MCP Server

Fügt Claude Desktop, Cursor und jedem MCP-kompatiblen Client akademische Zitationsprüfung hinzu.

@citetrue/mcp-servernpx -y @citetrue/mcp-server

Funktionen

Zwei Tools, die die CiteTrue REST-API kapseln. Gleiche Credits, gleiche Genauigkeit — nur über MCP statt HTTP.

Tool	Zweck	Credits / Aufruf
verify	Split a text blob into references and verify each against real sources.	1 per ref; tricky ones up to 5
get_credits	Aktuelles Credit-Guthaben des Kontos.	0

Quickstart

Zu Dashboard → API-Schlüssel gehen und Neuer API-Schlüssel klicken. Schlüssel kopieren, der mit sk_ beginnt.
MCP-Client-Konfiguration öffnen (siehe Client-Einrichtung) und citetrue-Block einfügen.
MCP-Client neu starten — nicht nur den Chat, die ganze App.
Assistent bitten "Verifiziere diese Zitate: [einfügen]". Er ruft verify auf und fasst zusammen.

Client-Einrichtung

Jeder stdio-MCP-Client funktioniert. Unten die drei häufigsten; andere verwenden die gleiche Konfigurationsstruktur.

Claude Desktop

Oder manuell konfigurieren

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json bearbeiten:

{
  "mcpServers": {
    "citetrue": {
      "command": "npx",
      "args": ["-y", "@citetrue/mcp-server"],
      "env": {
        "CITETRUE_API_KEY": "sk_..."
      }
    }
  }
}

Cursor

Unter Settings → MCP → Add new MCP server dieselbe command/args/env-Struktur wie im Claude-Desktop-JSON unten verwenden.

Windsurf, Zed, weitere

Jeder stdio-MCP-Client funktioniert — gleich wo die Config liegt, dieselben drei Felder (command, args, env).

Konfiguration

Env-Variable	Standard	Hinweise
CITETRUE_API_KEY	— (Pflicht)	Bearer-Token aus dem Dashboard.
CITETRUE_API_URL	`https://api.citetrue.com`	Für selbstgehostete Deployments überschreiben.

Tools

verify

Split a free-form text blob into individual references and verify each against real sources. Every reference goes through the same flow, and each one in the result reports what it cost.

Parameter

Supply exactly one of text or taskHash:

text string — raw text containing one or more references: numbered / bulleted / blank-line-separated lists, BibTeX, or prose with in-text author-year citations. Max 10MB.
taskHash string — resume a task started by an earlier call (the taskHash it returned). Finished results are replayed without charging again; citations that still need checking are completed and billed as usual.
force bool, optional — ignore cached results and check the text again from scratch (billed like a new check). Only applies with text.

Ausgabe

{
  "taskHash": "...",
  "refs": [
    {
      "hash": "a1b2c3...",
      "text": "[1] Vaswani, A., Shazeer, N., Parmar (2017)...",
      "assessment": "authentic",
      "value": {
        "type": "citation",
        "title": "Attention is all you need",
        "authors": ["A Vaswani", "N Shazeer", "N Parmar"],
        "year": 2017,
        "url": "https://..."
      },
      "note": "",
      "notices": [],
      "confidence": 0.97,
      "cost": 1
    }
  ],
  "cost": 2,
  "balance": 248
}

Each ref's cost is what the task has charged for that citation: 1 for most citations, up to 5 for tricky ones that needed more data sources and more analysis, 0 if it was already paid for in another task. Resuming a task with taskHash reports the same per-ref numbers again — they are not new charges. The top-level cost is what this call newly charged (0 when a finished task is simply replayed), and balance is what's left afterwards — it can be negative (see Billing). note is a free-form one-line natural-language explanation in English (intended for end-user display); for programmatic checks, match on notices[] instead.

Assessment values

authentic — paper exists and is the one cited; value contains the matched paper.
unsure — found something but can't confirm; notices and confidence describe why.
inauthentic — definitively not found / fabricated / unrelated.
invalid — input wasn't a citation; pipeline refused to search.
error — verification failed on this ref; errors[] lists tokens.
exceeded — credits ran out before this ref ran.

Abrechnung

Same credits as the REST API. Most citations cost 1 credit. Tricky ones that need more data sources and more analysis can cost up to 5. If you run out of credits mid-check, citations already in progress still finish; the overage is deducted at your next credit reset, so balance can be negative. Citations that couldn't start for lack of credits come back as exceeded. get_credits is free.

Fehlerbehebung

If the server fails to start, ensure npx is on PATH and CITETRUE_API_KEY is set.

Gepflegt vom CiteTrue-Team · Zuletzt aktualisiert: 1. Oktober 2026