Kraviona MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cms_health | Check whether the Kraviona backend API is online. |
| list_postsC | List editorial posts, optionally filtered by status or search query. |
| get_post | Fetch every editable field for a post by MongoDB ID. |
| create_post | Create a complete Kraviona story. Prefer draft status until a human has reviewed facts and SEO. |
| update_post | Update a post by ID. Fetch it first with get_post when making substantial changes. |
| set_post_status | Change a post between draft and published. Publishing automatically enforces indexability, date, canonical URL and word count. |
| delete_post | Permanently delete a post. The confirm flag must explicitly be true. |
| list_categories | List all dynamic frontend categories and SEO data. |
| save_categoryC | Create or update a category used by frontend navigation and landing pages. |
| delete_categoryA | Delete a category only when it contains no posts. |
| list_services | List the dynamic commercial services displayed on the public frontend. |
| save_serviceC | Manage a service, its deliverables, official kraviona.com URL, publishing status and homepage feature flag. |
| delete_serviceA | Permanently delete a service only if it has no associated client enquiries. |
| list_inquiriesC | Read project briefs submitted from the public services contact form. |
| update_inquiry | Set the sales follow-up status and private admin notes for a client enquiry. |
| get_site_settings | Read global branding, homepage content, newsletter copy, default SEO and social profiles. |
| update_site_settingsB | Update global content, official company link, contact details and SEO displayed dynamically on the public frontend. |
| update_crawler_settingsC | Control dynamic robots.txt, sitemap.xml, llms.txt and ai.txt generation. |
| generate_ai_draftC | Ask the configured Anthropic model to create a complete SEO draft for human review. |
| list_keyword_queueA | List pending and used keywords for automated content generation. |
| add_keywordB | Add a keyword and target category to the automatic generation queue. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Each tool targets a clearly distinct resource or action: categories, services, posts, inquiries, site settings, crawler settings, AI drafts, and keywords. The two settings tools are separated by their descriptions (global frontend content vs. robots/sitemap generation), so an agent should not confuse them.
The naming mostly follows a clear verb_noun pattern: save_category, delete_service, list_posts, update_site_settings. Minor deviations include generate_ai_draft and add_keyword instead of a save/create verb, but the overall style is consistent and predictable.
With 11 tools, the server is well-scoped for a content management and SEO workflow. Each tool addresses a distinct functional area without unnecessary duplication or bloat.
There are significant gaps in the workflow: categories and services can be saved/deleted but not listed, posts can only be listed with no create/update/delete tool, settings can only be updated and not read, and inquiries are read-only. Most notably, generate_ai_draft produces a draft but there is no tool to save or publish it as a post, leaving an obvious dead end.