[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) # Inoreader API and MCP server > Inoreader has a full REST API with OAuth 2.0 but no official MCP server (checked 17 Oct 2026). The API is free only for public apps on platforms where Inoreader is not available; everyone else needs the Pro plan, and the default quota on Pro is 100 requests per day in each of two zones. RSS and news reader: feeds, folders, tags, Read later and a rules engine that tags, stars, mails or forwards new articles on its own. ## What is the Inoreader API? Cotlet's Inoreader API exposes 13 endpoints for your own Inoreader account: list subscriptions, list folders and tags, get unread counts, list articles, search articles, list rules, mark as read, star article, tag article, add feed, move feed, unsubscribe from feed and create rule. The list_subscriptions endpoint returns feeds you follow, with title, URL and the folders each one is in. Each endpoint takes simple JSON inputs like article_ids, limit or cursor and works both as an operation of the inoreader_read or inoreader_write MCP tool for agents and as a REST call for scripts. - **Category:** [Productivity & teams](https://cotlet.dev/integrations/category/productivity-teams.md) - **Endpoints:** 13 (6 read, 7 write) - **Updated:** 2026-10-22 Inoreader has a full REST API with OAuth 2.0 but no official MCP server (checked 17 Oct 2026). Cotlet is a hosted MCP server and REST API for Inoreader with 13 endpoints (6 read, 7 write): you sign in once in your own cloud browser, your AI agent does the work. ## Does Inoreader have an official API? Inoreader has a full REST API with OAuth 2.0 but no official MCP server (checked 17 Oct 2026). The API is free only for public apps on platforms where Inoreader is not available; everyone else needs the Pro plan, and the default quota on Pro is 100 requests per day in each of two zones. | Task | Inoreader official | Cotlet | |---|---|---| | List subscriptions, folders and tags | Yes: API methods Feeds list and Folder/Tag list | Yes | | Read unread counts and unread articles | Yes: API methods Unread counts and Stream contents, 100 articles per call at most | Yes | | Mark articles as read | Yes: API edit-tag with the read tag | Yes | | Star and tag articles | Yes: API edit-tag with the starred tag or a custom tag | Yes | | Add a feed and move it to a folder | Yes: API Add feed and Edit feed | Yes | | Unsubscribe from a feed | Yes: API Edit feed with the unsubscribe action | Yes | | Search articles by text | Partly: Stream contents filters by read state, stars and time; no text search method is listed | Yes | | List and create rules | No: Rules are set in the Automate tab; the 14 documented API methods include none for them | Yes | Sources: [Inoreader developers: API overview](https://www.inoreader.com/developers/), [Inoreader developers: Rate limiting](https://www.inoreader.com/developers/rate-limiting), [Inoreader developers: Edit tag](https://www.inoreader.com/developers/edit-tag), [Inoreader blog: Save time with automations](https://www.inoreader.com/blog/2026/01/save-time-with-automations.html) ## For AI agents ```text Inoreader has a full REST API with OAuth 2.0 but no official MCP server (checked 17 Oct 2026). The API is free only for public apps on platforms where Inoreader is not available; everyone else needs the Pro plan, and the default quota on Pro is 100 requests per day in each of two zones. Cotlet provides a hosted MCP server and REST API for Inoreader: 13 tools (6 read, 7 write). Access Sign up at https://cotlet.dev/app/signup?app=inoreader, then request the app and create API keys in the Cotlet console. MCP server https://cotlet.dev/mcp/v1 MCP tools inoreader_read, inoreader_write, reads and writes apart; call one with {"operation": "", "arguments": {...}} REST base https://cotlet.dev/api/v1/inoreader, each operation at its own route, e.g. POST /api/v1/inoreader/article/star Auth Authorization: Bearer . Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in. Operations list_subscriptions, list_folders, get_unread_counts, list_articles, search_articles, list_rules, mark_as_read, star_article, tag_article, add_feed, move_feed, unsubscribe_feed, create_rule Confirm create_rule (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/inoreader-api-mcp-server.md How access works: 1. The user signs up at https://cotlet.dev/app/signup?app=inoreader, requests Inoreader in the Cotlet console and creates an API key there. 2. The user signs in to Inoreader once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Inoreader 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 Inoreader 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 Inoreader 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 Inoreader 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 Inoreader 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 Inoreader 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 Inoreader's terms; Cotlet is not affiliated with Inoreader. ``` ## What can an AI agent do in Inoreader? Cotlet is best for heavy Inoreader readers and research teams who want their agent to triage feeds, tag articles and set up rules without running or fixing a server. - **[Triage unread articles into starred and read](https://cotlet.dev/integrations/inoreader-api-mcp-server/triage-unread-articles.md)** (runs: daily): "Go through my unread Inoreader articles from the last 24 hours in the folder AI News. Star the ones about agents or MCP, mark the duplicates and obvious fluff as read, and give me a list of the starred ones with one line each." → `get_unread_counts`, `list_articles`, `star_article`, `mark_as_read` - **[Create Inoreader rules from a plain-language brief](https://cotlet.dev/integrations/inoreader-api-mcp-server/create-rules-from-a-brief.md)** (runs: weekly): "Look at my current Inoreader rules. Then create a rule for the folder Competitors: when the title or content mentions "pricing" or "price increase", tag the article pricing-watch and email it to me. Do not touch my existing rules." → `list_rules`, `create_rule` - **Clean up dead and noisy feeds** (runs: weekly): "List my Inoreader subscriptions with the unread count for each. Unsubscribe from feeds with more than 200 unread that I never starred, and show me the list before you do it." → `list_subscriptions`, `get_unread_counts`, `unsubscribe_feed` - **Add a list of feeds into folders** (runs: weekly): "Add these 12 feed URLs to Inoreader and put each one in the folder that fits its topic. Create no new folder if an existing one fits." → `list_folders`, `add_feed`, `move_feed` - **Save articles on a topic for research**: "Search my Inoreader for articles about "retrieval augmented generation" from the last 30 days, star the best ten and tag them rag-research." → `search_articles`, `star_article`, `tag_article` ## Can Inoreader automations run on a schedule in n8n, Make or Zapier? Yes. Cotlet does not replace your automation platform: it gives it a Inoreader 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 triage unread articles into starred and read, 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/inoreader/unread-counts. | 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/inoreader/unread-counts with your API key. | cron or GitHub Actions. | ## Tools **For AI agents:** Every endpoint and its schema is public. The 13 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 Inoreader. ### list_subscriptions Feeds you follow, with title, URL and the folders each one is in. Access: read. REST: `GET /api/v1/inoreader/subscriptions`. MCP: `inoreader_read → list_subscriptions`. No parameters. Returns every feed you follow with its title, site URL, feed ID and folders. Use the feed ID in list_articles, move_feed and unsubscribe_feed. The number of feeds is capped by your plan: 150 on Free and 2500 on Pro. Example response: ```json { "subscriptions": [ { "feed_id": "feed/https://example-changelog.dev/rss.xml", "title": "The Changelog Weekly", "site_url": "https://example-changelog.dev", "folders": [ "AI News" ] }, { "feed_id": "feed/https://labnotes.example/feed", "title": "Lab Notes", "site_url": "https://labnotes.example", "folders": [ "AI News", "Research" ] } ] } ``` ### list_folders Folders and tags in your account with their unread counts. Access: read. REST: `GET /api/v1/inoreader/folders`. MCP: `inoreader_read → list_folders`. No parameters. Returns your folders and tags with the unread count of each. Inoreader treats folders and tags alike: both are labels, and one article can sit under several. Use the name as the folder parameter of list_articles. Example response: ```json { "folders": [ { "name": "AI News", "type": "folder", "unread": 412 }, { "name": "Competitors", "type": "folder", "unread": 38 }, { "name": "to-read-friday", "type": "tag", "unread": 6 } ] } ``` ### get_unread_counts Unread articles per feed, folder and tag, and in total. Access: read. REST: `GET /api/v1/inoreader/unread-counts`. MCP: `inoreader_read → get_unread_counts`. No parameters. Returns the unread count for your whole account and for each feed, folder and tag. Inoreader caps a counter at a maximum that depends on your plan; when a count equals that maximum, at_cap is true and the real number is higher. Use it to pick where to start before reading articles. Example response: ```json { "total": 1180, "at_cap": false, "streams": [ { "name": "AI News", "type": "folder", "unread": 412 }, { "name": "Lab Notes", "type": "feed", "unread": 3 } ] } ``` ### list_articles Articles from your reading list, a folder, a tag, a feed or Starred, newest first. Access: read. REST: `GET /api/v1/inoreader/articles`. MCP: `inoreader_read → list_articles`. | Parameter | Type | Required | Description | |---|---|---|---| | `stream` | string | no | Folder or tag name, feed ID from list_subscriptions, or one of: reading_list, starred. Default: reading_list. | | `unread_only` | boolean | no | Leave out articles you have read. | | `since` | datetime | no | Only articles newer than this time. | | `oldest_first` | boolean | no | Oldest first instead of newest first. | | `limit` | integer | no | 1 to 100. Default: 20. | | `cursor` | string | no | Next page cursor from the previous call. | Lists articles from one stream, newest first unless oldest_first is set. Set unread_only to leave out articles you read, and since to cover a time window. Pages hold up to 100 articles and 20 by default; pass next_cursor back as cursor until it is null. Oldest-first lookback is limited to about one month. Example response: ```json { "articles": [ { "article_id": "1830442176", "title": "MCP spec adds elicitation", "feed": "The Changelog Weekly", "published_at": "2026-10-16T07:12:00Z", "starred": false, "read": false, "tags": [], "summary": "Servers can now ask the user a question mid-call..." }, { "article_id": "1830442190", "title": "Agents that plan before they browse", "feed": "Lab Notes", "published_at": "2026-10-16T08:40:00Z", "starred": false, "read": false, "tags": [], "summary": "A small planning step cut wasted page loads..." } ], "next_cursor": "eyJvZmZzZXQiOjIwfQ" } ``` ### search_articles Search your own articles by words in the title, the content or both. Access: read. REST: `GET /api/v1/inoreader/articles/search`. MCP: `inoreader_read → search_articles`. | Parameter | Type | Required | Description | |---|---|---|---| | `query` | string | yes | Words or phrases; AND, OR and NOT are supported. | | `match_in` | enum | no | title, content or both. Default: both. | | `include_public` | boolean | no | Search all public feeds, not only your own. Pro plan. | | `limit` | integer | no | 1 to 100. Default: 20. | | `cursor` | string | no | Next page cursor from the previous call. | Runs the Search bar of Inoreader on your own account and returns matching articles, newest first. Phrases in quotes and AND, OR and NOT work as in the app. Global search across public feeds is a Pro feature and is off unless include_public is set. Example response: ```json { "articles": [ { "article_id": "1830391002", "title": "Retrieval augmented generation, two years in", "feed": "Lab Notes", "published_at": "2026-10-09T06:30:00Z", "starred": false, "read": true, "tags": [] } ], "next_cursor": null } ``` ### list_rules Your automation rules with trigger, conditions, actions and how many articles each matched. Access: read. REST: `GET /api/v1/inoreader/rules`. MCP: `inoreader_read → list_rules`. No parameters. Returns the rules in the Automate tab: name, whether it is on, trigger, conditions and actions. The response also shows how many rule slots you use out of those your plan includes (30 on Pro). Rules are a Pro feature, so on Free the list can be empty. Example response: ```json { "rules": [ { "rule_id": "r_204", "name": "Mute sponsored posts", "enabled": true, "trigger": "new article in folder Newsletters", "conditions": "title and/or content contains \"sponsored\"", "actions": [ "mark as read" ], "matched_today": 3 } ], "slots_used": 11, "slots_total": 30 } ``` ### mark_as_read Mark up to 50 articles as read, or as unread again. Access: write. REST: `POST /api/v1/inoreader/as-read/mark`. MCP: `inoreader_write → mark_as_read`. | Parameter | Type | Required | Description | |---|---|---|---| | `article_ids` | array | yes | Article IDs from list_articles or search_articles, up to 50 per call. | | `read` | boolean | no | false marks as unread. Default: true. | Marks the articles as read, or as unread when read is false. Articles older than their feed's first item cannot be marked unread: Inoreader ignores that request, and those IDs come back in skipped. It reaches no one and is undone with one more call, so it runs without asking first. Example response: ```json { "updated": 51, "skipped": [], "read": true } ``` ### star_article Star articles, or remove the star. Access: write. REST: `POST /api/v1/inoreader/article/star`. MCP: `inoreader_write → star_article`. | Parameter | Type | Required | Description | |---|---|---|---| | `article_ids` | array | yes | Article IDs from list_articles or search_articles, up to 50 per call. | | `starred` | boolean | no | false removes the star. Default: true. | Adds the article to your Starred list, or removes it when starred is false. It reaches no one and is undone with one more call, so it runs without asking first. Example response: ```json { "updated": 2, "starred": true } ``` ### tag_article Add a tag to articles, or take one off. A new tag name creates the tag. Access: write. REST: `POST /api/v1/inoreader/article/tag`. MCP: `inoreader_write → tag_article`. | Parameter | Type | Required | Description | |---|---|---|---| | `article_ids` | array | yes | Article IDs from list_articles or search_articles, up to 50 per call. | | `tag` | string | yes | Tag name, for example rag-research. | | `remove` | boolean | no | true takes the tag off. Default: false. | Adds the tag to up to 50 articles, or removes it when remove is true. Tags are visible only to you and an article can carry several. It reaches no one and is undone with one more call, so it runs without asking first. A tag assigned this way can trigger a rule that watches that tag, and that rule may email or send the article on. Example response: ```json { "updated": 10, "tag": "rag-research", "removed": false } ``` ### add_feed Follow a feed by its URL, optionally in a folder. Access: write. REST: `POST /api/v1/inoreader/feeds`. MCP: `inoreader_write → add_feed`. | Parameter | Type | Required | Description | |---|---|---|---| | `url` | string | yes | Feed or site URL. | | `folder` | string | no | Folder to put the feed in. Created if missing. | Subscribes you to the feed at the URL and returns its title and feed ID. If you already follow it, the call still succeeds and nothing changes. Counts against your plan's feed cap (150 on Free, 2500 on Pro). It reaches no one and is undone with unsubscribe_feed, so it runs without asking first. Example response: ```json { "feed_id": "feed/https://example-changelog.dev/rss.xml", "title": "The Changelog Weekly", "already_following": false, "folder": "AI News" } ``` ### move_feed Add a feed to a folder, take it out of one, or rename it. Access: write. REST: `POST /api/v1/inoreader/feeds/{feed_id}/move`. MCP: `inoreader_write → move_feed`. | Parameter | Type | Required | Description | |---|---|---|---| | `feed_id` | string | yes | Feed ID from list_subscriptions. | | `add_to_folder` | string | no | Folder to add the feed to. | | `remove_from_folder` | string | no | Folder to remove the feed from. | | `title` | string | no | New title for the feed. | Changes where one feed sits: add_to_folder puts it in a folder, remove_from_folder takes it out, title renames it. A feed can be in several folders. It reaches no one and is undone with one more call, so it runs without asking first. Example response: ```json { "feed_id": "feed/https://labnotes.example/feed", "title": "Lab Notes", "folders": [ "AI News", "Research" ] } ``` ### unsubscribe_feed Stop following a feed. Access: write. REST: `POST /api/v1/inoreader/feeds/{feed_id}/unsubscribe`. MCP: `inoreader_write → unsubscribe_feed`. | Parameter | Type | Required | Description | |---|---|---|---| | `feed_id` | string | yes | Feed ID from list_subscriptions. | Removes the feed from your subscriptions. Its folder placement is lost, and add_feed brings the feed back without it. It reaches no one, so it runs without asking first; ask your agent to list the feeds before it unsubscribes. Example response: ```json { "feed_id": "feed/https://old-blog.example/rss", "title": "Old Blog", "status": "unsubscribed", "folders_were": [ "Misc" ] } ``` ### create_rule Create an automation rule: trigger, conditions and actions. Pro plan. Access: write, asks the user first. REST: `POST /api/v1/inoreader/rules`. MCP: `inoreader_write → create_rule`. | Parameter | Type | Required | Description | |---|---|---|---| | `name` | string | yes | Rule name. | | `scope` | enum | yes | account, feed, folder or tag: where the rule watches for new articles. | | `scope_name` | string | no | Folder or tag name, or feed ID. Required unless scope is account. | | `operator` | enum | no | all (AND) or any (OR) for the conditions. Default: all. | | `conditions` | array | yes | Objects with field (title_or_content, author, url, language, rss_category) and contains. | | `actions` | array | yes | Objects with type (assign_tag, read_later, mark_as_read, email, notification, webhook) and value where one is needed. | | `run_on_existing` | boolean | no | Also run the rule on articles you already have. Default: false. | Creates a rule in the Automate tab. Scope sets the trigger (account, feed, folder or tag), conditions match on title and/or content, author, URL, language or RSS category and are joined with any (OR) or all (AND), and actions can assign a tag, save to Read later, mark as read, send by email, notify or call a webhook. Rules need the Pro plan and count against its 30 rules. Email and webhook actions reach other people and services. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "rule_id": "r_219", "name": "Competitor pricing", "enabled": true, "slots_used": 12, "slots_total": 30 } ``` ## How do I connect Inoreader to Claude Code, Codex or Cursor? Connecting Inoreader takes three steps: sign up, sign in to Inoreader 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 Inoreader to your agent. 1. **Create an account** Sign up and add Inoreader in the console. Your API key is there too. 2. **Sign in to Inoreader in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Inoreader 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 Inoreader 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. ``` Go through my unread Inoreader articles from the last 24 hours in the folder AI News. Star the ones about agents or MCP, mark the duplicates and obvious fluff as read, and give me a list of the starred ones with one line each. ``` ### Call Inoreader 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/inoreader 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/inoreader/article/star \ -H "Authorization: Bearer $COTLET_API_KEY" \ -H "Content-Type: application/json" \ -d '{"article_ids":["1830442176","1830442190"]}' ``` 3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing. ``` { "updated": 2, "starred": true } ``` ## Why use Cotlet for Inoreader? **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 Inoreader 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 Inoreader changes, the tool pauses until we fix it. - Failed calls cost nothing. ## Is it safe to connect Inoreader to Cotlet? Yes. You sign in to Inoreader yourself, in your own Cloud Browser, and we never save your password. Your agents only get Inoreader 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 Inoreader integration?** No, Cotlet is independent of Inoreader. Inoreader's own API is too limited for this work. Cotlet works through your own Inoreader account, the way you use Inoreader 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 Inoreader in your console: your agents lose access at once and you stay signed in. Signing out of Inoreader in the browser works too, and Reset browser deletes the whole profile. ## Is there a Inoreader MCP server on GitHub? Yes. Community Inoreader MCP servers exist on GitHub and package registries, usually maintained by one person. You install one yourself, register your own Inoreader API app, run the OAuth sign-in, and keep it running. Cotlet hosts the same kind of server for you, so there is no app to register and no token to renew, and our team keeps it working. | | GitHub MCP server | Cotlet | |---|---|---| | Setup | Clone or install the package, register an API app in Inoreader preferences, complete OAuth, add the server to each MCP client | Sign up, sign in to Inoreader once, add one MCP server or API key | | When Inoreader changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free | | Your Inoreader session | App ID, app key and OAuth tokens 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 the session expires | Tools fail until you renew the token or sign in again by hand | Your Cloud Browser keeps you signed in; if Inoreader 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; the API itself needs a Pro plan | 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 Inoreader 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 Inoreader API cost? Free 7-day trial with 2,000 credits, no card needed. After that, the Inoreader 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 Inoreader 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 Inoreader 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 Inoreader only after you enable it. When Inoreader 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 Inoreader, sign out of Inoreader 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. - **Inoreader's terms:** You use your own Inoreader account and stay responsible for following Inoreader's terms. Cotlet is independent and not affiliated with Inoreader. [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 Inoreader in the console and press Request access. Then you create your API key and connect Inoreader there. **Do I need to be technical?** No. You sign in to Inoreader 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 Inoreader to Cotlet?** Yes. You sign in to Inoreader yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Inoreader 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 Inoreader 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 Inoreader 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 Inoreader's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Inoreader 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 Inoreader 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?** Inoreader 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). **Do I need the Pro plan?** For rules, yes: Inoreader lists rules, filters and monitoring feeds under Pro (30 rules, 50 filters, 30 monitoring feeds). Reading articles, starring, tagging and managing feeds work on any plan, within its feed cap of 150 on Free and 2500 on Pro. Inoreader's own API also needs Pro, which Cotlet does not use. **Does my agent run into the 100 requests per day API limit?** No. That quota belongs to Inoreader's API: on Pro, the default is 100 requests per day in each of two zones, one for reads and one for writes. Cotlet works in your signed-in account, not through the API, so that quota does not apply. **Can my agent post or send messages in Inoreader without asking me?** No. Every call to create_rule waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. mark_as_read, star_article, tag_article, add_feed, move_feed, unsubscribe_feed runs without asking, because it sends nothing to anyone and one call undoes it. **Can I use the Inoreader 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/inoreader 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.