Kraviona MCP Server

Kraviona MCP Server

MCP server for the Kraviona platform API, providing tools for posts, categories, services, client enquiries, website settings, crawler files, AI drafts, and the keyword queue.

Category
Visit Server

README

Kraviona MCP Server

MCP server for the Kraviona platform API. It supports local stdio and authenticated Streamable HTTP for production. It exposes tools for posts, categories, services, client enquiries, website settings, crawler files, AI drafts, and the keyword queue.

Configure

Set these variables in your MCP host configuration:

KRAVIONA_API_URL=http://localhost:4000
KRAVIONA_ADMIN_EMAIL=your-admin@example.com
KRAVIONA_ADMIN_PASSWORD=your-admin-password

Never commit real credentials. The server signs in through the normal Kraviona API and keeps its HTTP-only session cookies in memory only.

MCP host configuration

{
  "mcpServers": {
    "kraviona": {
      "command": "node",
      "args": ["/absolute/path/to/kravionasite/mcp-server/src/index.js"],
      "env": {
        "KRAVIONA_API_URL": "http://localhost:4000",
        "KRAVIONA_ADMIN_EMAIL": "your-admin@example.com",
        "KRAVIONA_ADMIN_PASSWORD": "your-password"
      }
    }
  }
}

Run npm test -w mcp-server while the backend is running to verify tool discovery and API connectivity.

Production API setup

Keep production credentials in the ignored mcp-server/.env.production file, then start the stdio server with Node's environment-file support:

node --env-file=/absolute/path/to/mcp-server/.env.production /absolute/path/to/mcp-server/src/index.js

For Codex, configure this command under [mcp_servers.kraviona_production] in ~/.codex/config.toml. The MCP process runs locally while all CMS operations use https://api.kraviona.site. Restart Codex after changing MCP configuration.

Render production web service

Create a separate Render Web Service from the monorepo using these values:

Name: kraviona-site-mcp
Language: Node
Branch: main
Root Directory: mcp-server
Build Command: npm install
Start Command: npm run start:http
Health Check Path: /health

Set these Render environment variables:

NODE_VERSION=22
KRAVIONA_API_URL=https://api.kraviona.site
KRAVIONA_ADMIN_EMAIL=<production admin email>
KRAVIONA_ADMIN_PASSWORD=<production admin password>
MCP_BEARER_TOKEN=<a unique random secret of at least 24 characters>
MCP_PUBLIC_URL=https://YOUR-RENDER-SERVICE.onrender.com

Generate the bearer token locally with openssl rand -hex 32. Do not use the admin password as the bearer token. After deployment, verify the public health URL at https://YOUR-RENDER-SERVICE.onrender.com/health. The MCP endpoint is https://YOUR-RENDER-SERVICE.onrender.com/mcp and requires Authorization: Bearer <MCP_BEARER_TOKEN>.

Remote Codex configuration:

[mcp_servers.kraviona_remote]
url = "https://YOUR-RENDER-SERVICE.onrender.com/mcp"
bearer_token_env_var = "KRAVIONA_MCP_TOKEN"
startup_timeout_sec = 30
tool_timeout_sec = 60

Export KRAVIONA_MCP_TOKEN in the environment that starts Codex, then restart Codex. Test the production HTTP transport before deployment with:

npm run test:http -w mcp-server

Claude custom connector

Use the full Streamable HTTP URL when adding the connector:

https://YOUR-RENDER-SERVICE.onrender.com/mcp

The server advertises OAuth protected-resource and authorization-server metadata, supports Claude Dynamic Client Registration, and enforces PKCE. Clicking Connect opens the Kraviona consent screen. Enter the same value stored in MCP_BEARER_TOKEN; Claude receives a revocable OAuth access token and never receives the backend admin password.

mcp-kraviona

mcp-kraviona

mcp-kraviona

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured