number, court, status and the incident each concerns. Pass an id as `case` to search, get_case_overview, list_case_topics and list_record_limitations. Every page id returned by search names its case.
list_case_topicsread-onlyList the evidence topics covered for one case and suggested questions. Use when the user asks what the connector knows or what they should investigate. `case` is a case id from list_cases.
list_record_limitationsread-onlyList what one case's reviewed record does NOT establish: unavailable filings, facts the evidence does not verify, review scope, and the legal status a document can and cannot prove. Call before asserting the record establishes something, and before answering a question the search results do not squarely answer. `case` is a case id from list_cases.
searchread-onlySearch the court record for case facts, testimony, positions, rulings, and jury findings. Call this for every case-specific factual question, then call fetch on relevant result IDs before answering. Each result says whether the page is in the reviewed evidence ledger and which classification it carries, so prefer reviewed pages over automatically extracted ones when both answer the question. `case` confines the search to one case id from list_cases; it is required once more than one case is held.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.dalenz50010/lipe-court-record",
  "title": "Lipe Court Record",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://lipe-api-production.up.railway.app/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.3.0",
  "websiteUrl": "https://lipe-api-production.up.railway.app/connect",
  "description": "Search page-cited evidence from the public court record in Lipe v. Lupus Superior."
}