What it does
The server gives MCP clients read-only access to AgentLoopKit data: tasks, policies, reports, handoffs and status. It does not change this data, so it only lets a client view what AgentLoopKit holds.
It would be used by someone who works with AgentLoopKit and wants an AI assistant to check task progress, review policies or reports, or look at handoffs and status from within an MCP-compatible client.
The publisher's description does not say how the server is installed or configured. The source repository is on GitHub under abhiyoheswaran1/AgentLoopKit.
Limitations and requirements
The publisher's description states the server is read-only. It does not list other requirements.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.abhiyoheswaran1/agentloopkit
Read-only MCP server for AgentLoopKit tasks, policies, reports, handoffs, and status.
v1.2.0As shown on registry.modelcontextprotocol.io when we last read it