Channels MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZABBIX_URL | Yes | Zabbix URL, e.g., https://zabbix.sophosapps.com | |
| SSH_USERNAME | Yes | Your SSH username for channel servers (e.g., pavanbhatt) | |
| SSH_AUTH_SOCK | No | Auto-detected on macOS. Only set manually if auto-detection fails. | |
| ATLASSIAN_HOST | Yes | Atlassian host, e.g., https://sophos.atlassian.net | |
| SSH_PASSPHRASE | No | Passphrase for the private key (if using SSH_PRIVATE_KEY_PATH) | |
| ATLASSIAN_EMAIL | Yes | Your Sophos email (e.g., your.name@sophos.com) | |
| ZABBIX_API_TOKEN | Yes | Zabbix API token from User Settings → API Tokens | |
| ATLASSIAN_API_TOKEN | Yes | Atlassian API token from https://id.atlassian.com/manage-profile/security/api-tokens | |
| SSH_PRIVATE_KEY_PATH | No | Alternative to SSH agent: path to your key (e.g., ~/.ssh/id_rsa) |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| investigate_serverA | Connect to a channel server, check all status JSONs (chirp, chmedic, chcheck, large_file_alert), and return categorized findings. SAFE: read-only. |
| check_channel_logB | Read the latest entries from a specific channel's chan.log. SAFE: read-only. |
| check_antispam_publishingA | Check if there is an active incident for antispam-publishing.labs.sophos (most common root cause for multiple channel alerts). |
| get_server_problemsC | Get all active Zabbix problems/alerts for a channel server. |
| acknowledge_alertsC | Acknowledge Zabbix alerts with a message and ticket reference. |
| create_linfra_ticketC | Create a LINFRA Jira ticket with investigation findings. |
| add_ticket_commentC | Add a comment to an existing Jira ticket. |
| search_related_incidentsC | Search Jira for related past incidents by keyword. |
| check_large_filesC | Check for large files on a channel server that may trigger large_file_alert. SAFE: read-only. |
| list_channel_serversA | List all channel servers with their roles, Zabbix IDs, and priorities. |
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 10 tools
Each tool targets a distinct action or resource (e.g., acknowledge_alerts vs. get_server_problems) with clear boundaries, so an agent can reliably select the correct tool.
All tool names follow a consistent verb_noun pattern using lowercase and underscores (e.g., check_channel_log, list_channel_servers) with no mixing of conventions.
10 tools are well-scoped for the channel server management domain, covering monitoring, alerting, and Jira integration without being overwhelming.
Core workflows (listing, investigating, acknowledging alerts, creating tickets) are present, but missing operations like closing incidents or updating alerts beyond acknowledgment create minor gaps.