Click on "Deploy 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., "@a2a-bridge-mcp Find code review agents and delegate review of PR #42"
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 server for agent-to-agent communication -- capability discovery, task delegation, and result aggregation across MCP agents.
MCP connects agents to tools, but not to each other. This server adds a standardized agent-to-agent layer within the MCP protocol -- register agents, discover capabilities, delegate tasks, and broadcast work to multiple agents. Inspired by Google's A2A protocol.
npx a2a-bridge-mcpAdd to claude_desktop_config.json:
{
"mcpServers": {
"a2a-bridge": {
"command": "npx",
"args": ["a2a-bridge-mcp"]
}
}
}git clone https://github.com/mdfifty50-boop/a2a-bridge-mcp.git
cd a2a-bridge-mcp
npm install
node src/index.jsRelated MCP server: kitty-hive
Register an agent with capabilities for discovery by other agents.
Param | Type | Default | Description |
| string | required | Unique agent identifier |
| string[] | required | Capability strings (e.g. |
| string |
| Human-readable description |
| object |
| JSON schema for accepted input |
| object |
| JSON schema for produced output |
| string |
| Optional endpoint or transport hint |
Find agents matching a capability need with fuzzy text similarity scoring.
Param | Type | Default | Description |
| string | required | Capability to search for |
| number | 0.3 | Minimum similarity score (0-1) |
Returns scored matches sorted by relevance.
Delegate a task to a specific registered agent. Creates a tracked task with status lifecycle.
Param | Type | Default | Description |
| string | required | Delegating agent ID |
| string | required | Target agent ID |
| string | required | What the target should do |
| object |
| Input data for the task |
| number | 30000 | Timeout in milliseconds |
Returns a task_id for tracking.
Get status and result of a delegated task. Also used by executing agents to submit results.
Param | Type | Description |
| string | Task ID from delegate_task or broadcast_task |
| object | (Optional) Submit completion result |
| string | (Optional) Submit failure error |
Status lifecycle: pending -> running -> completed / failed.
Send a task to ALL agents matching a capability. Creates individual tracked tasks for each match.
Param | Type | Default | Description |
| string | required | Broadcasting agent ID |
| string | required | Capability to match |
| string | required | What matched agents should do |
| object |
| Input data |
| number | 0.3 | Minimum match score |
| number | 30000 | Timeout per agent |
Returns list of task IDs for aggregation via get_task_result.
Get an agent's full capability card with schemas, stats, and task history.
Param | Type | Description |
| string | Agent identifier |
Returns capabilities, input/output schemas, success rate, and task counts. Inspired by Google A2A agent cards.
List all registered agents, optionally filtered by capability.
Param | Type | Default | Description |
| string |
| Capability keyword to filter by (empty = all) |
URI | Description |
| All registered agents with capabilities and stats |
1. register_agent -- each agent registers at startup
2. discover_agents -- find who can handle a task
3. delegate_task -- send work to a specific agent
OR broadcast_task -- send work to all matching agents
4. get_task_result -- poll for completion or submit results
5. get_agent_card -- inspect an agent's full profile
6. list_agents -- overview of the agent networkAgent A (orchestrator):
1. register_agent(agent_id="orchestrator", capabilities=["planning", "coordination"])
2. discover_agents(capability_needed="code review")
-> finds Agent B (score: 0.95)
3. delegate_task(from="orchestrator", to="agent-b", task="Review PR #42")
-> task_id: "task_1234"
4. get_task_result(task_id="task_1234")
-> status: "completed", result: { approved: true, comments: [...] }
Agent B (worker):
1. register_agent(agent_id="agent-b", capabilities=["code-review", "linting"])
2. (receives task via external notification or polling)
3. get_task_result(task_id="task_1234", submit_result={ approved: true })MIT
This server cannot be deployed
MCP Server for an Agent Task Marketplace
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
Hosted MCP server for task-first delegation to remote workstations and workers.
Agent communication platform for agent to agent messaging via MCP. Messages, channels, skills.
