[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup)

# Instapaper API and MCP server

> Instapaper has a full REST API, API v2, and no official MCP server (checked 17 Oct 2026). Instapaper launched API v2 on 29 Sep 2026 with OAuth 2, personal access tokens, an OpenAPI spec and Python and TypeScript SDKs. It covers bookmarks, folders, tags and highlights, and free accounts can use it. Instapaper's docs list no MCP server, so the hosted, maintained MCP is the part Cotlet adds.

Read-it-later service: you save web pages to a reading list, sort them into folders and tags, archive what you finished, and highlight passages.

## What is the Instapaper API?

Cotlet's Instapaper API exposes 12 endpoints for your own Instapaper account: list bookmarks, get article text, list folders, list tags, list highlights, save a URL, move an article, like or unlike an article, add or remove tags, create a folder, highlight a passage and delete an article. The list_bookmarks endpoint returns articles in one list: Home, Archive, Liked, a folder or a tag, with reading progress. Each endpoint takes simple JSON inputs like bookmark_id, folder_id or title and works both as an operation of the instapaper_read or instapaper_write MCP tool for agents and as a REST call for scripts.

- **Category:** [Productivity & teams](https://cotlet.dev/integrations/category/productivity-teams.md)
- **Endpoints:** 12 (5 read, 7 write)
- **Updated:** 2026-10-18

Instapaper has a full REST API, API v2, and no official MCP server (checked 17 Oct 2026). Cotlet is a hosted MCP server and REST API for Instapaper with 12 endpoints (5 read, 7 write): you sign in once in your own cloud browser, your AI agent does the work.

## Does Instapaper have an official API?

Instapaper has a full REST API, API v2, and no official MCP server (checked 17 Oct 2026). Instapaper launched API v2 on 29 Sep 2026 with OAuth 2, personal access tokens, an OpenAPI spec and Python and TypeScript SDKs. It covers bookmarks, folders, tags and highlights, and free accounts can use it. Instapaper's docs list no MCP server, so the hosted, maintained MCP is the part Cotlet adds.

| Task | Instapaper official | Cotlet |
|---|---|---|
| List the Home, Archive, Liked, folder or tag lists | Yes: API v2 bookmarks list; you page and sync it yourself | Yes |
| Save a URL into a folder with tags | Yes: API v2 save bookmark | Yes |
| Archive, unarchive or move to a folder | Yes: API v2 move bookmark | Yes |
| Like and unlike an article | Yes: API v2 like and unlike | Yes |
| Add and remove tags | Yes: API v2; new tag names are created on the way | Yes |
| Read and create highlights | Yes: In the official SDKs; free accounts can create 5 highlights a month, Premium has no cap | Yes |
| Fetch the text of a saved article | Partly: No key for your own account; for other people's accounts you send your own Instaparser key | Yes |
| Delete an article permanently | Yes: API v2 delete bookmark | Yes |

Sources: [Instapaper blog: Instapaper API v2 (29 Sep 2026)](https://blog.instapaper.com/2026/09/29/instapaper-api-v2/), [Instapaper API v2 OpenAPI spec](https://www.instapaper.com/api/2/openapi.json), [Instapaper API v2 TypeScript SDK (official)](https://github.com/Instapaper/instapaper-api-js), [Instapaper Premium: free and Premium features](https://www.instapaper.com/premium)

## For AI agents

```text
Instapaper has a full REST API, API v2, and no official MCP server (checked 17 Oct 2026). Instapaper launched API v2 on 29 Sep 2026 with OAuth 2, personal access tokens, an OpenAPI spec and Python and TypeScript SDKs. It covers bookmarks, folders, tags and highlights, and free accounts can use it. Instapaper's docs list no MCP server, so the hosted, maintained MCP is the part Cotlet adds.
Cotlet provides a hosted MCP server and REST API for Instapaper: 12 tools (5 read, 7 write).
Access       Sign up at https://cotlet.dev/app/signup?app=instapaper, then request the app and create API keys in the Cotlet console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    instapaper_read, instapaper_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/instapaper, each operation at its own route, e.g. POST /api/v1/instapaper/bookmark/save
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations   list_bookmarks, get_article_text, list_folders, list_tags, list_highlights, save_bookmark, move_bookmark, set_liked, tag_bookmark, create_folder, create_highlight, delete_bookmark
Confirm      delete_bookmark (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown     https://cotlet.dev/integrations/instapaper-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=instapaper, requests Instapaper in the Cotlet console and creates an API key there.
2. The user signs in to Instapaper once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Instapaper for agents. An agent cannot do this step.
3. The API key goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Instapaper server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Instapaper MCP server instead.

Policy: Cotlet never stores passwords, never solves CAPTCHAs, never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Instapaper in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Instapaper only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Instapaper login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Instapaper's terms; Cotlet is not affiliated with Instapaper.
```

## What can an AI agent do in Instapaper?

Cotlet is best for heavy Instapaper readers and researchers who want an agent to sort, archive and digest their reading list without running or fixing a server.

- **[Archive old and finished articles](https://cotlet.dev/integrations/instapaper-api-mcp-server/archive-old-instapaper-articles.md)** (runs: weekly): "Look at my Instapaper Home list. Archive every article I read to the end, and every article saved more than 90 days ago that I never opened. List the second group for me before archiving it." → `list_bookmarks`, `move_bookmark`
- **[Sort saved articles into folders and tags](https://cotlet.dev/integrations/instapaper-api-mcp-server/sort-instapaper-articles-into-folders.md)** (runs: daily): "Take the articles I saved to Instapaper today. Move recipes into my Recipes folder, and tag each article with one topic from my existing tags. If no tag fits, tell me instead of making a new one." → `list_bookmarks`, `list_folders`, `list_tags`, `move_bookmark`, `tag_bookmark`
- **[Export highlights from read articles](https://cotlet.dev/integrations/instapaper-api-mcp-server/export-instapaper-highlights.md)** (runs: weekly): "Every Sunday, take the Instapaper articles I archived this week. Collect my highlights from each one and send me a digest grouped by article, with the link and the passages." → `list_bookmarks`, `list_highlights`
- **Save a list of links to a folder**: "Save these 12 URLs to my Instapaper folder "Conference talks" and tag them "2026". Skip any that are already saved and tell me which." → `list_folders`, `list_bookmarks`, `save_bookmark`
- **Summarize unread articles for the week** (runs: weekly): "Take my 5 oldest unread articles in the Reading folder. Fetch the text of each, write a three-line summary, and tell me which are worth finishing and which to archive." → `list_bookmarks`, `get_article_text`, `move_bookmark`

## Can Instapaper automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Instapaper connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to archive old and finished articles, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

| Where | How to connect | How to schedule |
|---|---|---|
| Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. |
| n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/instapaper/bookmarks. | Schedule Trigger node. |
| Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. |
| Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. |
| Your own script | GET https://cotlet.dev/api/v1/instapaper/bookmarks with your API key. | cron or GitHub Actions. |

## Tools

**For AI agents:** Every endpoint and its schema is public. The 12 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Instapaper.

### list_bookmarks

Articles in one list: Home, Archive, Liked, a folder or a tag, with reading progress. Access: read. REST: `GET /api/v1/instapaper/bookmarks`. MCP: `instapaper_read → list_bookmarks`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `section` | enum | no | home, archive, liked, folder or tag. Default: home. |
| `folder_id` | integer | no | Folder ID from list_folders. Needed for section folder. |
| `tag` | string | no | Tag name from list_tags. Needed for section tag. |
| `limit` | integer | no | Articles per page. Default: 25. |
| `offset` | integer | no | Number of articles to skip. Default: 0. |

Returns saved articles from one list, newest first, with title, URL, saved time, reading progress from 0 to 1, and whether each is liked and archived. Choose the list with section: home, archive, liked, folder or tag. Section folder needs folder_id and section tag needs tag. Pass offset to read the next page. Folder and tag together are not allowed.

Example response:

```json
{
  "bookmarks": [
    {
      "bookmark_id": 1893240551,
      "title": "How to Salt Pasta Water",
      "url": "https://cooking.example.com/salt-pasta-water",
      "saved_at": "2026-08-03T18:22:00Z",
      "progress": 1,
      "liked": false,
      "archived": false,
      "folder_id": null,
      "tags": [
        "Cooking"
      ]
    }
  ],
  "total": 212
}
```

### get_article_text

The cleaned text of one saved article, with title, author and word count. Access: read. REST: `GET /api/v1/instapaper/bookmarks/{bookmark_id}/article-text`. MCP: `instapaper_read → get_article_text`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `bookmark_id` | integer | yes | Bookmark ID from list_bookmarks. |
| `max_chars` | integer | no | Cut the text after this many characters. Default: the whole article. |

Returns the article body Instapaper shows in its reader view, with title, author, published date, word count and the image URLs kept in the body. A paywalled flag says when the page looked paywalled and the body may be only a preview. The kind says whether the item is an article, email, video, PDF or social post. Read-only, nothing in the account changes.

Example response:

```json
{
  "bookmark_id": 1893240551,
  "title": "How to Salt Pasta Water",
  "author": "Rosa Delgado",
  "published_at": "2026-07-29T09:00:00Z",
  "kind": "article",
  "words": 1180,
  "paywalled": false,
  "text": "Most home cooks under-salt the water. The usual advice is a tablespoon per quart, but..."
}
```

### list_folders

Your folders with their IDs, in the order you set. Access: read. REST: `GET /api/v1/instapaper/folders`. MCP: `instapaper_read → list_folders`.

No parameters.

Returns every folder in the account with its ID, title and position. The ID is what list_bookmarks, save_bookmark and move_bookmark take. Home, Archive and Liked are not folders and are not listed.

Example response:

```json
{
  "folders": [
    {
      "folder_id": 381204,
      "title": "Recipes",
      "position": 1
    },
    {
      "folder_id": 381877,
      "title": "Conference talks",
      "position": 2
    },
    {
      "folder_id": 402115,
      "title": "Reading",
      "position": 3
    }
  ]
}
```

### list_tags

Your tags with their IDs and how many articles carry each. Access: read. REST: `GET /api/v1/instapaper/tags`. MCP: `instapaper_read → list_tags`.

No parameters.

Returns every tag with its ID, name and article count. Use the names to tag consistently and the IDs to remove a tag with tag_bookmark. The names come back as you typed them.

Example response:

```json
{
  "tags": [
    {
      "tag_id": 7,
      "name": "Cooking",
      "count": 41
    },
    {
      "tag_id": 12,
      "name": "Design",
      "count": 18
    },
    {
      "tag_id": 15,
      "name": "Finance",
      "count": 9
    }
  ]
}
```

### list_highlights

The highlighted passages of one article. Access: read. REST: `GET /api/v1/instapaper/bookmarks/{bookmark_id}/highlights`. MCP: `instapaper_read → list_highlights`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `bookmark_id` | integer | yes | Bookmark ID from list_bookmarks. |

Returns the highlights you made in one saved article, with the highlighted text and when you made each one. An article with no highlights returns an empty list. One call covers one article, so a digest reads one article after another.

Example response:

```json
{
  "bookmark_id": 1893240551,
  "highlights": [
    {
      "highlight_id": 77120431,
      "text": "Salt the water until it tastes like the sea, then add the pasta.",
      "created_at": "2026-10-12T19:04:00Z"
    }
  ]
}
```

### save_bookmark

Save a web page to your reading list, optionally into a folder, with tags. Access: write. REST: `POST /api/v1/instapaper/bookmark/save`. MCP: `instapaper_write → save_bookmark`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `url` | string | yes | The page to save. |
| `title` | string | no | Title to show. If left out, it is looked up. |
| `folder_id` | integer | no | Folder ID from list_folders. Default: Home. |
| `archived` | boolean | no | Save straight to the Archive. Default: false. |
| `tags` | string[] | no | Tag names to apply. New names are created. |

Saves the URL as a new article, in Home or straight into a folder or the archive. Tags you pass are created if they do not exist. Without a title, Instapaper looks the title up, which makes the call slower. Reaches no one and is undone with one move_bookmark or delete_bookmark call, so it runs without asking. Returns the new article.

Example response:

```json
{
  "bookmark_id": 1893301187,
  "title": "Slow Cooker Beans, Start to Finish",
  "url": "https://cooking.example.com/slow-cooker-beans",
  "folder_id": 381204,
  "archived": false,
  "tags": [
    "2026",
    "Cooking"
  ]
}
```

### move_bookmark

Move an article to the Archive, back to Home, or into a folder. Access: write. REST: `POST /api/v1/instapaper/bookmarks/{bookmark_id}/move`. MCP: `instapaper_write → move_bookmark`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `bookmark_id` | integer | yes | Bookmark ID from list_bookmarks. |
| `destination` | string | yes | 'archive', 'home', or a folder ID from list_folders as a string, e.g. '381204'. |

Moves one article and returns it. Destination is archive, home or a folder ID as a string. Liked stays as it was, because liked and archived are separate. Reaches no one and is undone by moving the article back, so it runs without asking.

Example response:

```json
{
  "bookmark_id": 1893240551,
  "title": "How to Salt Pasta Water",
  "archived": true,
  "folder_id": null,
  "liked": false
}
```

### set_liked

Add an article to your Liked list, or remove it. Access: write. REST: `PUT /api/v1/instapaper/bookmarks/{bookmark_id}/liked`. MCP: `instapaper_write → set_liked`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `bookmark_id` | integer | yes | Bookmark ID from list_bookmarks. |
| `liked` | boolean | yes | true to like, false to unlike. |

Sets the liked flag on one article and returns it. It does not change whether the article is in Home, the Archive or a folder. Reaches no one and is undone with the same call, so it runs without asking.

Example response:

```json
{
  "bookmark_id": 1893240551,
  "title": "How to Salt Pasta Water",
  "liked": true,
  "archived": false
}
```

### tag_bookmark

Add tags to an article by name, or remove them by ID. Access: write. REST: `POST /api/v1/instapaper/bookmarks/{bookmark_id}/tag`. MCP: `instapaper_write → tag_bookmark`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `bookmark_id` | integer | yes | Bookmark ID from list_bookmarks. |
| `add_tags` | string[] | no | Tag names to add. |
| `remove_tag_ids` | integer[] | no | Tag IDs to remove, from list_tags. |

Adds the tag names you pass, creating any that do not exist, and removes the tag IDs you pass. Removals run before additions. Returns the full tag list of the article afterwards and the tags this call created. Reaches no one and is undone with another call, so it runs without asking.

Example response:

```json
{
  "bookmark_id": 1893240551,
  "created_tags": [
    {
      "tag_id": 31,
      "name": "Weeknight"
    }
  ],
  "tags": [
    {
      "tag_id": 7,
      "name": "Cooking"
    },
    {
      "tag_id": 31,
      "name": "Weeknight"
    }
  ]
}
```

### create_folder

Create a new folder in your account. Access: write. REST: `POST /api/v1/instapaper/folders`. MCP: `instapaper_write → create_folder`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `title` | string | yes | Folder name. |

Creates a folder with the title you give and returns its ID. It goes to the end of your folder order. Reaches no one and is undone by deleting the folder in Instapaper, so it runs without asking.

Example response:

```json
{
  "folder_id": 403350,
  "title": "Home projects",
  "position": 4
}
```

### create_highlight

Highlight a passage of text in a saved article. Access: write. REST: `POST /api/v1/instapaper/bookmarks/{bookmark_id}/highlights`. MCP: `instapaper_write → create_highlight`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `bookmark_id` | integer | yes | Bookmark ID from list_bookmarks. |
| `text` | string | yes | The exact passage from the article. |
| `position` | integer | no | Which occurrence of the text to highlight, counting from 0. Default: 0. |

Highlights the text you pass inside one article and returns the highlight. Pass position to pick which occurrence when the text appears more than once; 0 is the first. Free accounts can create 5 highlights a month; past that the call fails. Reaches no one and is undone by deleting the highlight in Instapaper, so it runs without asking.

Example response:

```json
{
  "highlight_id": 77120502,
  "bookmark_id": 1893240551,
  "text": "Salt the water until it tastes like the sea.",
  "created_at": "2026-10-17T08:15:00Z"
}
```

### delete_bookmark

Delete a saved article permanently. Access: write, asks the user first. REST: `DELETE /api/v1/instapaper/bookmarks/{bookmark_id}`. MCP: `instapaper_write → delete_bookmark`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `bookmark_id` | integer | yes | Bookmark ID from list_bookmarks. |

Deletes the article, with its highlights and tags on it. This is not archiving: a deleted article does not come back. Use move_bookmark with destination archive to keep it. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "bookmark_id": 1893240551,
  "deleted": true
}
```

## How do I connect Instapaper to Claude Code, Codex or Cursor?

Connecting Instapaper takes three steps: sign up, sign in to Instapaper once in your Cloud Browser and enable it for agents, then add one MCP server or call the REST API with the same key.

### Connect Instapaper to your agent.

1. **Create an account** Sign up and add Instapaper in the console. Your API key is there too.

2. **Sign in to Instapaper in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Instapaper there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

3. **Add Cotlet to your agent** Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

   Claude Code:

```
claude mcp add --transport http cotlet \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"
```

   Cursor:

```
{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}
```

   Codex:

```
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
```

4. **Ask your agent** Ask in plain words. Your agent finds the Instapaper tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.

```
Look at my Instapaper Home list. Archive every article I read to the end, and every article saved more than 90 days ago that I never opened. List the second group for me before archiving it.
```

### Call Instapaper from your scripts.

1. **Export your API key** Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.

```
export COTLET_API_KEY="cotlet_..."
```

2. **Call a tool** Every tool is an endpoint under /api/v1/instapaper with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.

```
curl -X POST https://cotlet.dev/api/v1/instapaper/bookmark/save \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://cooking.example.com/slow-cooker-beans","folder_id":381204,"tags":["2026","Cooking"]}'
```

3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing.

```
{
  "bookmark_id": 1893301187,
  "title": "Slow Cooker Beans, Start to Finish",
  "url": "https://cooking.example.com/slow-cooker-beans",
  "folder_id": 381204,
  "archived": false,
  "tags": [
    "2026",
    "Cooking"
  ]
}
```

## Why use Cotlet for Instapaper?

**Built for agents**

- One MCP server for every app you connect.
- The same tools as a REST API for scripts and cron jobs.
- Works with Claude Code, Codex and Cursor.

**Your login stays yours**

- You sign in to Instapaper yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
- A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
- The model never sees a login.
- No stored passwords, no CAPTCHA solving, no MFA bypass.

**You stay in control**

- Scope each API key: its apps, its tools, read only or read and write.
- Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
- Every background request listed in your Background activity. Disable for agents in one click.

**Kept working for you**

- We test every integration every 6 hours.
- When Instapaper changes, the tool pauses until we fix it.
- Failed calls cost nothing.

## Is it safe to connect Instapaper to Cotlet?

Yes. You sign in to Instapaper yourself, in your own Cloud Browser, and we never save your password. Your agents only get Instapaper once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

- **A+ on Qualys SSL Labs**: Encryption in transit: TLS setup and certificates, on all four server addresses. [Live result](https://www.ssllabs.com/ssltest/analyze.html?d=cotlet.dev)
- **A+ on securityheaders.com**: Browser protections sent with every page, all six headers present. [Live result](https://securityheaders.com/?q=cotlet.dev&followRedirects=on)
- **A+ on Mozilla Observatory**: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. [Live result](https://developer.mozilla.org/en-US/observatory/analyze?host=cotlet.dev)
- **Clean on Sucuri SiteCheck**: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. [Live result](https://sitecheck.sucuri.net/results/cotlet.dev)

[How Cotlet protects your access](https://cotlet.dev/security.md)

### Common concerns

**Who runs Cotlet?**

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

**Is this an official Instapaper integration?**

No, Cotlet is independent of Instapaper. Instapaper's own API is too limited for this work. Cotlet works through your own Instapaper account, the way you use Instapaper in the browser, so you need no partner approval and no developer setup.

**What about client data and GDPR?**

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

**Can I start with read only?**

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

**Is it reliable?**

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

**How do I stop?**

Press Disable for agents next to Instapaper in your console: your agents lose access at once and you stay signed in. Signing out of Instapaper in the browser works too, and Reset browser deletes the whole profile.

## Is there a Instapaper MCP server on GitHub?

Yes. Community Instapaper MCP servers exist on GitHub, usually maintained by one person. You install one yourself, give it an API token, and fix it when Instapaper changes. Cotlet hosts the same kind of server for you, signs in as you, and our team keeps it working. For one-off scripts the official API is free and fine.

|  | GitHub MCP server | Cotlet |
|---|---|---|
| Setup | Clone the repo, register an application at Instapaper, generate an access token, add the server to each MCP client | Sign up, sign in to Instapaper once, add one MCP server or API key |
| When Instapaper changes | It breaks until you or the maintainer fix it; a server built on API v1 needs a rewrite before xAuth ends on 30 Sep 2027 | Our team tests it daily and fixes it for you; failed calls are free |
| Your Instapaper access | An access token in a file on your computer, readable by any program you run | Signed in inside your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When access expires | Access tokens do not expire, so you only renew one if you revoke it | Your Cloud Browser keeps you signed in; if Instapaper logs you out, your agent gets a link to sign in again |
| Upkeep | You update, monitor and debug it yourself | Nothing to host or update |
| Where it runs | Your computer, while it is on | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription |

### Which one fits you

**Pick Cotlet if**

- you are not a developer, or you do not want to maintain a server
- you need it to keep working when Instapaper changes, without checking it yourself
- your agent or a script should run it on a schedule, also while your computer is off

**Pick an open-source server if**

- you are comfortable installing, updating and fixing it yourself
- you want your sign-in to stay on your own computer
- you only need it now and then, from one MCP client

## How much does the Instapaper API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Instapaper API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 20 to 30 credits (25 for most tools, about $0.10 to $0.15), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

| Credits | Price, one time | Calls at 25 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 200 | $5.80 |
| 15,000 | $79 | 600 | $5.27 |
| 32,000 | $149 | 1,280 | $4.66 |
| 60,000 | $249 | 2,400 | $4.15 |

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the `Authorization: Bearer` header. [See full pricing](https://cotlet.dev/pricing.md)

## How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Instapaper account.

- **Company details:** Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. [Terms of service](https://cotlet.dev/terms)
- **Your sign-in:** You sign in to Instapaper yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Instapaper only after you enable it. When Instapaper signs you out, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security.md)
- **Revoking access:** Press Disable for agents next to Instapaper, sign out of Instapaper in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
- **What we never do:** Store passwords, solve CAPTCHAs or bypass MFA.
- **Instapaper's terms:** You use your own Instapaper account and stay responsible for following Instapaper's terms. Cotlet is independent and not affiliated with Instapaper. [Terms](https://cotlet.dev/terms)
- **Contact:** Questions about the company, security or an app: [contact@cotlet.dev](mailto:contact@cotlet.dev)

## Frequently asked questions

**How do I get access?**

Sign up free, open Instapaper in the console and press Request access. Then you create your API key and connect Instapaper there.

**Do I need to be technical?**

No. You sign in to Instapaper once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

**Is it safe to connect Instapaper to Cotlet?**

Yes. You sign in to Instapaper yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Instapaper once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

**Is a hosted server safer than a local one? My Instapaper sign-in would leave my computer.**

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Instapaper cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

**Why does Cotlet send requests instead of clicking in my browser?**

To be fast, Cotlet doesn't click through Instapaper's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Instapaper sees the same browser and IP you signed in with, and every request is listed in your Background activity.

**What if someone gets my Cotlet API key?**

The key holds no Instapaper login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

**Why a signed-in browser and not OAuth, like other integration platforms?**

Instapaper offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

**Does Instapaper Premium change what the tools can do?**

A little. Free accounts can create 5 highlights a month and have no full-text search across saved articles. Folders, tags, archiving and the official API are free (Instapaper Premium page, checked 17 Oct 2026). create_highlight stops at the monthly cap on a free account.

**Can the agent read articles that are behind a paywall?**

Only what Instapaper saved. get_article_text returns a paywalled flag when the page looked paywalled, and the text may then be a preview (Instapaper API v2 spec).

**Can my agent post or send messages in Instapaper without asking me?**

No. Every call to delete_bookmark waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. save_bookmark, move_bookmark, set_liked, tag_bookmark, create_folder, create_highlight runs without asking, because it sends nothing to anyone and one call undoes it.

**Can I use the Instapaper API in n8n?**

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/instapaper from the HTTP Request node.

---

Give your AI agents your signed-in browser.

**Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md)

**Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet)

**Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md)

**Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md)

**Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors)

**Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet)

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.

## For AI agents: sign your user up

Is your user asking you to sign them up for Cotlet? You can do it for them, no account or key needed.

1. Read the fields and their allowed values: GET https://cotlet.dev/api/v1/access-requests
2. Ask the user for each value: email, apps, what you will do with them. If they leave the password to you, generate a strong one and show it to them.
3. Show the user what you will send, then POST it as JSON to https://cotlet.dev/api/v1/access-requests.

One call creates the account and sends the access request; we email the user when access is granted.