MCP Server
Markdown (per LLM)Aggiunge la verifica di citazioni accademiche a Claude Desktop, Cursor o qualsiasi client MCP.
Cosa ottieni
Due strumenti che incapsulano l'API REST CiteTrue. Stessi crediti, stessa precisione — solo via MCP invece di HTTP.
| Strumento | Scopo | Crediti / chiamata |
|---|---|---|
| verify | Split a text blob into references and verify each against real sources. | 1 per ref; tricky ones up to 5 |
| get_credits | Ritorna il saldo crediti del conto. | 0 |
Avvio rapido
- Andare su Dashboard → Chiavi API e cliccare Nuova chiave API. Copiare la chiave che inizia con
sk_. - Aprire la config del client MCP (vedi Configurazione client) e aggiungere il blocco citetrue.
- Riavviare il client MCP — non solo la chat, l'intera app.
- Chiedere all'assistente "Verifica queste citazioni: [incolla]". Chiamerà verify e riassumerà.
Configurazione client
Qualsiasi client MCP stdio funziona. Sotto i tre più comuni; altri usano la stessa struttura.
Claude Desktop
Installa CiteTrue come estensione di Claude Desktop — senza modificare JSON né configurare Node. Il server incluso gira sul Node fornito con Claude Desktop.
Scarica per Claude DesktopFai doppio clic sul file scaricato (o trascinalo in Impostazioni → Extensions) e incolla la tua chiave API quando richiesto — viene salvata in modo sicuro nel portachiavi del tuo sistema.
Importante: dopo l'installazione, assicurati che l'estensione sia abilitata (attiva) in Impostazioni → Extensions e riavvia Claude Desktop — è questo che attiva i suoi strumenti.
Oppure configura manualmente
Modificare ~/Library/Application Support/Claude/claude_desktop_config.json su macOS, %APPDATA%\Claude\claude_desktop_config.json su Windows:
{
"mcpServers": {
"citetrue": {
"command": "npx",
"args": ["-y", "@citetrue/mcp-server"],
"env": {
"CITETRUE_API_KEY": "sk_..."
}
}
}
}Cursor
In Settings → MCP → Add new MCP server, usare la stessa struttura command / args / env del JSON Claude Desktop sotto.
Windsurf, Zed, altri
Qualsiasi client MCP stdio funziona — qualunque sia il percorso config, stessi tre campi (command, args, env).
Configurazione
| Env var | Default | Note |
|---|---|---|
| CITETRUE_API_KEY | — (Obbligatorio) | Token Bearer dal dashboard. |
| CITETRUE_API_URL | https://api.citetrue.com | Sovrascrivere per deployment self-hosted. |
Strumenti
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.
Parametri
Supply exactly one of text or taskHash:
textstring — raw text containing one or more references: numbered / bulleted / blank-line-separated lists, BibTeX, or prose with in-text author-year citations. Max 10MB.taskHashstring — resume a task started by an earlier call (thetaskHashit returned). Finished results are replayed without charging again; citations that still need checking are completed and billed as usual.forcebool, optional — ignore cached results and check the text again from scratch (billed like a new check). Only applies withtext.
Output
{
"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;valuecontains the matched paper.unsure— found something but can't confirm;noticesandconfidencedescribe 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.
Fatturazione
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.
Risoluzione problemi
If the server fails to start, ensure npx is on PATH and CITETRUE_API_KEY is set.
Mantenuto dal team di CiteTrue · Ultimo aggiornamento: