Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agloop-mcpshow me the current plan and list all pending tasks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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-mcpTools
Read Tools (10)
Tool | Description |
| Full AgLoop state: phase, tasks, iteration, compaction context |
| Single task details by ID |
| All tasks with optional status/dependency filter |
| Execution log entries with agent/task/limit filters |
| Current plan (YAML or Markdown) |
| Compaction recovery context |
| Full-text search through execution logs |
| Agent definition file (.agent.md) content |
| Topological-sort next task recommendation |
| All available agent names |
Write Tools (4)
Tool | Description |
| Update task status and result log |
| Append structured entry to execution log |
| Snapshot current state for recovery |
| 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/projectState 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 snapshotsRequirements
Python 3.11+
No additional dependencies beyond
mcp
License
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.