ArcXP MCP. Manage articles, assets, and authors from your AI chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
ArcXP MCP Server automates publishing workflows for newsrooms. Use it to manage, search, and update articles, photos, and videos directly from your AI agent.
It lets you create new content, find specific assets using powerful Elasticsearch search, and list author profiles without touching the CMS editor.
What your AI agents can do
Create ans content
Builds a new story payload that must follow the strict Arc Native Schema (ANS) rules, then publishes it to the Arc XP Content CMS.
Delete ans content
Removes content from the Arc XP Content CMS. Note: This action is irreversible and destroys data.
Get ans content
Retrieves the complete JSON payload for a specific story, matching the Arc Native Schema (ANS).
Use create_ans_content to write new stories or update_ans_content to push revisions to existing articles.
The search_ans_content tool queries the CMS using Elasticsearch syntax to find articles or reports by keyword or date.
You can pull high-res images with get_photo_asset or video playlists with get_video_asset from the media libraries.
The list_content_authors tool gives you a roster of active publishers, and get_content_author fetches a specific reporter's bio.
You can fetch content payloads with get_ans_content or delete stories entirely using delete_ans_content.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
ArcXP MCP Server: 10 Tools for Content Publishing
These tools let your AI agent interact with the ArcXP Content CMS, allowing you to manage content, search assets, and automate the entire publishing lifecycle.
019d7551create ans content
Builds a new story payload that must follow the strict Arc Native Schema (ANS) rules, then publishes it to the Arc XP Content CMS.
019d7551delete ans content
Removes content from the Arc XP Content CMS. Note: This action is irreversible and destroys data.
019d7551get ans content
Retrieves the complete JSON payload for a specific story, matching the Arc Native Schema (ANS).
019d7551get content author
Looks up a specific publisher's profile or author details from Arc XP.
019d7551get photo asset
Retrieves a high-resolution photo asset from the Arc XP Media Library using a given identifier.
019d7551get video asset
Pulls a specific video asset or its associated streaming playlist from the Arc XP Video Center.
019d7551list content authors
Lists all available author profiles registered in the Arc XP Author Service.
019d7551search ans content
Searches the entire newsroom for stories, returning matching ANS JSON objects based on search criteria.
019d7551search photo assets
Searches the Arc XP Media Library for photo assets using keywords or filters.
019d7551update ans content
Replaces or publishes revisions to existing content in the Arc XP Content CMS.
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
Make Your AI Do More
Start with ArcXP, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
You're running a newsroom, and you don't wanna mess with the CMS editor. Connect your AI agent to this server, and you'll manage everything—articles, photos, videos—straight through conversation. You'll handle the entire publishing workflow without ever touching the actual editor. create_ans_content builds a new story payload that follows the strict Arc Native Schema (ANS) rules and publishes it straight to the Arc XP Content CMS. update_ans_content pushes revisions to existing articles in the CMS.
You can pull the full JSON payload for any story using get_ans_content, or wipe a story clean with delete_ans_content; just know that action is permanent. When you need to find something specific, search_ans_content queries the whole newsroom using Elasticsearch syntax, letting you track down articles or reports by keyword or date.
You can pull high-res images from the media library using get_photo_asset, and you'll get specific video assets or their streaming playlist by calling get_video_asset. To manage who's writing, list_content_authors gives you a list of every active publisher, and get_content_author pulls a specific reporter's bio. You'll also find search_photo_assets lets you search the media library for photos using keywords or filters.
You'll get a full picture of your publishing roster and the assets you need, all from your chat window.
How ArcXP MCP Works
- 1 Subscribe to the ArcXP server and provide your Environment URL and Access Token.
- 2 Your AI agent invokes the desired tool (e.g.,
search_ans_content) through the MCP protocol. - 3 The server executes the request against the ArcXP API and returns the structured data payload to your agent.
The bottom line is that your AI agent handles the API calls, letting you manage the CMS using natural language.
Who Is ArcXP MCP For?
Editors, journalists, and digital publishers who spend too much time in slow CMS interfaces. This is for the workflow specialist who needs to manage content, assets, and authors without switching screens or building custom scripts.
Fetches related archive material using search_ans_content and then sends it to an editor for quick review.
Automates bulk content updates or sanitizes raw CMS payloads using update_ans_content.
Creates new stories or updates drafts using create_ans_content and ensures the correct author is linked via get_content_author.
What Changes When You Connect
- Publishing is faster. Instead of manually submitting JSON or waiting for the CMS editor, use
create_ans_contentto publish new stories directly through your agent. - Find anything instantly. The
search_ans_contenttool uses Elasticsearch search to find articles across the entire CMS, not just keyword matching in one field. - No more asset hunting. Need a specific image?
get_photo_assetpulls the high-resolution file directly, saving you time in the media uploader. - Streamline author checks. Use
list_content_authorsto get a complete roster of publishers, andget_content_authorto verify a specific reporter's bio before publishing. - Control the full lifecycle. You can fetch content with
get_ans_contentand then push revisions usingupdate_ans_content, keeping the entire workflow inside your AI agent. - Handle bulk changes. If you need to update 50 articles, you can use
update_ans_contentinstead of logging into the CMS 50 times.
Real-World Use Cases
Need to publish breaking news immediately.
A journalist gets a scoop. Instead of logging into the CMS and filling out forms, they tell their agent: 'Publish the story about X.' The agent uses create_ans_content, then runs get_photo_asset for the accompanying image, and finally uses get_content_author to confirm the current reporter's profile. The story is live.
Researching old articles for a retrospective piece.
A reporter needs background context. They ask their agent to search_ans_content for 'Election 2024' in the last two years. The agent returns 32 matching nodes. The reporter then uses get_ans_content on the most relevant ID to pull the full JSON payload for summarizing.
Updating a story with new facts.
An editor finds a fact error in a published article. They instruct their agent to get_ans_content for the story ID, make the necessary edits in the agent's memory, and then call update_ans_content to push the corrected version back to the CMS.
Finding media for a current assignment.
A journalist is assigned a piece on tech. They ask the agent to search_photo_assets for 'AI chip design' and search_video_assets for 'Quantum computing'. The agent provides a list of viable media IDs, which the journalist then pulls into their article.
The Tradeoffs
Manual JSON Schema Compliance
Manually constructing the required Arc Native Schema (ANS) JSON payload and ensuring every field is correct, which often leads to copy-paste errors or missing required tags.
→
Let your agent handle the structure. Use create_ans_content or update_ans_content. You feed the agent the raw facts, and it manages the complex ANS payload structure for you.
CMS Workflow Switching
Having to switch between the CMS editor, the media library, the author profiles, and an external spreadsheet just to build one article.
→
Keep everything in the chat. Use search_ans_content for articles, search_photo_assets for media, and list_content_authors for personnel. Your agent orchestrates it all.
Over-relying on GUI Search
Using the CMS built-in search bar, which often only searches titles or limited metadata fields, missing older or archived content.
→
Use the search_ans_content tool. It uses advanced Elasticsearch syntax to query the entire content body, ensuring you find everything.
When It Fits, When It Doesn't
Use this if you need to manage the full lifecycle of content, assets, and authors programmatically. You need to interact with the CMS using structured data (JSON) via natural language commands. The ideal use case is a journalist or content engineer who needs to build, revise, and publish stories without ever leaving their primary development environment. Don't use this if you only need to view a single static piece of data or if your content structure is simple enough for a basic database query; use a simple read-only tool instead. If your process relies on proprietary, non-ANS data formats, this server won't help.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ArcXP. 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
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 server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Building a news story requires opening five different tabs and copying data everywhere.
Today, writing a complex article means navigating the CMS editor, checking the media library for photos, pulling author bios from a separate database, and manually formatting the story payload into the required ANS JSON structure. You spend more time copying and pasting IDs than writing.
With this MCP server, you just tell your agent, 'Write about X and include this photo.' Your agent runs `get_photo_asset` for the image ID, then builds the full ANS payload using `create_ans_content`—all in the chat. The story is ready.
ArcXP MCP Server: Manage content, assets, and publishing
You eliminate the manual steps of logging into the Content CMS, searching the Media Library, and calling the Author Service separately. The agent runs `search_ans_content` for related articles, `search_photo_assets` for media, and then drafts the complete, structured content payload.
The result is a single, continuous session where your AI agent handles the complexity of the underlying CMS APIs. You simply focus on the content.
Common Questions About ArcXP MCP
How do I use the `search_ans_content` tool? +
You give the agent natural language search parameters. The agent translates this into an Elasticsearch query, searching across the whole CMS for matching story nodes. You can then request the full JSON payload for the results.
Can I use `create_ans_content` to post a story without an image? +
Yes, you can. The tool requires the ANS payload structure, which you must provide. If you need an image, you should first use get_photo_asset to retrieve the asset ID, then include that ID in your content payload.
What is the difference between `get_ans_content` and `search_ans_content`? +
search_ans_content finds multiple stories based on criteria (like date or keyword). get_ans_content retrieves the full, specific JSON payload for a single, known article ID.
How do I find available authors in the CMS? +
Use the list_content_authors tool. This returns a list of all active publisher profiles in the Author Service, which you can then use to reference an author when creating content.
Is `delete_ans_content` safe to use? +
No, it's not. The delete_ans_content tool permanently deletes data. Only use it when you are 100% sure you want to destroy the record, as the action is irreversible.
How do I use the `get_photo_asset` tool to find a specific image? +
You provide a unique asset ID or search query. This tool retrieves the high-resolution photo asset and associated metadata. You can then use this data to update a story or build a media gallery.
What should I do if `create_ans_content` fails due to a schema error? +
Review the error message for the required ANS schema field. The payload JSON must strictly comply with the requested Arc Native Schema (ANS) version. Correct the payload and try the call again.
How can I manage my publishing workflow using `update_ans_content`? +
You must pass the existing content's ID and the new content payload. This tool publishes revisions to articles, ensuring that your changes are saved to the CMS.
Can my AI automatically rewrite an older story using Arc Native Schema and safely publish the update? +
Absolutely. Ask your agent to fetch a specific story by its ID. It understands the complex JSON structure of ANS, allows you to instruct it on what changes to make (e.g., 'Update the headline and add this new quote to paragraph 3'), and can dispatch an update command that preserves the content tree without breaking the CMS.
Is it possible to find specific high-res photos inside the ArcXP Media Library using natural language? +
Yes! Use the photo assets search action to query tags or captions using descriptive words. The AI fetches the asset ID, caption, credit strings, and directly accessible image URLs, letting you browse your editorial imagery seamlessly.
Can I query what articles a specific editor has authored? +
Yes! You can retrieve the Editor ID from the Author service and run an Elasticsearch query targeting their author object in the search tool. This quickly compiles all the CMS output for that specific reporter.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Readwise
Equip your AI to directly search, read, and retrieve your unified digital highlights, books, and Reader documents stored in Readwise.
Deterministic Fair-Share Tip Splitter
Transform your AI into a hyper-precise ledger. Mathematically split complex restaurant bills, proportionally distribute taxes and tips, and resolve fractional penny discrepancies instantly.
Zoho Bookings
Automate appointment scheduling via Zoho Bookings — manage appointments, services, and staff with AI.
You might also like
JobScore
Manage jobs, candidates, and hiring teams via JobScore ATS API.
BCB Economia — PIB, Dívida, Reservas, PIX e SGS
Brazilian economic indicators: monthly GDP proxy (IBC-Br), public debt/GDP ratio, international reserves, trade balance, unemployment rate (PNAD), PIX payment statistics, and universal access to 20,000+ BCB time series via SGS codes.
GPTZero
Detect AI-generated text with confidence scores and highlight exactly which passages were likely written by a language model.