mcp-a2a-bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HERMES_HOME | No | Used to find $HERMES_HOME/a2a_audit.jsonl when no override is set | |
| A2A_BRIDGE_CONFIG | No | Absolute path to the agents JSON registry | |
| A2A_BRIDGE_DASHBOARD | No | Set to 1 to persist this bridge process's activity | 0 |
| A2A_BRIDGE_ACTIVITY_DB | No | Shared SQLite activity database | ~/.config/a2a-bridge/activity.sqlite3 |
| A2A_BRIDGE_HERMES_AUDIT | No | Read-only override for Hermes' a2a_audit.jsonl | |
| A2A_BRIDGE_DASHBOARD_HOST | No | Dashboard bind address | 127.0.0.1 |
| A2A_BRIDGE_DASHBOARD_PORT | No | Dashboard port | 9100 |
| A2A_BRIDGE_ACTIVITY_SOURCE | No | Source label for activity written by compatible processes | remote |
| A2A_BRIDGE_DASHBOARD_TOKEN | No | Optional bearer token that protects the dashboard and API |
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| a2a_list_agentsA | List configured A2A agents with their skills and reachability. Set refresh=true to re-fetch agent cards that were previously cached. |
| a2a_send_messageA | Send a message to an A2A agent and return its reply. Set provider to "litellm-auto" or "github" when the target agent supports provider selection. The selected provider is carried in the message for the local Copilot A2A agent; other agents may ignore it. Pass task_id to continue an existing task, for example to answer an agent that returned state="input_required". If the agent is still working when timeout_s elapses, this returns done=false with a task_id to poll rather than blocking. |
| a2a_get_taskA | Get the current state and output of a previously started A2A task. |
| a2a_cancel_taskB | Cancel a running A2A task and return its final state. |
| a2a_add_agentA | Register a new A2A agent by its base URL. The agent card is fetched first, so an unreachable URL is rejected instead of being saved. With persist=true the agent is written to the shared registry file and stays available in future sessions. |
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 5 tools
Each tool has a distinct purpose: listing agents, sending messages, getting task state, cancelling tasks, and adding agents. No overlap or ambiguity between them.
All tools follow a consistent 'a2a_' prefix followed by a verb_noun pattern (list_agents, send_message, get_task, cancel_task, add_agent). Naming is predictable and uniform.
Five tools is well-scoped for an A2A bridge: listing, messaging, task management, and agent registration cover the core functionality without being excessive or sparse.
The tool surface covers the essential operations for an A2A bridge. A remove_agent or update_agent tool is missing, but it's not critical; the set supports the primary workflows adequately.