# Pocket MCP > Pocket MCP Server lets your AI client manage a personal reading library. Save articles, videos, and web pages from any source into one place. You can programmatically tag items, archive completed reads, or search your entire saved collection using simple conversation. ## Overview - **Category:** industry-titans - **Price:** Free - **Tags:** content-curation, reading-list, bookmarking, knowledge-base, web-clipping ## Description Pocket MCP Server lets your AI client take full charge of what you save online. You clip articles, videos, and web pages from any source right into one place, treating that content library like structured data. Your agent acts like a dedicated curator for everything you collect. **Saving Content:** Clip URLs or articles straight to Pocket using `save_to_pocket`. When you send the link, your AI client can even slap on a custom title before it saves, keeping things organized from the jump. **Managing Tags and Metadata:** You're in control of how everything gets filed. Your agent adds tags to single items or multiple items using `add_tags_to_item`. If you need to clean up some old labels, you can use `remove_tags_from_item` to pull specific tags off an item. Sometimes you gotta wipe the slate clean; that's where `clear_item_tags` comes in. Need to adjust how you categorize stuff? You can run `rename_pocket_tag` to change a tag's name across your whole collection. **Filtering and Searching Your Library:** Finding that one piece of info when you need it is critical. Use `search_pocket_list` to search all saved items by keywords, specific tags, or other criteria. You can also get a full inventory of everything you’ve collected using `list_saved_items`. If something's gone off-track from your favorites list, you can mark it as one with `favorite_pocket_item`, and if you change your mind, running `unfavorite_pocket_item` takes it right back. **Controlling Item Status:** Your agent manages the lifecycle of every piece. If an article is finished reading, you archive it to keep your main list clean using `archive_pocket_item`. For items that are garbage or redundant, you can permanently delete them with `delete_pocket_item`; remember, that action is final. You can also completely strip all tags from an item that's been mislabeled by running `remove_tags_from_item` on a specific label or using `clear_item_tags` if you gotta go nuclear. **Authentication:** Before doing anything else, run `test_pocket_auth`. This confirms your agent can connect and operate with the right credentials. You'll never need to manually click through web pages again; you just talk to your research notes. ## Tools ### save_to_pocket Saves a given URL and optional custom title into your Pocket reading list. ### add_tags_to_item Adds one or more specified labels (tags) to a single reading list item. ### archive_pocket_item Moves an existing article from your active reading list into the archive. ### clear_item_tags Removes every single tag associated with a specific item. ### delete_pocket_item Permanently removes an article from your Pocket library. This action cannot be undone. ### favorite_pocket_item Marks a selected item as a favorite, making it easy to find later. ### list_saved_items Retrieves and displays a list of items currently saved in your Pocket library. ### remove_tags_from_item Removes specific labels or tags from an item that were previously applied. ### rename_pocket_tag Changes the name of an existing tag across your entire library. ### search_pocket_list Searches all saved items using keywords, tags, or other search parameters. ### test_pocket_auth Runs a check to confirm the connection credentials are valid and authorized for use. ### unfavorite_pocket_item Removes an item from your list of favorites. ## Prompt Examples **Prompt:** ``` List my last 10 unread items in Pocket. ``` **Response:** ``` I've retrieved your list. You have 10 unread items including 'Future of AI' and 'Rust Guide'. Which one would you like to tag or archive? ``` **Prompt:** ``` Show me all articles I saved this week organized by tag and reading time. ``` **Response:** ``` You saved 23 articles this week. By tag: "Tech" (8 articles, avg 7 min read), "Business" (6 articles, avg 12 min), "Design" (5 articles, avg 5 min), "Untagged" (4 articles). Longest read: "The Future of AI Infrastructure" at 24 minutes. 14 articles are still unread. Top source: Hacker News (6 saves), followed by Medium (5) and individual blogs (4). Total estimated reading time: 3 hours 15 minutes. ``` **Prompt:** ``` Archive all articles tagged with Q1 Research that I have already read. ``` **Response:** ``` 12 articles archived successfully from the "Q1 Research" tag. Articles moved from your reading list to the archive: 8 from Harvard Business Review, 2 from McKinsey Quarterly, 1 from MIT Technology Review, and 1 from Stanford GSB. Average reading time of archived articles: 14 minutes. 3 articles with the same tag remain in your list as they are still marked unread. ``` ## Capabilities ### Save and Clip Content Sends a URL or article link to Pocket for permanent storage in your reading list. ### Filter and Search Library Items Searches all saved articles using keywords, tags, or specific criteria. ### Manage Item Metadata (Tags) Adds, removes, renames, or clears tags from one or many items to organize content by topic. ### Control Item Status Archives completed articles, deletes unwanted saves, or marks sources as favorites within your library. ## Use Cases ### Researching a new industry vertical. A student saves 40 links over two weeks. Instead of opening Pocket and clicking tags, they tell their agent: 'Find all articles tagged 'AI Ethics' that I haven't read yet.' The agent runs `search_pocket_list` and filters the results instantly. ### Cleaning up a messy content library. A curator saved 100 items, but half are junk. They ask the agent to 'Archive all articles that I favorited last month.' The tool runs `archive_pocket_item` and keeps the valuable favorites separate. ### Restructuring a knowledge base. A team realized their tags are inconsistent. They tell the agent: 'Rename all instances of 'Tech Stuff' to 'Deep Tech Focus' across my entire library.' The tool runs `rename_pocket_tag` and fixes consistency in one command. ### Preparing for a deep dive session. A writer needs sources on 'Modern Finance'. They tell the agent: 'Show me all articles tagged 'Finance' but not yet read.' The tool runs `list_saved_items` and narrows down their focus immediately. ## Benefits - You don't lose track of sources. Use `add_tags_to_item` to categorize dozens of articles at once, grouping them by 'Q3 Research' or 'Marketing Concept,' instead of relying on memory. - Finding specific content is instant. Instead of scrolling through hundreds of saves, run `search_pocket_list` for a keyword like 'GraphQL' and get immediate results. - Manage your reading list cleanly. Once you finish an article, use `archive_pocket_item`. This moves it out of the main view without deleting the record. - Control your tags completely. If you mislabel something, run `remove_tags_from_item` or use `clear_item_tags` to wipe the slate clean for that specific item. - The system handles the heavy lifting. Instead of manually remembering which articles need reviewing, ask your agent to `list_saved_items` filtered by 'unread' status. ## How It Works The bottom line is: Your AI client becomes the interface for managing your entire web-clipped knowledge base. 1. Subscribe to this server and enter your Pocket Consumer Key and Access Token. 2. Your AI client connects the credentials and verifies connection using `test_pocket_auth`. 3. You give a command (e.g., 'Add Tech and Research tags to these three articles'). The agent executes the tool calls, modifying your library instantly. ## Frequently Asked Questions **How do I check if my Pocket connection is working with add_tags_to_item?** Run `test_pocket_auth` first to confirm credentials. If that succeeds, you can start testing the tags immediately by using `add_tags_to_item` on a test article. **Can I move articles from my list without deleting them?** Yes. Use the `archive_pocket_item` tool. This moves the article out of your main reading view but keeps it in Pocket's archive, so you don't lose it. **Is there a way to find articles based on multiple tags?** You can search by combining tags and keywords using `search_pocket_list`. For example: 'Search for AI AND tag:Future'. **If I delete an item, is it permanent?** Yes. The `delete_pocket_item` tool permanently removes the content from your Pocket account. Use this only when you are sure the article is junk. **If I run `test_pocket_auth` and it fails, what should I check first?** Check your Consumer Key and Access Token. The connection requires valid credentials from the Pocket developer portal. If they're correct, confirm that there are no rate limits currently enforced. **How can I use `add_tags_to_item` to tag multiple articles at once?** You must provide a list of item IDs and the tags you want to apply. The agent handles batch inputs, so you don't need to run the command for each article individually. **If I use `search_pocket_list`, what should I do if multiple articles match my keywords?** Specify more details in your query, like a date range or an item ID. The search needs unique identifiers to pinpoint the exact article you're talking about. **What happens if I try to use `remove_tags_from_item` on an item that has no tags?** Nothing bad happens. The system will simply report that no tags were found and the operation completes successfully without throwing an error. **Can my AI automatically find items with a specific tag in Pocket?** Yes! Use the `get_pocket_items` tool. Provide the `tag` parameter, and your agent will respond with all matching items, including titles, URLs, and time added in seconds. **How do I find my Consumer Key and Access Token?** Visit the [**Pocket Developer Portal**](https://getpocket.com/developer/), create an application to get your **Consumer Key**, and perform the OAuth flow to obtain your **Access Token**. **Can I archive multiple items at once via the AI?** While the `archive_item` tool handles items individually, you can ask the agent to process a list of IDs sequentially to clean up your library.