AE Test Bridge MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_mock_bridgeA | Start a fake After Effects bridge listener speaking the real wire protocol, for testing bridge client code without real After Effects. Fails if one is already running. |
| stop_mock_bridgeB | Stop the currently running mock bridge. |
| queue_responseA | Register a canned response: any incoming request whose |
| set_default_responseA | Set the response returned when no queue_response rule matches an incoming request. |
| get_received_requestsA | Return every request the mock bridge has received so far, in order -- for asserting what a client under test actually sent. |
| clear_received_requestsA | Clear the recorded request history without stopping the bridge or its response rules. |
| clear_rulesA | Remove all queue_response rules without stopping the bridge or clearing received-request history. The default response (if set) is unaffected. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a clearly distinct role: lifecycle management (start/stop), response configuration (queue vs default), and request inspection/reset. The relationship between queue_response and set_default_response is well-defined, so there is no real ambiguity.
All tools follow a consistent snake_case verb_noun pattern: start_, stop_, queue_, set_, get_, clear_. The naming style is uniform and predictable across the entire set.
Seven tools is well-scoped for a mock bridge server. Each tool covers a necessary capability—lifecycle, response control, request inspection, and state reset—without redundancy or bloat.
The surface covers the full testing workflow: start/stop the bridge, configure responses, inspect received requests, and reset state. Minor extras like checking bridge status or removing individual rules are absent but not critical to the core purpose.