Amicus MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONTEXT_BUS_DIR | No | The directory where the context bus state is stored. Defaults to {CWD}/.ai if not set. |
Instructions
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.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| update_stateB | Update the context bus state with the current agent's information. Args: summary: A summary of what has been done so far next_steps: What needs to be done next active_files: List of files currently being worked on ask_user: Whether human input is required Returns: Success message |
| read_stateB | Read the current state from the context bus. Returns: The current state as a formatted string |
| toggle_trackingB | Enable or disable state tracking. Args: enabled: Whether tracking should be enabled Returns: Success message |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| catch_up | Get the current context bus state with headers to reset agent focus. This prompt is designed to help an agent "catch up" on the current state of the project by injecting the state with specific headers. Note: The "Ignore previous instructions" phrasing is intentional per the specification to help agents refocus. This assumes the state content is generated by trusted AI agents, not arbitrary user input. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: read_state retrieves current state, toggle_tracking controls tracking functionality, and update_state modifies state with agent information. There is no overlap in functionality between these three tools.
All tools follow a consistent verb_noun naming pattern (read_state, toggle_tracking, update_state) with perfect consistency. The naming convention is clear, predictable, and follows the same structure throughout.
With only 3 tools, this feels somewhat thin for a context management server. While the tools cover basic state operations, the limited count suggests potential gaps in functionality that agents might need for comprehensive context management.
The tools provide read, update, and tracking control for state management, but there are notable gaps. Missing operations include clearing/resetting state, managing state history, or handling multiple contexts. The surface covers basic needs but lacks comprehensive lifecycle management.