A2a Bridge MCP server

by mdfifty50-boop·io.github.mdfifty50-boop/a2a-bridge·v0.1.1·1 stars

No reviews yet

Agent-to-agent communication bridge for multi-agent systems

B78/100grade B

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

B78/100

full report

Adoption

New

1 stars37 downloads/wk

Reviews

Write one

Nobody has reviewed A2a Bridge yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

A2a Bridge tools (8, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

broadcast_taskwrite action
Send a task to ALL agents matching a capability. Creates individual tasks for each match for aggregation.
delegate_task
Delegate a task to a specific registered agent. Creates a tracked task with status lifecycle (pending -> running -> completed/failed).
discover_agents
Find registered agents matching a capability need. Returns scored results with fuzzy text matching.
get_agent_card
Get an agent's full capability card — capabilities, schemas, stats. Inspired by Google A2A agent cards.
get_task_result
Get status/result of a delegated task. Executing agents call this with submit_result or submit_error to report completion.
health_check
Returns server health, uptime, version, and call stats
list_agents
List all registered agents. Optionally filter by a capability keyword.
register_agent
Register an agent with its capabilities, input/output schemas for discovery by other agents.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings

Code scan9 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 156 days ago8/15
Maintainer identityregistry namespace matches repository owner6/10

Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How A2a Bridge compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 78/100; higher than 57% of 4,460 AI and agents servers
Tools: 8; the typical AI and agents server has 6
Tools that change things: 13%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 1; more than 50% of 2,711 AI and agents servers
Downloads a week: 37; more than 28% of 1,538 AI and agents servers with a package

What its tools let an agent do: 6 read · 1 create · 1 send or post

Install A2a Bridge in Claude Code, Cursor or VS Code

Runs npx -y a2a-bridge-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add a2a-bridge -- npx -y a2a-bridge-mcp

Add to Cursor

What the publisher says

From the A2a Bridge repository's README, as published. We do not edit it. Read it on GitHub

a2a-bridge-mcp

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.

Install

npx a2a-bridge-mcp

Claude Desktop

Add to claudedesktopconfig.json:

{
  "mcpServers": {
    "a2a-bridge": {
      "command": "npx",
      "args": ["a2a-bridge-mcp"]
    }
  }
}

From source

git clone https://github.com/mdfifty50-boop/a2a-bridge-mcp.git
cd a2a-bridge-mcp
npm install
node src/index.js

Tools

register_agent

discover_agents

Find agents matching a capability need with fuzzy text similarity scoring.

Returns scored matches sorted by relevance.

delegate_task

Delegate a task to a specific registered agent. Creates a tracked task with status lifecycle.

Returns a task_id for tracking.

gettaskresult

Get status and result of a delegated task. Also used by executing agents to submit results.

Status lifecycle: pending -> running -> completed / failed.

broadcast_task

Send a task to ALL agents matching a capability. Creates individual tracked tasks for each match.

Returns list of task IDs for aggregation via gettaskresult.

getagentcard

Get an agent's full capability card with schemas, stats, and task history.

Returns capabilities, input/output schemas, success rate, and task counts. Inspired by Google A2A agent cards.

list_agents

List all registered agents, optionally filtered by capability.

Resources

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

A2a Bridge: common questions

Is A2a Bridge MCP server safe?: Mostly: it is graded B (78/100). Read the A2a Bridge safety report
How do I install A2a Bridge?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does A2a Bridge need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is A2a Bridge maintained?: The last commit was 194 days ago (2026-04-24). The latest release is v0.1.1.
What can I use instead of A2a Bridge?: Servers from other publishers that do the same job: PaperBanana MCP server, Roast My Design System MCP server and three.ws Brain MCP server.
How does A2a Bridge compare with other AI and agents MCP servers?: safety score 78/100 (higher than 57% of 4,460 AI and agents servers); tools 8 (the typical AI and agents server has 6); tools that change things 13% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to A2a Bridge

Same job from other publishers: the closest match first, then the best rated.

PaperBanana
Generate academic diagrams and statistical plots from text using multi-agent AI.
not reviewed
Established
A
Roast My Design System
Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.
not reviewed
Established
A
three.ws Brain
List LLM providers and run chat completions through the three.ws multi-provider router.
not reviewed
Established
B
Roast My Design System
Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.
not reviewed
Established
A
NVIDIA Elements
NVIDIA Elements UI design system and agent tools for AI/ML, robotics, and autonomous vehicles.
not reviewed
Established
A