Daktela MCP Server¶

The Daktela MCP Server connects AI assistants (Claude Code, Claude Desktop, Cursor, and others) to your Daktela Contact Centre using the Model Context Protocol (MCP). It provides read-only access to your contact centre data, enabling tasks like email quality audits, sales pipeline reviews, and call analysis — without writing any code.

Info

The MCP server provides read-only access to your Daktela data. It cannot create, modify, or delete any records in your instance.

There are two ways to use the Daktela MCP Server:

Hosted (Built-in) — the MCP server runs as part of your Daktela instance. No installation required.
Self-hosted — run the open-source PHP server yourself for custom deployments or cloud setups.

What is MCP?¶

The Model Context Protocol is an open standard that lets AI applications connect to external data sources and tools. By connecting to the Daktela MCP Server, your AI assistant gets structured, read-only access to your Daktela instance — enabling analysis and reporting tasks without any custom code.

Hosted (Built-in)¶

The hosted MCP server is built into your Daktela instance. No PHP, Docker, or Composer needed.

Step 1 — Get your Access Token¶

You need a personal API access token from your Daktela user profile. Go to your user profile → Access Tokens and generate a new token.

Tip

Create a dedicated token for your AI assistant so you can revoke it independently if needed.

Step 2 — Configure your AI client¶

Add the configuration below to your AI client. Replace YOUR_DOMAIN with your Daktela hostname (e.g. yourcompany.daktela.com) and YOUR_ACCESS_TOKEN with the token from Step 1.

Claude Code¶

Add to your project .mcp.json file:

{
  "mcpServers": {
    "daktela": {
      "type": "http",
      "url": "https://YOUR_DOMAIN/mcp-server/mcp",
      "headers": {
        "X-Daktela-Access-Token": "YOUR_ACCESS_TOKEN"
      }
    }
  }
}

Alternatively, configure globally in your Claude Code settings file (macOS / Linux: ~/.claude/settings.json; Windows: %USERPROFILE%\.claude\settings.json, which expands to C:\Users\<you>\.claude\settings.json):

{
  "mcpServers": {
    "daktela": {
      "type": "http",
      "url": "https://YOUR_DOMAIN/mcp-server/mcp",
      "headers": {
        "X-Daktela-Access-Token": "YOUR_ACCESS_TOKEN"
      }
    }
  }
}

Claude Desktop¶

Add the following to your Claude Desktop config file. The file location depends on your OS:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json (expands to C:\Users\<you>\AppData\Roaming\Claude\claude_desktop_config.json)

{
  "mcpServers": {
    "daktela": {
      "type": "http",
      "url": "https://YOUR_DOMAIN/mcp-server/mcp",
      "headers": {
        "X-Daktela-Access-Token": "YOUR_ACCESS_TOKEN"
      }
    }
  }
}

Tip

On Windows, the AppData folder is hidden in File Explorer by default. To open the Claude folder quickly, press Win+R, paste %APPDATA%\Claude, and press Enter. Alternatively, enable Hidden items under View → Show in File Explorer.

Other MCP clients¶

Any client that supports the MCP HTTP transport can connect using:

URL: https://YOUR_DOMAIN/mcp-server/mcp
Authentication: HTTP header X-Daktela-Access-Token: YOUR_ACCESS_TOKEN

Tip

You can find the setup guide directly in Daktela under Settings → System → Integrations → Daktela MCP Server → Setup guide.

Self-hosted (Advanced)¶

For custom or cloud deployments, you can run the MCP server yourself using the open-source PHP package.

GitHub Repository: Daktela/daktela-v6-php-mcp-server

Requirements¶

PHP 8.2 or higher
Composer (PHP package manager)
A Daktela instance with API read access
An API Access Token from your Daktela account

Installation¶

Clone the repository:

git clone https://github.com/Daktela/daktela-v6-php-mcp-server.git
cd daktela-v6-php-mcp-server

Install dependencies:
```
composer install
```

Configuration¶

The server is configured using environment variables. Create a .env file based on the provided example, or pass the variables directly when running the server.

Variable	Required	Default	Description
`DAKTELA_URL`	Yes	—	Your Daktela instance URL, e.g. `https://your-instance.daktela.com`
`DAKTELA_ACCESS_TOKEN`	Yes	—	API Access Token from your Daktela account
`CACHE_ENABLED`	No	`true`	Enable caching of reference data (queues, users, statuses, etc.)
`CACHE_TTL_SECONDS`	No	`3600`	Cache duration in seconds

Tip

You can generate an API Access Token in your Daktela instance under Manage → Users → Edit user → Access Tokens.

Deployment Options¶

The self-hosted server supports two transport modes: stdio (for local AI desktop apps) and HTTP (for remote/cloud deployments).

Claude Desktop — Docker¶

This is the recommended approach for self-hosted. Build the Docker image and configure Claude Desktop to use it.

Build the image:

docker build -f Dockerfile.prod -t daktela-v6-php-mcp-server .

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "daktela": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "DAKTELA_URL=https://your-instance.daktela.com",
        "-e", "DAKTELA_ACCESS_TOKEN=your-api-token",
        "daktela-v6-php-mcp-server"
      ]
    }
  }
}

Claude Desktop — Direct PHP¶

If you prefer to run PHP directly without Docker:

{
  "mcpServers": {
    "daktela": {
      "command": "php",
      "args": ["/path/to/daktela-v6-php-mcp-server/bin/server.php"],
      "env": {
        "DAKTELA_URL": "https://your-instance.daktela.com",
        "DAKTELA_ACCESS_TOKEN": "your-api-token"
      }
    }
  }
}

Docker — Standalone¶

Run the server as a standalone Docker container:

docker run -i --rm \
  -e DAKTELA_URL=https://your-instance.daktela.com \
  -e DAKTELA_ACCESS_TOKEN=your-api-token \
  daktela-v6-php-mcp-server

HTTP Server Mode (Cloud Deployment)¶

For remote deployments such as Google Cloud Run, the server operates in HTTP mode where clients pass credentials via headers:

docker run --rm -p 8080:8080 \
  -e DAKTELA_URL=https://your-instance.daktela.com \
  -e DAKTELA_ACCESS_TOKEN=your-api-token \
  daktela-v6-php-mcp-server php bin/http-server.php

Example cloud deployment with Google Cloud Run:

gcloud run deploy daktela-v6-php-mcp-server \
  --source . \
  --dockerfile Dockerfile.prod \
  --region europe-west1 \
  --allow-unauthenticated \
  --memory 1Gi

Warning

When deploying to the cloud with --allow-unauthenticated, ensure you implement appropriate access controls to protect your Daktela data.

Available Tools¶

The MCP server exposes 43 read-only tools organised into the following categories. All list tools support pagination, sorting, and contextual filtering.

Tickets¶

Tool	Description
`count_tickets`	Count tickets matching filter criteria
`get_ticket`	Get a specific ticket by ID
`get_ticket_detail`	Get detailed ticket information
`list_account_tickets`	List tickets for a specific account
`list_ticket_categories`	List available ticket categories
`list_tickets`	List tickets with filtering and pagination

Activities¶

Tool	Description
`count_activities`	Count activities matching filter criteria
`get_activity`	Get a specific activity by ID
`list_activities`	List activities with filtering and pagination

Calls¶

Tool	Description
`count_calls`	Count calls matching filter criteria
`get_call`	Get a specific call by ID
`get_call_transcript`	Get the transcript of a specific call
`list_call_transcripts`	List available call transcripts
`list_calls`	List calls with filtering and pagination

Emails¶

Tool	Description
`count_emails`	Count emails matching filter criteria
`get_email`	Get a specific email by ID
`list_emails`	List emails with filtering and pagination

Messaging¶

Covers webchat, SMS, Facebook Messenger, Instagram, WhatsApp, and Viber.

Tool	Description
`count_chats`	Count chat messages matching filter criteria
`get_chat`	Get a specific chat message by ID
`list_chats`	List chat messages with filtering and pagination

Contacts and CRM¶

Tool	Description
`count_accounts`	Count accounts matching filter criteria
`count_contacts`	Count contacts matching filter criteria
`count_crm_records`	Count CRM records matching filter criteria
`get_account`	Get a specific account by ID
`get_contact`	Get a specific contact by ID
`get_crm_record`	Get a specific CRM record by ID
`list_accounts`	List accounts with filtering and pagination
`list_contacts`	List contacts with filtering and pagination
`list_crm_records`	List CRM records with filtering and pagination

Campaigns¶

Tool	Description
`count_campaign_records`	Count campaign records matching filter criteria
`get_campaign_record`	Get a specific campaign record by ID
`list_campaign_records`	List campaign records with filtering and pagination
`list_campaign_types`	List available campaign types

Reference Data¶

Tool	Description
`list_groups`	List agent groups
`list_pauses`	List available pause types
`list_queues`	List queues
`list_statuses`	List ticket/activity statuses
`list_templates`	List message templates
`list_users`	List users

Real-time¶

Tool	Description
`list_realtime_sessions`	List current real-time agent sessions

Knowledge Base¶

Tool	Description
`list_article_folders`	List knowledge base folders
`list_articles`	List knowledge base articles
`get_article`	Get a specific knowledge base article

Built-in Prompts¶

The server includes four pre-built prompt templates for common analysis workflows. These prompts are available directly in your AI client when the MCP server is connected.

Prompt	Description
`email_quality_audit`	Audit recent emails for negative sentiment, unprofessional tone, and lost deals
`sales_pipeline_review`	Review deal health and identify at-risk opportunities
`call_quality_review`	Analyse calls for escalations, knowledge gaps, and quality issues
`daily_call_analysis`	Daily call review for churn risk and recurring issues

Usage Examples¶

Once the MCP server is connected to your AI client, you can ask questions like:

"Show me all open tickets from the last 7 days and summarise common issues."
"Audit the last 50 emails for negative sentiment and unprofessional tone."
"List all missed calls from today and identify patterns."
"Review the sales pipeline and flag deals that have been stalled for more than 2 weeks."
"Analyse call transcripts from this week and highlight any escalations."

The AI assistant will use the appropriate MCP tools to fetch data from your Daktela instance and provide structured analysis.

Best Practices¶

Token Security: Never share your API Access Token publicly. Use environment variables or secret management services to store credentials.
Caching: Keep caching enabled (default) to reduce API calls for reference data like queues, users, and statuses.
Access Control: Create a dedicated API user with minimal read-only permissions for the MCP server rather than using an admin token.
Cloud Deployments: Always implement authentication when exposing the HTTP server endpoint publicly.

Support¶

If you encounter bugs or have feature requests, please use the Issues section on the GitHub repository.