mcp-context-loop
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., "@mcp-context-loopBookmark this context and show me the next iteration brief."
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.
mcp-context-loop
MCP stdio server for CONTEXT LOOP navigation: goto and loop_start_marker.
These tools do not implement context-window mutation themselves. They call
methods angela exposes on a unix-socket host (ANGELA_HOST_SOCK):
HTTP | angela method |
|
|
|
|
Angela starts that host for every harness and passes the socket path into this
server's env when the context-loop MCP preset is connected.
Not enabled by default
New angela agents only get file-io / term-local (or whatever the agent
coffee lists). This server is opt-in:
Add the preset to the agent:
mcp: [
'file-io'
'term-local'
'context-loop'
]Allowlist the tools (they are not on
DEFAULT_LUCY_ALLOWLIST):
goto
loop_start_marker(Registered without a server prefix so the model still sees goto /
loop_start_marker, matching the playbook text.)
Related MCP server: Hermes Kernel MCP Server
Tools
Tool | Purpose |
| Bookmark the previous context item; return the per-iteration playbook |
| Hide context after that bookmark (keep the goto nav suffix); return the next-iteration brief |
Env
ANGELA_HOST_SOCK— unix socket path (set by angela). Required for tool calls.
Run (usually via angela)
ANGELA_HOST_SOCK=/tmp/angela-host-….sock bun /workspace/mcp-context-loop/server.mjsThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Stop re-explaining yourself to Agents. Give it the right context, right when needed.
Connect AI agents to Replynodes over the Model Context Protocol.
Git-backed platform for skills, tools, and context for AI agents
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to manage a homelab by providing tools for Docker, Ollama, and system monitoring through the Model Context Protocol.MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to discover and invoke kernel tools and capabilities via the Model Context Protocol (MCP), supporting stdio, SSE, and Streamable HTTP transports for bidirectional communication.-
- AlicenseNot gradedqualityAmaintenanceGives Notion Custom Agents real file tools and a real terminal over the Model Context Protocol, enabling them to read, edit, and run commands directly on the user's machine.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables registering custom agent tools via a minimal JSON-RPC over stdio implementation, with zero external dependencies, to expose them to AI agents like Claude, Cursor, and Gemini.MIT