MCP server that lets your agents convene and collaborate with other agents: meetings and multi-agent collaborations between personas on Anthropic, OpenAI, Together, Replicate, Ollama, or any...
Overview
An MCP server for multi-agent collaboration across six LLM providers: discuss, challenge and agree on a plan, then execute a contract with parallel workers, budgets and human oversight. Runs locally over stdio with Claude Code or any MCP client. Requires Node 22+. Create personas in that directory or copy the examples. Set keys for the providers you use; local meetings use your Claude CLI login. For source installs, .env, add-json and project .mcp.json registration, see getting started and configuration. After a rebuild, reconnect with /mcp. Ask in chat; the host calls the tools and keeps session ids for follow-ups. Heads-down runs execute an agreed, frozen contract in parallel task worktrees with leases, checks, a watchdog and escalations. Example: “Execute the approved contract with a $20 budget and a dashboard; keep me posted here.” See the example contract. Worker tools appear in both; the orchestrator's copies also require execution_id and agent_token.
README
agent-roundtable
Agents talk it out at the table, then go heads-down. An MCP server for multi-agent collaboration across six LLM providers: discuss, challenge and agree on a plan, then execute a contract with parallel workers, budgets and human oversight. Runs locally over stdio with Claude Code or any MCP client. Requires Node 22+.
Install and register with Claude Code
npm install -g agent-roundtable
claude mcp add agent-roundtable \
-e ROUNDTABLE_AGENTS_DIR="$HOME/my-project/.claude/agents" \
-- agent-roundtable
Create personas in that directory or copy the examples. Set keys for the providers you use; local meetings use your Claude CLI login. For source installs, .env, add-json and project .mcp.json registration, see getting started and configuration. After a rebuild, reconnect with /mcp.
Modes
At the table
Ask in chat; the host calls the tools and keeps session ids for follow-ups.
| Format | What it does | Example prompt |
|---|---|---|
| Meeting | Talk with one persona on a chosen provider/model. | “Start a meeting via agent-roundtable with cfo about our Q3 budget.” |
| Local meeting | Talk with a persona through your installed Claude CLI and login. | “Start a local meeting with product-lead about onboarding.” |
| Collaboration: collaborate | Personas take turns building a shared idea. | “Have cfo and product-lead collaborate on launch priorities for three rounds.” |
| Collaboration: debate | One proponent faces challengers. | “Have cfo defend our pricing plan against skeptic in a roundtable debate.” |
| Collaboration: waffle-house | A defender refines an idea through repeated attacks and rebuttals. | “Run a two-round waffle-house: product-lead defends one-click checkout against cfo and skeptic.” |
| Collaboration: conversation | Informal colleague chat with an optional theme and private grounding. | “Let cfo and product-lead chat about the launch in conversation mode.” |
| Ultraplan | Collect input, review revisions and record sign-offs on a plan. | “Ultraplan the launch with product-lead, cfo and skeptic; show the final document verbatim.” |
| Agent workshops | Specialists create or improve an agent and reusable skills. | “Have cfo and skeptic create a budget agent, then improve product-lead’s escalation rules; preview both.” |
| Prototype mode | Show ephemeral proposals on a local board for assessment. | “Run a prototype collaboration on checkout with product-lead and skeptic.” |
| Public sessions | Mirror an explicitly public session to ntfy or a webhook. | “Make that pricing debate public and give me the viewing link.” |
Heads-down
Heads-down runs execute an agreed, frozen contract in parallel task worktrees with leases, checks, a watchdog and escalations. Example: “Execute the approved contract with a $20 budget and a dashboard; keep me posted here.” See the example contract.
Tools
37 tools on the orchestrator server; 7 on worker servers. Worker tools appear in both; the orchestrator’s copies also require execution_id and agent_token. The table follows the registered definitions in src/tools/*.ts; full arguments and examples.
| Group | Tool | Purpose |
|---|---|---|
| Meetings | start_meeting |
Start a conversation with one persona. |
| Meetings | say |
Send a message in an API meeting. |
| Meetings | end_meeting |
End an API meeting, optionally with a summary. |
| Meetings | list_meetings |
List active API meetings. |
| Local meetings | start_local_meeting |
Start a persona meeting on the local Claude CLI. |
| Local meetings | say_local |
Send a message in a local meeting. |
| Local meetings | end_local_meeting |
End a local meeting, optionally with a summary. |
| Local meetings | list_local_meetings |
List active local meetings. |
| Collaborations | start_collaboration |
Start a discussion between two or more personas. |
| Collaborations | continue_collaboration |
Run additional rounds. |
| Collaborations | nudge_collaboration |
Inject guidance without consuming an agent turn. |
| Collaborations | pause_collaboration |
Pause after the current turn. |
| Collaborations | end_collaboration |
End a discussion and return its transcript and optional summary. |
| Collaborations | get_collaboration_transcript |
Read a discussion without ending it. |
| Collaborations | list_collaborations |
List active collaborations. |
| Ultraplan | start_ultraplan |
Collect input and begin a reviewed plan. |
| Ultraplan | submit_plan |
Review a full plan version or collect final sign-offs. |
| Ultraplan | end_ultraplan |
Close a plan without sign-offs. |
| Agent workshops | create_agent |
Have specialists design and optionally save a new agent. |
| Agent workshops | improve_agent |
Review and optionally update an agent with a backup. |
| Contracts | propose_contract |
Turn a plan into a draft execution contract. |
| Contracts | amend_contract |
Apply a versioned contract merge patch. |
| Contracts | freeze_contract |
Freeze the current contract after consent. |
| Runs | execute |
Preflight and start an authorized frozen contract. |
| Runs | execution_status |
Report progress, blockers, budget and context. |
| Runs | control_execution |
Pause, resume, steer, abort or purge a run. |
| Runs | resolve_escalation |
Decide, huddle, retry, reassign or amend after an escalation. |
| Runs | join_execution |
Register an external worker and return its token once. |
| Workers (both servers) | read_blackboard |
Read shared run state and your inbox. |
| Workers (both servers) | claim_task |
Claim or release an external worker task. |
| Workers (both servers) | lease |
Request or release path leases. |
| Workers (both servers) | post_update |
Post progress, notes, interfaces, needs or acknowledgements. |
| Workers (both servers) | run_command |
Run structured argv or a contract check in the sandbox. |
| Workers (both servers) | submit_work |
Checkpoint or submit leased changes for checks and merging. |
| Workers (both servers) | escalate |
Raise a blocker, question, conflict or emergency. |
| Completion | chat_completion |
Call any of the six text providers directly. |
| Diagnostics | debug_env |
Inspect configuration and key presence without key values. |
CLI
No arguments starts the orchestrator MCP server. The 8 subcommands are documented in the CLI reference.
| Subcommand | Purpose |
|---|---|
mcp |
Start an orchestrator or token-bound worker stdio server. |
hook pre-tool-use |
Check worker file access and leases using stdin hook JSON. |
run |
Run or recover a heads-down runner. |
watch --as |
Wait for one orchestrator wake, printing JSON. |
status [--json] |
Inspect a run’s tasks, budget and health. |
verify [--json] |
Verify execution and audit chains. |
purge --confirm |
Delete a finished run’s worktrees, branches and log. |
help |
Print usage. |
Docs
- Getting started and registration
- Mode guides: collaborations, ultraplan, agent workshops, prototypes, public sessions
- Heads-down user guide and design specification
- Tool reference and CLI reference
- Configuration and providers
- Agent personas and skills and session archives
- Changelog, threat model, security controls
Security
Read the security policy and private reporting instructions.
Contributing
Build and run npm test before a pull request. See contributing for test isolation and checks.
License
MIT.
Install
This server does not publish a one-line install command.
Open the repository installation guide