Schema | Agent Communication MCP Server

Agent Communication MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`AGENT_COMM_DIR`	No	Where to store task communications	./comm
`AGENT_COMM_LOG_DIR`	No	Where to store operation logs	./comm/.logs
`AGENT_COMM_ARCHIVE_DIR`	No	Where to store completed tasks	./comm/.archive
`AGENT_COMM_DISABLE_ARCHIVE`	No	Turn off archiving completely	false

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Functions exposed to the LLM to take actions

Name	Description
check_tasksC	Check for tasks assigned to an agent
read_taskA	Read a task file by type (init, plan, done, error)
write_taskC	Write a task progress file
create_taskA	Unified task creation tool with duplicate prevention - replaces delegate_task and init_task
list_agentsA	List all agents with task counts and statistics
archive_tasksB	Archive tasks to clean up communication directory (clear comms)
restore_tasksC	Restore tasks from archive
get_task_contextA	Get pure task context without file paths - for current or specified task
submit_planB	Submit implementation plan content - handles file creation internally
report_progressC	Report progress updates on plan steps - no file operations exposed
mark_completeB	Mark task as complete or error with intelligent reconciliation for unchecked plan items
archive_completed_tasksC	Archive all completed tasks - batch cleanup operation
get_full_lifecycleB	Get complete lifecycle visibility for a task - diagnostic tool for comprehensive task journey
track_task_progressC	Track real-time task progress - diagnostic tool for progress monitoring
get_server_infoA	Get comprehensive server information including version, capabilities, and runtime status
pingA	Health check tool that returns server status and timestamp
sync_todo_checkboxesB	Sync TodoWrite updates to PLAN.md checkboxes - TodoWrite integration for automatic checkbox updates
protocol_configB	Manage protocol injection configuration for task and plan templates

Interactive templates invoked by user choice

Name	Description
`task-workflow-guide`	Complete guide for task management workflow with context-aware instructions
`agent-validation-requirements`	Agent ownership validation requirements and best practices
`flexible-task-operations`	Guide for working with multiple tasks in flexible order
`troubleshooting-common-errors`	Solutions for common errors and issues in agent communication
`protocol-compliance-checklist`	Verification checklist for MCP protocol compliance

Contextual data attached and managed by the client

Name	Description
`Server Information`	Complete server information including version, uptime, and system details
`Server Version`	Current server version number
`Server Capabilities`	Server capabilities and supported MCP features
`Server Statistics`	Runtime statistics and performance metrics
`Server Configuration`	Current server configuration (sanitized)
`Server Information`	Complete server information and metadata
`Server Version`	Current server version
`Server Capabilities`	Server capabilities and supported features

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jerfowler/agent-comm-mcp-server'

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