Skip to main content
Glama
kagan-sh

Kagan - AI Orchestration Layer

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
task_get

Get a task by ID.

The response includes a board_hint field summarizing other active tasks in the same project so the agent can decide whether to call task_list() for coordination.

task_list-
task_create-
task_update-
task_add_note-
task_search-
task_events-
tasks_wait-
task_counts-
task_delete-
task_batch_create

Create multiple tasks at once.

Each entry must have a title key and may include description, priority, base_branch, acceptance_criteria, and agent_backend. Returns the list of created tasks.

run_start-
run_summary-
run_cancel-
run_exists

Check whether a task has an interactive session.

run_create

Start an interactive session for a task.

run_get

Get the latest task and session status for a task.

run_kill

Cancel a task run by task id.

run_detach

Detach from an interactive session and update task state.

project_list-
project_set_active-
project_add_repo-
project_set_repo_default_branch-
repo_list-
project_create-
project_delete-
review_approve

Approve a review-ready task.

review_reject

Reject a review-ready task with feedback.

review_merge

Merge an approved task into its base branch.

review_rebase

Rebase a task branch onto its current base branch.

review_conflicts-
review_continue_rebase-
review_abort_rebase-
review_set_criterion_verdict

Report the AI review verdict for a single acceptance criterion.

Call this once per criterion during review, BEFORE calling review_approve or review_reject. verdict must be 'PASS' or 'FAIL'. reason is a one-line justification.

review_clear_verdicts

Clear all AI review verdicts for a task. Call before starting a new review.

settings_get-
audit_list-
settings_set-
persona_preset_audit-
persona_preset_import-
persona_preset_export-
persona_preset_whitelist_list-
persona_preset_whitelist_add-
persona_preset_whitelist_remove-
plugins_sync

Sync external items from a plugin source into the active project.

Imports issues from the specified repository as kagan tasks. Labels like priority:high and kagan:auto on GitHub issues auto-map to task properties. Operation is idempotent — previously synced issues are skipped.

Args: plugin: Plugin to sync (e.g. "github"). Use plugins_preflight to list available. repo: Repository in owner/repo format (e.g. "octocat/hello-world"). state: Issue state filter — "open", "closed", or "all". import_label: Only sync issues with this label.

plugins_preflight

Check if a plugin's external dependencies are satisfied.

Returns pass/warn/fail checks for the requested plugin (or all plugins). For github: verifies gh CLI is installed and authenticated.

Args: plugin: Plugin to check. If omitted, checks all installed plugins.

Prompts

Interactive templates invoked by user choice

NameDescription
review_taskReturn a structured code-review prompt for the given task.
plan_tasks_from_descriptionReturn a task-breakdown prompt for the given feature description.
diagnose_failureReturn a diagnostic prompt for a failed task.
security_audit_persona_repo

Resources

Contextual data attached and managed by the client

NameDescription
pingHealth check
settings_snapshotSettings snapshot
projects_listProject list
runtime_infoActive sessions and agent processes

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kagan-sh/kagan'

If you have feedback or need assistance with the MCP directory API, please join our Discord server