README.md
MCP server providing 14 agent introspection tools for AgLoop
agloop-mcp
MCP server providing 14 agent introspection tools for AgLoop — the VS Code Copilot custom agent framework.
Quick Start
Add to your .vscode/mcp.json:
For claude desktop or cli users use
mcpserversinstead ofservers
{
"servers": {
"agloop": {
"command": "uvx",
"args": ["agloop-mcp"]
}
}
}
Or run directly:
uvx agloop-mcp
Tools
Read Tools (10)
| Tool | Description |
|---|---|
agloop_get_state |
Full AgLoop state: phase, tasks, iteration, compaction context |
agloop_get_task |
Single task details by ID |
agloop_list_tasks |
All tasks with optional status/dependency filter |
agloop_get_logs |
Execution log entries with agent/task/limit filters |
agloop_get_plan |
Current plan (YAML or Markdown) |
agloop_get_compaction_context |
Compaction recovery context |
agloop_search_logs |
Full-text search through execution logs |
agloop_get_agent_info |
Agent definition file (.agent.md) content |
agloop_get_next_task |
Topological-sort next task recommendation |
agloop_list_agents |
All available agent names |
Write Tools (4)
| Tool | Description |
|---|---|
agloop_update_task |
Update task status and result log |
agloop_append_log |
Append structured entry to execution log |
agloop_create_checkpoint |
Snapshot current state for recovery |
agloop_set_phase |
Transition to a new phase |
Configuration
The server uses the current working directory as the workspace root. Override with:
uvx agloop-mcp --workspace /path/to/project
State Files
The server reads/writes from .agloop/ in the workspace root:
.agloop/
├── state.json # Phase, tasks, iteration
├── log.json # Execution log (JSON Lines)
├── plan.yaml # Current plan
└── checkpoints/ # State snapshots
Requirements
- Python 3.11+
- No additional dependencies beyond
mcp
License
MIT
Tools (14)
agloop_get_stateReturns full AgLoop state including phase, tasks, iteration, and compaction context.agloop_get_taskRetrieves details for a single task by ID.agloop_list_tasksLists all tasks with optional status or dependency filters.agloop_get_logsRetrieves execution log entries with filters for agent, task, or limit.agloop_get_planReturns the current plan in YAML or Markdown format.agloop_get_compaction_contextRetrieves the compaction recovery context.agloop_search_logsPerforms full-text search through execution logs.agloop_get_agent_infoRetrieves content from the agent definition file (.agent.md).agloop_get_next_taskProvides a topological-sort recommendation for the next task.agloop_list_agentsLists all available agent names.agloop_update_taskUpdates task status and result log.agloop_append_logAppends a structured entry to the execution log.agloop_create_checkpointSnapshots the current state for recovery.agloop_set_phaseTransitions the agent to a new phase.Environment Variables
--workspacePath to the project workspace root (defaults to current directory)Configuration
claude_desktop_config.json
{"servers": {"agloop": {"command": "uvx", "args": ["agloop-mcp"]}}}Try it
→What is the current phase of my AgLoop agent and what tasks are pending?
→Search the execution logs for any errors related to the data processing task.
→Show me the current plan for the agent and suggest the next task to execute.
→Create a checkpoint of the current agent state for recovery purposes.
→List all available agents and get the definition for the primary agent.