# MCP Quickstart

> Zero to a first Copyleaks result inside your AI agent, in six steps.

Ten minutes, six steps. By the end you'll have Copyleaks connected to your agent, a scan run, and a result you can ask questions about.

<Note>
  **Technical reference:** [the MCP Server pages](/mcp/overview) are the canonical documentation for endpoints, per-client setup, OAuth scopes, the twelve tools and their parameters, limits and troubleshooting. This page gives the general picture; go there for anything technical.
</Note>

## Before you start

Two things, and they take a moment to check.

<Steps>
  <Step title="A Copyleaks account you can already scan with">
    Sign in to Copyleaks and check you can run a scan there on a paid balance. A subscription, a prepaid balance, or an account your organization pays for all work.

    <Warning>
      Free plans can't connect, and neither can an account whose plan has ended. A Copyleaks **API key doesn't count** - the API is a separate product, and having a key doesn't connect an agent.
    </Warning>
  </Step>

  <Step title="An AI agent that supports MCP">
    Copyleaks works with **any agent that speaks MCP** - it's an open standard, not a per-agent integration. These are the ones we've tested and written setup steps for:

    | Agent | Where |
    |---|---|
    | **Claude** | claude.ai · Claude Desktop · Claude Code |
    | **Codex** | Codex CLI |
    | **Gemini** | Antigravity CLI |

    Using something else? The same connector address works - follow your agent's own instructions for adding a remote MCP server.
  </Step>
</Steps>

### If you're using Claude, use Claude Code - not claude.ai

<Warning>
  **The Claude chat apps - claude.ai and Claude Desktop - are the most limited way to use Copyleaks, and we don't recommend them.** They can't send a file to an upload address, and that one gap removes two things you probably want.

  **Claude Code's desktop app is not Claude Desktop.** Two different products sharing a word - Claude Code is fully capable in all four of its forms, desktop app included.
</Warning>

| | The Claude chat apps (claude.ai · Claude Desktop) | Claude Code (terminal · **desktop app** · web · IDE) |
|---|---|---|
| Pasted text · web pages | ✅ | ✅ |
| Reading results, scan history, scan profiles | ✅ | ✅ |
| **Files** | ⚠️ **Small files only** - larger ones must be uploaded in the Copyleaks app | ✅ Any size the app accepts |
| **Image scanning** | ⛔ **Not available at all** | ✅ |
| How much a single reply can hold | ✅ Roomiest of any agent | ⚠️ Cuts off sooner on very large results |

**Claude Code isn't only a terminal tool** - it also runs as a desktop app, on the web, and as an IDE extension. **All four forms have the full capability**, including the desktop app.

**Only use claude.ai or Claude Desktop if** pasted text and questions about past scans are genuinely all you need - that much works well. **For anything involving a file or an image, use Claude Code.**

## The six steps

<Steps>

<Step title="Add Copyleaks to your agent" icon="plug">
  You don't need to wait for Copyleaks to appear in any connector store. Add it yourself, today.

  The server is called `copyleaks_app`, and its address is `https://extensions.copyleaks.com/mcp`.

  **Claude Code** - one line:

  ```bash title="Add the server" icon="terminal"
  claude mcp add --transport http copyleaks_app https://extensions.copyleaks.com/mcp --scope user
  ```

  `--scope user` makes it available in every project on your machine. Then run `/mcp` inside a session to sign in.

  **Claude Desktop or claude.ai** - go to **Settings → Customize → Connectors**, press **+ → Add custom connector**, paste the endpoint, then **Add → Connect**.

  **Every other client** - Gemini CLI, Codex CLI, Antigravity, Cursor, VS Code, or anything else - needs its own config file and its own field name for the address, and getting that field wrong is the usual reason a setup silently fails. **Copy the exact block for your client from [Client setup](/mcp/client-setup).**
</Step>

<Step title="Approve what it can do" icon="shield-check">
  Your browser opens, you sign in to Copyleaks, and you see exactly what you're granting:

  | | |
  |---|---|
  | **See your scans and results** | Look up past scans and read reports |
  | **Run scans** | Start new scans - these use your credits |
  | **See your scan profiles** | Read your saved scan settings |
  | **Create and edit your scan profiles** | Add new profiles or change existing ones |
  | **See your plan and credit balance** | Check what's left |

  Approve, and you land back where you started - your connector settings, or your terminal.

  <Note>
    **Your agent can only do what you could do in Copyleaks.** It can never buy credits, change your plan, delete anything, create a share link, download a report, hand you back a document you scanned, or open a scan someone else shared with you.
  </Note>
</Step>

<Step title="Start a new session" icon="arrows-rotate">
  **Do this before anything else - it's the step people skip.**

  Agents read their connector list when a session begins. If you added Copyleaks in the middle of a conversation, it isn't there yet, and asking about it will look like the setup failed.

  | Your agent | What to do |
  |---|---|
  | **Claude Desktop** | **Quit the app completely and reopen it** - closing the window isn't enough. Then start a new chat |
  | **claude.ai** | Reload the page, then start a new chat |
  | **Claude Code** | Exit and relaunch. In an open session, `/mcp` picks it up without restarting |
  | **Codex** · **Antigravity** | Exit and relaunch the CLI |

  **Using it in Claude Desktop** - you add the connector on **claude.ai**; there's no separate setup in the desktop app, because connectors follow your Claude account. After quitting and reopening: start a new chat, open the tools menu in the message box, check Copyleaks is listed and enabled, then just ask - *"Check my Copyleaks credit balance."*

  If Copyleaks isn't in that list, you're either signed in to a different Claude account than the one you added it on, or the app didn't fully quit.
</Step>

<Step title="Check it worked" icon="circle-check">
  Ask your agent:

  > *"Check my Copyleaks credit balance."*

  If it comes back with a number, you're connected. That's the whole test.
</Step>

<Step title="Run your first scan" icon="magnifying-glass">
  Paste a few paragraphs and ask:

  > *"Check this for plagiarism and AI."*

  Your agent submits the scan, then checks back until it's finished. **Scans aren't instant** - while it runs you can ask how far along it is and get a percentage. You won't get an estimate of when it'll finish; Copyleaks doesn't predict that.

  What comes back: your **`Plagiarism score`** and your **`AI score`**, as percentages to one decimal place, plus **which checks actually ran**.

  <Warning>
    **A missing `AI score` is not a clean bill of health.** `AI Detection` needs at least **350 words**. Below that it doesn't run at all, so there's no score to report. Your agent tells you which checks ran, so a blank reads as *not measured* rather than *nothing found*.
  </Warning>

  **Other ways to start a scan:**

  | Ask for | What happens |
  |---|---|
  | *"Scan this file"* | Including PDFs, scanned pages and photos - Copyleaks pulls the text out and scans that |
  | *"Scan these files"* | **Up to ten at a time.** Each is its own scan, run together rather than one after another |
  | *"Scan this page"* | A web address, as long as it opens without signing in |
  | *"Was this image AI-generated?"* | An image scan - about the picture itself, not the words in it. **Not available on the Claude chat apps** (claude.ai, Claude Desktop) |
  | *"Run that scan again"* | Re-checks an existing scan against current sources. Costs credits, like any scan |
  | *"…using my Client Reports profile"* | Runs it with the settings from a saved scan profile |

  **A scan is text or image, never both.** Asking whether a photo is AI-generated and asking whether the words in it are plagiarised are two different scans.
</Step>

<Step title="Go deeper on the result" icon="layer-group">
  This is the part that isn't in the report. Keep asking:

  > *"Which sources did I match?"*
  >
  > *"Show me the exact text that overlapped with the third one."*
  >
  > *"Walk me through everything flagged, in the order I wrote it."*
  >
  > *"Which of those are just my citations?"*
  >
  > *"Are those thirty actually thirty different sources, or the same article republished?"*

  **Nothing is withheld.** Your agent starts narrow and widens on request - score, then sources, then the exact overlapping text on both sides. You pull the depth the question needs.

  Your agent uses the same words your report does: **`Exact match`** · **`Minor changes`** · **`Paraphrased`** for match types; **Web** · **Shared data hub** · **This Batch** · **Private cloud hub** for where a match came from; **AI content** and the **AI phrases** inside it; **`Excluded text`** for what your `Exclusions` left out.

  **To see the document itself, open the report.** Every finished scan comes with a link - `Open this scan in Copyleaks`. Nothing is hidden behind it; it's just where your marked-up document lives.
</Step>

</Steps>

## Nine things worth knowing on day one

<AccordionGroup>

<Accordion title="1. It uses your normal credits" icon="coins">
  Same balance, same meter, whichever way you scanned. There's nothing extra to buy and no separate agent balance. Your agent **can't** tell you what a scan will cost, before or after - your usage meter is the record.
</Accordion>

<Accordion title="2. Results are what was flagged, not your document" icon="file-lines">
  Matched passages, AI content, AI phrases, excluded text. The document itself stays in Copyleaks. That's permanent, not a gap.
</Accordion>

<Accordion title="3. Links that need a sign-in don't work" icon="link-slash">
  Copyleaks opens a link without signing in - so Google Docs, Drive, SharePoint, OneDrive, Notion, Dropbox and anything on a company network return a login page, not your document.

  <Warning>
    If one is submitted anyway, Copyleaks scans the login page and that spends credits. Ask your agent to send the document as a file instead.
  </Warning>
</Accordion>

<Accordion title="4. Large files need an agent with a shell" icon="upload">
  | Your agent | Larger files |
  |---|---|
  | **Claude Code** - terminal, desktop app, web, IDE extension | ✅ |
  | **Codex** · **Antigravity** | ✅ |
  | **The Claude chat apps** - claude.ai and Claude Desktop | ⛔ Small files only. Upload larger ones in the Copyleaks app |

  Small files go straight through everywhere. This is permanent on the two chat surfaces, not a temporary limitation.
</Accordion>

<Accordion title="5. Image scanning needs an agent with a shell" icon="image">
  The same line as fact 4. An image always travels through the upload step, so **the Claude chat apps - claude.ai and Claude Desktop - can't do image scans at all.** Claude Code can, its desktop app included. Upload the image in Copyleaks instead; your agent can read the finished scan back.

  <Warning>
    **Your agent will never shrink or convert an image to make it fit** - altering it changes the answer, so it refuses rather than scanning a different picture.
  </Warning>

  Images must be **512 × 512** or larger, **27 megapixels** or smaller, and PNG · JPEG · BMP · WebP · HEIC · HEIF.
</Accordion>

<Accordion title="6. Long text goes as a file" icon="align-left">
  Pasted text is capped at **25,000 characters**. A file has no character ceiling - so if the paste is refused, send the same content as a file.
</Accordion>

<Accordion title="7. 10 scans a minute, the same on every paid plan" icon="gauge">
  Each file and each web address counts as one, so ten files is ten scans against the minute. **Going over doesn't fail anything** - your agent starts what fits, queues the rest, and carries on by itself. There's no faster tier to buy.
</Accordion>

<Accordion title="8. Your own scans only" icon="user">
  Anything a colleague shared *with* you stays in Copyleaks. And if your team wants this, each person connects their own account - there's no shared connection and no team-level scan profiles.
</Accordion>

<Accordion title="9. Nothing it does deletes anything" icon="trash-can">
  Not scans, not results, not scan profiles. Deleting is done in Copyleaks, deliberately.
</Accordion>

</AccordionGroup>

## If something doesn't work

| Symptom | What to do |
|---|---|
| Connector added, but no Copyleaks tools appear | **Start a new session first** (step 3) - agents only read their connector list at startup. On Claude Desktop, quit the app fully and reopen. If they still don't appear, you haven't signed in: `claude mcp login copyleaks_app`, or `/mcp` in a session |
| Added it on claude.ai, but Claude Desktop doesn't have it | Quit Desktop completely and reopen - closing the window isn't enough. Check you're signed in to the same Claude account |
| Tools appear, but every call is refused | Check your Copyleaks plan is active and paid, and that you have credits |
| *Connection error* after signing in, in a terminal | The local redirect failed. Copy the full callback URL from your browser's address bar and paste it back at the prompt |
| The browser never opened | Open the printed URL yourself, or add `--no-browser` and paste the redirect back |
| Works in one project, not another | Scope. Re-add with `--scope user` |
| *"Your connection expired"* | Reconnect Copyleaks in your agent's settings |

Full list: [Troubleshooting](/mcp/troubleshooting).

<Note>
  **One known build gap is left, and it isn't a failure:** a score in a list of scans is shown as a whole number, while the scan itself carries one decimal. Where the two differ, the scan is the accurate one.
</Note>

## Where to go next

<CardGroup cols={2}>
  <Card title="Tools" icon="wrench" href="/mcp/tools">
    Everything you can ask for - the twelve tools and their parameters.
  </Card>
  <Card title="Limits and access" icon="gauge" href="/mcp/limits">
    Credits, throughput, who can connect, and how to disconnect.
  </Card>
  <Card title="Client setup" icon="plug" href="/mcp/client-setup">
    Per-client config blocks and the field name each one expects.
  </Card>
  <Card title="How results work" icon="layer-group" href="/mcp/results">
    Scores, matched sources, AI content and AI phrases.
  </Card>
</CardGroup>

## Disconnecting

Remove the Copyleaks connection **in your agent**, wherever that agent manages its connections - that's where connections live. Access ends immediately, and your scans and reports stay exactly where they are.