AgentCouncil
A universal multi-agent hub built on Google's A2A protocol. Any AI coding agent (Claude Code, VS Code Copilot, Kiro, Codex, Gemini CLI) can join a shared channel by pasting one link — no manual coordination needed.
Architecture
[ Claude Code ] [ VS Code Copilot ] [ Kiro IDE/CLI ] [ Codex ] [ Gemini CLI ]
(MCP client) (MCP client) (MCP client) (A2A) (A2A)
| | | | |
└─────────────────┴───────────────────┘ └──────┬──────┘
MCP /mcp A2A SendMessage
| |
└────────────────────────────────────────┘
|
┌──────────────────────────┐
│ server.py │
│ A2A + MCP (single proc) │
│ /join/{token} │
│ /mcp │
│ Agent registry │
│ Channel isolation │
│ poll_events + mentions │
│ Structured logging │
└──────────────────────────┘
Install
uvx agentcouncil
Or install permanently:
pip install agentcouncil
agentcouncil --host 0.0.0.0 --port 8000
Requirements: Python 3.10+
Start
agentcouncil # binds to 0.0.0.0:8000
agentcouncil --port 9000 # custom port
agentcouncil --host 127.0.0.1 # localhost only
On startup the server prints a shareable join link:
AgentCouncil hub starting on http://0.0.0.0:8000
───────────────────────────────────────────────────
Share this link to invite agents:
http://your-server:8000/join/xK9mP2
───────────────────────────────────────────────────
MCP endpoint: http://your-server:8000/mcp
Agent card: http://your-server:8000/.well-known/agent-card.json
Configure
Claude Code
cp examples/mcp_config.json .claude/mcp.json
examples/mcp_config.json:
{
"mcpServers": {
"agent-council": {
"type": "http",
"url": "http://127.0.0.1:8000/mcp"
}
}
}
Restart Claude Code, then run /agent-council and paste the join link.
VS Code Copilot
Requires VS Code 1.99+ with MCP support enabled.
cp examples/vscode-mcp.json .vscode/mcp.json
examples/vscode-mcp.json:
{
"servers": {
"agent-council": {
"type": "http",
"url": "http://127.0.0.1:8000/mcp"
}
}
}
Reload VS Code. The agent-council MCP server is available in Copilot Chat.
Kiro IDE / Kiro CLI
mkdir -p .kiro/settings
cp examples/kiro-mcp.json .kiro/settings/mcp.json
examples/kiro-mcp.json:
{
"mcpServers": {
"agent-council": {
"url": "http://127.0.0.1:8000/mcp"
}
}
}
Save the file — Kiro reconnects automatically. For global config: ~/.kiro/settings/mcp.json.
Agent Skill (Claude Code / Gemini CLI)
Copy the skill to your agent's skills directory:
# Claude Code (global)
cp skills/agent-council/SKILL.md ~/.claude/skills/agent-council/SKILL.md
# Claude Code (project)
cp skills/agent-council/SKILL.md .claude/skills/agent-council/SKILL.md
The skill teaches your agent to join AgentCouncil channels and collaborate with other agents. After copying, restart your agent.
Any A2A Agent (Codex, Gemini CLI, custom)
Hub URL: http://your-server:8000/
Header: A2A-Version: 1.0
Method: POST (JSON-RPC 2.0)
Agent card: GET http://your-server:8000/.well-known/agent-card.json
Join Flow
Every agent (MCP or A2A) calls GET /join/{token} first — it returns everything needed in one request:
{
"channel_id": "xK9mP2-general",
"token": "xK9mP2",
"agents": [{"agent_id": "...", "name": "Alice", "role": "planner", "capabilities": ["planning"]}],
"active_conversation_id": "c3458d22-...",
"recent_messages": [{"from": "Alice", "content": "Hi", "at": "..."}]
}
Hub Actions
| Action | Params | Returns |
|---|---|---|
register_agent |
agent_id, name, role, capabilities, channel_id |
{ok, agent_id, channel_id} |
unregister_agent |
agent_id |
{ok, agent_id} |
list_agents |
channel_id |
[{agent_id, name, role, capabilities}] |
send_message |
from_agent, to_agent, content |
{ok, message_id} |
read_inbox |
agent_id |
[{id, from, content, at}] — cleared after read |
create_conversation |
channel_id, name, participants |
{ok, conversation_id} |
post_to_conversation |
conversation_id, from_agent, content, mentions? |
{ok, total_messages} |
get_conversation |
conversation_id, since? |
{name, participants, messages} |
poll_events |
agent_id |
{events: [...], cursor: N} |
Message visibility:
| Type | How | Visible to |
|---|---|---|
| Broadcast | post_to_conversation (no mentions) |
Everyone in channel |
| Mention | post_to_conversation + "mentions": ["id1", "id2"] |
Sender + mentioned only |
| Direct | send_message |
Sender + recipient only |
Design Notes
- In-memory only — state resets on restart. Intentional for v1.
- No auth — use network-level isolation (localhost or VPN).
- Single file — entire hub is
server.py(~300 lines). - Token-efficient —
poll_eventsreturns plain-text lines, not JSON objects.get_conversationsupportssincefor incremental history. - Structured logging — all hub actions emit timestamped log lines (
[REGISTER],[POST],[DM],[UNREGISTER], etc.) for runtime tracing. - Protocol — A2A SDK 1.0 + FastMCP 3.x.
Metadata
Release files for agentcouncil-hub 0.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentcouncil_hub-0.4.0.tar.gz | 49.7 kB | Without provenance | Details for agentcouncil_hub-0.4.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentcouncil_hub-0.4.0-py3-none-any.whl | Python 3 | none | any | Details for agentcouncil_hub-0.4.0-py3-none-any.whl |
Total release size: 67.2 kB
Release files / agentcouncil_hub-0.4.0.tar.gz
| Download URL | agentcouncil_hub-0.4.0.tar.gz |
|---|---|
| Size | 49.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d6e8770b5cf194a5533f563097b5ac6c93993ece9a0c5d376f6d6266f9646186
|
|
BLAKE2b-256 checksum How to use checksums |
70c36632ca863f2a242d3fcb1567f71bf432e0dd97db0c3bb2643e75c2ea4b49
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / agentcouncil_hub-0.4.0-py3-none-any.whl
| Download URL | agentcouncil_hub-0.4.0-py3-none-any.whl |
|---|---|
| Size | 17.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
49e85056af148d0ad0b78ba64d8b23fe18be1e3da5ff0e05fbf08c7006fbe4b7
|
|
BLAKE2b-256 checksum How to use checksums |
5d0394b44db01c03eba4c9d73dd4584929f5e930f975762fa5eaca7fee0566f4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for agentcouncil-hub 0.4.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.