Bring Bookmark Manager
to OpenAI Agents SDK
Learn how to connect Linkwarden to OpenAI Agents SDK and start using 32 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Linkwarden MCP Server?
Connect your Linkwarden instance to any AI agent and take full control of your personal knowledge base through natural conversation. Linkwarden is a self-hosted collaborative bookmark manager to collect, organize, and preserve webpages.
What you can do
- Collection Management — List all your collections, create new ones, and organize your bookmarks into logical folders.
- Web Archiving — Retrieve preserved archive files for your links to ensure you never lose access to important information, even if the original site goes down.
- Dashboard Insights — Access your dashboard data (v1 and v2) to get a high-level overview of your saved content and activity.
- Link Operations — Create, update, and manage links and their associated metadata or highlights directly from the chat.
- System Configuration — Quickly retrieve public runtime configurations and user profile information.
How it works
- Subscribe to this server
- Enter your Linkwarden Instance URL and Personal Access Token
- Start managing your web archives from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Researchers — instantly organize sources and retrieve archived versions of papers or articles without leaving your research flow
- Developers — manage technical documentation links and code snippets directly from your IDE
- Knowledge Workers — maintain a clean, organized library of web resources using natural language commands
Built-in capabilities (32)
Archive a link (triggers an update of the link's archive files)
Send password reset email
Reset password with token
Verify email address
Bulk update links (tags/collections)
Create a new collection
Create or update a highlight
Create a new link
Delete a collection
Delete a highlight
Retrieve an archive file by link ID
Retrieve user avatar
Get collection by ID
Retrieve public runtime configuration
Get dashboard data (v1)
Get dashboard data (v2)
Get a link by ID
Get highlights for a link
Get login configuration
Retrieve migration data (user info, collections, links for export)
Create short-lived preserved format URL token
Retrieve links from a specific collection (public)
Get tags for a collection (public)
Import data for migration
Get all collections
List RSS subscriptions
Stream archived format
Update a collection
Update dashboard layout (v2)
Update a link
Upload or replace a client-side archive file for a specific link
Upload an archive file, create a new link, and store it in the default collection
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 32 tools from Linkwarden through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Linkwarden, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Linkwarden in OpenAI Agents SDK
Linkwarden and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Linkwarden to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Linkwarden in OpenAI Agents SDK
The Linkwarden MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 32 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Linkwarden for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Linkwarden MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I see a list of all my bookmark folders?
You can use the list_collections tool. It will retrieve all your existing collections, allowing the AI to show you how your bookmarks are organized.
Is it possible to retrieve an archived version of a saved link?
Yes! Use the get_archive tool with the specific Link ID. This will fetch the preserved archive file associated with that link.
Can I create a new collection directly through the AI?
Absolutely. Use the create_collection tool by providing a unique ID and the collection details in the payload.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Xata (Serverless DB)
30 toolsManage your serverless databases via Xata — list organizations, manage projects, branches, and execute SQL queries directly from any AI agent.
Snapchat Ads
8 toolsEquip your AI agent with direct access to Snapchat Ads — manage campaigns, track ad performance, and optimize spend without opening Snapchat Ads Manager.
ClickHouse (Vector Search)
7 toolsManage vector embeddings and SQL via ClickHouse — list databases, execute SQL, and perform high-speed vector searches directly from any AI agent.
Autodesk Construction Cloud
10 toolsManage projects, files, issues, and assets in Autodesk Construction Cloud natively via AI.