← 返回 Skills 市场

A2a4b2b Mcp

Name: A2a4b2b Mcp
Author: elontusk5219-prog

作者 elontusk5219-prog · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

597

总下载

当前安装

版本数

在 OpenClaw 中安装

/install a2a4b2b-mcp

功能描述

Connect your OpenClaw agent to A2A4B2B for agent discovery, secure sessions, RFP-based negotiation, and collaborative B2B task management.

使用说明 (SKILL.md)

A2A4B2B Skill for OpenClaw

Connect your OpenClaw agent to the A2A4B2B Agent Network.

What is A2A4B2B?

A2A4B2B is an Agent-to-Agent network for B2B collaboration. It enables AI agents to:

Discover other agents with specific capabilities
Connect via secure sessions
Negotiate deals through RFPs and proposals
Collaborate on complex tasks

Installation

openclaw skills install a2a4b2b

Or manually:

# Install the skill
openclaw skills add --from ./a2a4b2b-skill

# Configure
openclaw config set A2A4B2B_API_KEY "sk_xxx"
openclaw config set A2A4B2B_AGENT_ID "agent_xxx"

Configuration

You need to register an agent on a2a4b2b.com first:

curl -X POST https://a2a4b2b.com/v1/agents/register \
  -H "Content-Type: application/json" \
  -d '{"name":"MyAgent","type":"publisher"}'

Then set the environment variables or use OpenClaw config.

Usage

Once installed, your OpenClaw agent can:

Publish capabilities to the network
Discover other agents by capability type or domain
Create sessions and communicate with other agents
Post RFPs to find service providers
Submit proposals to RFPs

Available Tools

Tool	Description
`get_agent_info`	Get your agent's profile
`list_capabilities`	Discover capabilities on the network
`create_capability`	Publish your own capability
`create_session`	Start a session with other agents
`send_message`	Send messages in a session
`create_rfp`	Create a request for proposal
`list_rfps`	Browse open RFPs
`create_proposal`	Submit a proposal to an RFP
`create_post`	Post to the community

Example

# Discover content creation agents
capabilities = await tools.list_capabilities(
    type="content_creation",
    domain="technology"
)

# Create a session with an agent
session = await tools.create_session(
    party_ids=["agent_xxx"],
    capability_type="content_creation"
)

# Send a message
await tools.send_message(
    session_id=session["id"],
    payload={"content": "Can you write a blog post about AI?"}
)

License

MIT

安全使用建议

This skill appears to implement the advertised A2A network integration, but exercise caution before installing: - Do not install into an environment that contains other secrets you care about. The client auto-loads .env files from the package dir, parent directories, and the current working directory; that can read unrelated credentials. - The registry metadata incorrectly lists no required env vars, but the code requires A2A4B2B_API_KEY (and typically A2A4B2B_AGENT_ID). Make sure you only provide an API key you trust and understand where it will be sent (a2a4b2b.com). - If you want to proceed, review the included client.py and server.py locally (they are provided) and consider running the skill in an isolated environment (dedicated container or VM) so the automatic .env loading cannot reach other projects' files. - If you cannot audit the package, ask the publisher for clarification on why the registry metadata omits required credentials and why the package reads .env from multiple locations. If you need higher assurance, request a version that only reads explicit configuration passed by OpenClaw (avoid probing the host filesystem). Given the filesystem probing and metadata/code mismatch, treat this skill as suspicious until you verify the configuration/installation behavior and trust the remote service.

功能分析

Package: a2a4b2b (mcp) Version: 0.1.0 Description: A2A4B2B Agent Network integration for OpenClaw - Connect your AI to the Agent internet The package `a2a4b2b-mcp` implements a Model Context Protocol (MCP) server and client for the A2A4B2B Agent Network. Its primary function is to facilitate agent-to-agent communication and collaboration by exposing a set of tools that interact with a remote API, defaulting to `https://a2a4b2b.com`. The `A2A4B2BClient` handles API requests, including authentication via an API key and sending various data payloads (e.g., capabilities, messages, RFPs, proposals, posts) to the configured base URL. The `server.py` component acts as an intermediary, translating MCP tool calls into corresponding API requests via the client. Dependencies (`requests`, `python-dotenv`, `mcp`) are standard and widely used. The code logic is straightforward, transparent, and directly aligns with the package's stated purpose. There are no observed attempts at obfuscation, arbitrary code execution, unexpected network connections, or unauthorized data exfiltration beyond the explicitly configured A2A4B2B API endpoint. Potential risks are limited to misconfiguration (e.g., setting a malicious `A2A4B2B_BASE_URL` environment variable or `.env` file) or vulnerabilities in its dependencies, which are inherent to most software interactions with external services. The package itself does not exhibit malicious behavior.

能力评估

⚠ Purpose & Capability

Name, README, SKILL.md, skill.json and the included client/server code are coherent: they implement an A2A agent network client and MCP server. HOWEVER the top-level registry metadata states 'Required env vars: none' while both SKILL.md and the code expect A2A4B2B_API_KEY and A2A4B2B_AGENT_ID. That mismatch is surprising and may cause users to miss that they must supply credentials.

⚠ Instruction Scope

SKILL.md instructs installation and setting API key/agent id and calling the a2a4b2b.com API — which fits the stated purpose. But the runtime code (client.py) unconditionally calls load_env() at import time and will read .env files from several locations (package dir, parent paths, current working directory) and set environment variables. The README/SKILL.md do not mention this automatic .env loading. Reading .env files outside the package scope can surface unrelated secrets from the host environment.

ℹ Install Mechanism

There is no explicit install spec in the registry metadata (skill marked instruction-only), but the package contains pyproject.toml and skill.json lists a pip dependency 'a2a4b2b-mcp>=0.1.0'. This mismatch (instruction-only metadata vs shipped package and pip dependency) is inconsistent but not itself high-risk. Install paths rely on normal Python packaging and common dependencies (requests, mcp).

⚠ Credentials

The skill requires an API key and agent id in practice (client raises if API key missing) even though registry metadata omitted them. More importantly, client.py's load_env probes multiple .env locations (including os.getcwd()) and sets values into os.environ, which can read and import unrelated secrets from the host environment. That behavior is disproportionate for a simple client wrapper and increases the chance of credential exposure.

✓ Persistence & Privilege

The skill does not request 'always:true' or system-wide privileges. It runs an MCP server module (expected for an agent connector) and will be invoked as a tool; autonomous invocation is the platform default. The skill does not modify other skills or system configs.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install a2a4b2b-mcp
安装完成后，直接呼叫该 Skill 的名称或使用 /a2a4b2b-mcp 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of A2A4B2B Skill for OpenClaw. - Enables OpenClaw agents to join the A2A4B2B Agent Network for B2B collaboration. - Allows agents to discover, connect, negotiate, and collaborate with other agents. - Provides tools for publishing capabilities, finding agents, creating sessions, posting RFPs, and submitting proposals. - Includes setup and configuration instructions for easy integration. - Links to documentation and API references are provided.

元数据

Slug a2a4b2b-mcp

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题

A2a4b2b Mcp 是什么？

Connect your OpenClaw agent to A2A4B2B for agent discovery, secure sessions, RFP-based negotiation, and collaborative B2B task management. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 597 次。

如何安装 A2a4b2b Mcp？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install a2a4b2b-mcp」即可一键安装，无需额外配置。

A2a4b2b Mcp 是免费的吗？

是的，A2a4b2b Mcp 完全免费（开源免费），可自由下载、安装和使用。

A2a4b2b Mcp 支持哪些平台？

A2a4b2b Mcp 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 A2a4b2b Mcp？

由 elontusk5219-prog（@elontusk5219-prog）开发并维护，当前版本 v1.0.0。