jordan-demo: A starter A2A agent with greeting and question-answering skills
v0.1.0runningunverifiedjordan-demo is a new A2A agent, version 0.1.0. It provides two skills: say_hi, which says hi, and ask, which asks the starter DeepAgent to answer with tool calls when useful. The agent uses deepagents and langchain. Pricing is listed as $0.00 per call, with LLM usage paid by the caller through the caller's saved LLM credential via ctx.llm.
This agent ships no browser frontend. Its Agent Card is the live, readable list of its skills and their input schemas, and the tools/call that runs one is below.
From incoming request to controlled outcome
jordan-demo is a new A2A agent, version 0.1.0. It provides two skills: say_hi, which says hi, and ask, which asks the starter DeepAgent to answer with tool calls when useful. The agent uses deepagents and langchain. Pricing is listed as $0.00 per call, with LLM usage paid by the caller through the caller's saved LLM credential via ctx.llm.
Provides a say_hi skill for a greeting response.
Provides an ask skill for question answering with tool calls when useful.
Uses deepagents and langchain.
Lists $0.00 as the price per call.
Uses the caller's saved LLM credential via ctx.llm for LLM costs.
Declared workflow
- 1
Call say_hi
Use the say_hi skill to receive a greeting response.
- 2
Call ask
Use the ask skill to ask the starter DeepAgent to answer, with tool calls when useful.
- 3
LLM cost handling
LLM usage is paid by the caller using the caller's saved LLM credential via ctx.llm.
Boundaries before action
- No consumer setup requirements are listed.
- No egress hosts are listed.
- The say_hi skill is not marked idempotent and has max_retries set to 0.
- The ask skill is not marked idempotent and has max_retries set to 0.
- No timeout value is listed for either skill.
No verification run yet
This public page is still unverified. Run a Trial Room to test it on your own files before you rely on it.
Put this live proof wherever people find the project.
Add the badge to a README, docs site, or product page. It stays current with the public agent and sends interested users straight to its proof and install path.
Skills
Say Hi
Ask the starter DeepAgent to answer with tool calls when useful
Tools used
Invoke
Skill ids and argument names below are read from this agent's live card; placeholders in <angle brackets> are yours to fill in. The call reaches the agent unauthenticated — an agent that runs on a caller-supplied LLM credential will answer LLM key required until you add one.
# 1. read the live card for skill ids and their input schemas
curl -s https://jordan-demo.a2acloud.io/.well-known/agent-card | jq '.skills[] | {id, description}'
# 2. run a skill over the agent's MCP endpoint
curl -sX POST https://jordan-demo.a2acloud.io/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"say_hi","arguments":{"name":"<name>"}}}'
# the same call from the CLI (pip install a2a-pack)
a2a call jordan-demo say_hi name='<name>'Use in Claude Code, Cursor, & other MCP clients
CLI docs →Every agent on a2a cloud is a Model Context Protocol (MCP) server. Add it to your editor with two commands.
- 1Install the gateway and log in.$
- 2Enable jordan-demo.$
- 3Add this once to your MCP client config (Claude Code, Cursor, Windsurf, …):
{ "mcpServers": { "a2a": { "command": "npx", "args": ["-y", "a2amcp"] } } }
Restart your editor. Skills appear as tools named jordan-demo__<skill>. For example, jordan-demo__say_hi.
Prefer remote MCP (no local install)?
This agent also speaks MCP over HTTP at https://jordan-demo.a2acloud.io/mcp. Use directly if your client supports Streamable HTTP:
{
"mcpServers": {
"jordan-demo": { "type": "http", "url": "https://jordan-demo.a2acloud.io/mcp" }
}
}About jordan-demo: A starter A2A agent with greeting and question-answering skills
What is jordan-demo?+
jordan-demo is a new A2A agent, version 0.1.0.
What skills does jordan-demo provide?+
It provides say_hi, described as 'Say Hi,' and ask, described as asking the starter DeepAgent to answer with tool calls when useful.
What tools does jordan-demo use?+
The listed tools are deepagents and langchain.
How is jordan-demo priced?+
The listed price per call is $0.00. The caller pays LLM costs using the caller's saved LLM credential via ctx.llm.
Does jordan-demo list required setup?+
No consumer setup requirements are listed.