An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Writer AI Enterprise LLM to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run Palmyra models and manage knowledge graphs through your agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 24 capabilities

We ship only the actions that matter.

Capability set01 / 06

01-04

4 capabilities in this set.

Part of 24 available through Writer.

  1. 01

    Get file

    Get the metadata for a specific file using its unique ID.

  2. 02

    List applications

    Get a list of all deployed no-code agents and applications.

  3. 03

    List models

    Check which Writer models are currently available for use.

  4. 04

    Parse PDF

    This deprecated capability converts PDF files into text or markdown.

Capability set02 / 06

05-08

4 capabilities in this set.

Part of 24 available through Writer.

  1. 05

    Remove file from graph

    Delete a specific file from a Knowledge Graph.

  2. 06

    Text completion

    Generate text completions for a single prompt using Writer models.

  3. 07

    Chat completion

    Generate chat-based responses using the Writer model family.

  4. 08

    Upload file

    Upload new files to be used for Knowledge Graphs or vision tasks.

Capability set03 / 06

09-12

4 capabilities in this set.

Part of 24 available through Writer.

  1. 09

    Web search

    Perform a web search to find real-time information outside of your local data.

  2. 10

    Download file

    Retrieve the binary content of a file using its unique ID.

  3. 11

    Add file to graph

    Add an existing uploaded file to a specific Knowledge Graph.

  4. 12

    Analyze vision

    This capability lets your agent analyze images or documents using specific prompts and variable mappings.

Capability set04 / 06

13-16

4 capabilities in this set.

Part of 24 available through Writer.

  1. 13

    Ask question

    Query one or more Knowledge Graphs using RAG to get answers to specific questions.

  2. 14

    Create graph

    Use this to start a new Knowledge Graph by providing a unique name and description.

  3. 15

    Delete file

    Permanently remove a file from your storage using its ID.

  4. 16

    Generate application content

    Run synchronous content generation for a no-code application using its ID and required variables.

Capability set05 / 06

17-20

4 capabilities in this set.

Part of 24 available through Writer.

  1. 17

    Generate application content async

    This capability triggers asynchronous content generation for a specific no-code application and returns a job ID.

  2. 18

    Get application

    Retrieve the configuration and input requirements for a specific no-code application.

  3. 19

    Get application job

    Check the status and final result of an application job using its unique ID.

  4. 20

    List application jobs

    View the history and current status of all jobs for a specific application.

Capability set06 / 06

21-24

4 capabilities in this set.

Part of 24 available through Writer.

  1. 21

    List files

    Get a paginated list of all files you have uploaded.

  2. 22

    List graphs

    Retrieve a list of all your created Knowledge Graphs.

  3. 23

    Retry application job

    Restart a failed application job using its job ID.

  4. 24

    Translate text

    Translate text between different supported languages.

Real work

What teams actually run

01

RAG Implementation

Build a knowledge base by uploading documents to a Knowledge Graph and querying them for answers.

02

Automated Content Pipelines

Trigger no-code applications to generate large batches of content asynchronously.

03

Document Intelligence

Use vision capabilities to extract information from uploaded images or complex documents.

04

Knowledge Management

Organize and clean up enterprise data by managing files and graph structures via your agent.

Automate a task

Put Writer to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Writer works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Writer to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1039ms average. Fast in production.

Writer is checked daily against the live service.

Daily averagePeak 1317ms
Oct 3Today
Fastest day
786ms
Slowest day
1317ms
14-day trend
Improving-10%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 24 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Writer, so you can see the experience inside your AI.

It does not authenticate your account with Writer. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Writer Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_yrsful81rgtIcMZXt4yQE12SkSrbuSWmhu7UnyRz/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Writer capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "writer-ai-enterprise-llm-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_yrsful81rgtIcMZXt4yQE12SkSrbuSWmhu7UnyRz/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Writer in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Writer owners hand off.

This MCP is built for technical teams working within enterprise environments that require secure, scalable AI.

  • 01

    Enterprise Developers

    Build RAG applications using secure and compliant LLMs.

  • 02

    Content Teams

    Automate high-quality content production with custom models.

  • 03

    Data Engineers

    Manage document pipelines and knowledge graphs through conversation.

FAQ

Questions Writer owners ask.

  • 01

    How do I connect this MCP to my AI client?

    You subscribe to the MCP on Vinkius and connect your client, such as Claude or Cursor, in one click. Vinkius handles the hosting and credentials for you.

  • 02

    What models can my agent access?

    Your agent can access the Palmyra family of models, including Palmyra-X5, through the list_models capability.

  • 03

    Can I use this for RAG?

    Yes. You can create Knowledge Graphs, add files to them, and use the ask_question capability to perform RAG-based queries.

  • 04

    Do I need to manage my own API keys?

    You will need to provide your Writer API Key during the setup process to authenticate your requests.

  • 05

    Can I run large content generation tasks?

    Yes. You can use the asynchronous generation capabilities to trigger jobs and then check their status using the job ID.

  • 06

    How do I see which Palmyra models are available in my account?

    Use the list_models capability. It will return a list of all active models in your Writer account, such as palmyra-x5 or palmyra-med.

  • 07

    Can I use my own documents for AI responses?

    Yes. First, use upload_file to add your documents, then create_graph and add_file_to_graph to build a Knowledge Graph for RAG-based querying.

  • 08

    Does this support conversational history?

    Yes, the chat_completion capability accepts a messages array, allowing you to maintain full context for multi-turn dialogues with the model.

Explore

More in Developer Tools

Suggestions

Connect Writer to Claude, Cursor, ChatGPT & more