Pocket MCP for AI. Organize and tag saved articles via chat.

Q: How do I check if my Pocket connection is working with addtagstoitem?

Run testpocketauth first to confirm credentials. If that succeeds, you can start testing the tags immediately by using addtagstoitem on a test article.

Q: Can I move articles from my list without deleting them?

Yes. Use the archivepocketitem tool. This moves the article out of your main reading view but keeps it in Pocket's archive, so you don't lose it.

Q: Is there a way to find articles based on multiple tags?

You can search by combining tags and keywords using searchpocketlist. For example: 'Search for AI AND tag:Future'.

Q: If I delete an item, is it permanent?

Yes. The deletepocketitem tool permanently removes the content from your Pocket account. Use this only when you are sure the article is junk.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

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.

What your AI can do

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.

+ 9 more capabilities included

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.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Pocket MCP Server: 12 Tools for Content Management

Use these twelve tools to save, organize, categorize, and retrieve every piece of content you clip into Pocket.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Pocket on Vinkius

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...

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.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Pocket integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "pocket": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Pocket tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"pocket": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Pocket, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,000+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Pocket. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Finding your saved articles shouldn't feel like digging through junk mail.

Today, if you save an article to Pocket, you open the app. You scroll down a list of links that have nothing to do with what you were researching last week. To find the one key piece, you manually remember which tag you *think* it had, and then click through multiple filters until you get close—a process that takes minutes just to locate a single source.

With this MCP server, you talk directly to your reading list via natural language. You tell your agent: 'Show me all unread articles tagged 'Q1 Strategy' from the last month.' The agent runs `search_pocket_list` and returns only what you need. No clicks required.

Pocket MCP Server gives you total control over your saved content.

The manual steps that go away are the constant context-switching: opening Pocket, scrolling to find a tag, manually adding it, and then closing the app. You're constantly bouncing between your source material and your organization system.

Now, you clip the article, and in the same chat window, you run `add_tags_to_item` and `favorite_pocket_item`. Your AI handles the whole workflow. It keeps your research flow entirely within the conversation.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

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.

Built · Hosted · Managed by Vinkius Pocket MCP Server - Organize and Tag Articles

Server ID 019dd13e-2178-71ce-b596-07f6a83c0d0f

Vinkius Inspector

Compliance Grade A+

Score 98.33/100

Report View Report ↗

Here's how it actually works

The bottom line is: Your AI client becomes the interface for managing your entire web-clipped knowledge base.

Subscribe to this server and enter your Pocket Consumer Key and Access Token.

Your AI client connects the credentials and verifies connection using test_pocket_auth.

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.

Who is this actually for?

Researchers who collect dozens of articles weekly but can't keep track of which one was about what. Content strategists who need to tag and categorize inspiration feeds quickly. Technical writers drowning in research PDFs. If your knowledge base is a messy folder full of links, this is for you.

Academic Researcher

Needs to save papers from diverse sources (HBR, MIT) and instantly tag them by sub-field or research phase without leaving the terminal.

Content Strategist

Collects articles for future content pillars. Uses tags like 'SEO Pillar' or 'Design Inspiration' to keep sources organized before writing a single draft.

Technical Writer

Crops together research from multiple industry blogs and needs the AI agent to run list_saved_items filtered by source to track coverage gaps.

What Changes When You Connect

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.

See it in action

01 01

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.

02 02

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.

03 03

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.

04 04

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.

The honest tradeoffs

Treating Pocket as a simple folder.

Anti-pattern

Thinking that because you saved an article, it means nothing about its context. You forget why you saved it and just scroll aimlessly through the list.

The Fix

Don't rely only on saving. Always use add_tags_to_item immediately after clipping to give it immediate context (e.g., 'Source: HBR', 'Topic: Marketing').

Over-relying on manual tag deletion.

Anti-pattern

Running remove_tags_from_item repeatedly without a plan, leaving the item with no metadata and making it impossible to find later.

The Fix

If you need to clear tags, first run list_saved_items filtered by name. Then use clear_item_tags. Always confirm your intent before running that.

Searching without filters.

Anti-pattern

Typing a vague keyword into the search bar and getting 50 irrelevant results, forcing you to manually sort them all out.

The Fix

Be specific. Combine keywords with tags: 'Search for [Keyword] AND tag:[Tag Name]' using search_pocket_list.

When It Fits, When It Doesn't

Use this server if your core problem is metadata organization and retrieval. You need a system that lets you talk to your saved content like a database. Specifically, if you want to query across tags (add_tags_to_item) or manage item states (archiving with archive_pocket_item), this is right for you.

Don't use it if you need real-time collaboration sync, or if the source content itself needs active editing (like a document editor). If your goal is to write something based on research, and not just organize the links, you'll need a different tool set. This server manages what you saved, not what you create. Always confirm you are using test_pocket_auth first."

Questions you might have

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, 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.

Connect to your AI in seconds.

Save to pocket

Add tags to item

Archive pocket item

Pocket MCP Server: 12 Tools for Content Management

Make your AI actually useful.

Save To Pocket

Add Tags To Item

Archive Pocket Item

Clear Item Tags

Delete Pocket Item

Favorite Pocket Item

List Saved Items

Remove Tags From Item

Rename Pocket Tag

Search Pocket List

Test Pocket Auth

Unfavorite Pocket Item

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Finding your saved articles shouldn't feel like digging through junk mail.

Pocket MCP Server gives you total control over your saved content.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Researching a new industry vertical.

Cleaning up a messy content library.

Restructuring a knowledge base.

Preparing for a deep dive session.

The honest tradeoffs

Treating Pocket as a simple folder.

Over-relying on manual tag deletion.

Searching without filters.

When It Fits, When It Doesn't

Questions you might have