agent-roundtable
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_URL | No | Base URL for local Ollama server. Required for provider 'ollama'. Default: 'http://localhost:11434'. | |
| OPENAI_API_KEY | No | Required for provider 'openai'. No default. | |
| TOGETHER_API_KEY | No | Required for provider 'together'. No default. | |
| ANTHROPIC_API_KEY | No | Required for provider 'anthropic'. No default. | |
| REPLICATE_API_TOKEN | No | Required for provider 'replicate'. No default. | |
| ROUNDTABLE_AGENTS_DIR | No | Directory containing agent prompt markdown files. Default: '.claude/agents' relative to working directory; use absolute path. | |
| ROUNDTABLE_MAX_TOKENS | No | Max output tokens (thinking tokens count). Default: '8192'. | |
| OPENAI_COMPATIBLE_MODEL | No | Default model for 'openai_compatible'. Default: 'default'. | |
| ROUNDTABLE_OLLAMA_MODEL | No | Default Ollama model. Default: 'qwen3:14b'. | |
| ROUNDTABLE_OPENAI_MODEL | No | Default OpenAI model. Default: 'gpt-5.6-luna'. | |
| OPENAI_COMPATIBLE_API_KEY | No | Optional API key for 'openai_compatible'. Sent to whichever base URL is used when set. | |
| ROUNDTABLE_LLM_TIMEOUT_MS | No | Per-request timeout in milliseconds. Default: '600000'. | |
| ROUNDTABLE_TOGETHER_MODEL | No | Default Together model. Default: 'zai-org/GLM-5.3'. | |
| OPENAI_COMPATIBLE_BASE_URL | No | Required for provider 'openai_compatible' unless a base_url is passed per call. No default. | |
| ROUNDTABLE_ANTHROPIC_MODEL | No | Default Anthropic model (id or alias). Default: 'claude-opus-5'. | |
| ROUNDTABLE_REPLICATE_MODEL | No | Default Replicate model. Default: 'qwen/qwen3-235b-a22b-instruct-2507'. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_meetingA | Start a meeting with an agent. Returns a meeting ID for follow-up messages. Use this to begin a synchronous conversation with another agent (CFO, FP&A, Product, etc.). |
| sayC | Continue a conversation in an active meeting. |
| end_meetingC | End a meeting and optionally get a summary. |
| list_meetingsB | List all active meetings. |
| start_local_meetingA | Start a LOCAL meeting with an agent using the installed Claude CLI. This uses your Claude Pro/Max subscription instead of API credits. Returns a meeting ID for follow-up messages. Ideal for cost-conscious lengthy conversations. |
| say_localA | Continue a conversation in an active LOCAL meeting (CLI-based). |
| end_local_meetingA | End a LOCAL meeting and optionally get a summary. |
| list_local_meetingsA | List all active LOCAL meetings (CLI-based). |
| chat_completionB | Call an LLM for text completion. Providers: anthropic (claude-opus-5 / claude-sonnet-5), openai (gpt-5.6-luna), together (Together AI), replicate (any Replicate text model), ollama (local, optional), openai_compatible (any /v1/chat/completions server). |
| start_collaborationA | Start a collaboration session where multiple agents discuss a topic with each other. Returns a collaboration ID. Agents take turns responding, building on each other's ideas. |
| continue_collaborationA | Continue an active collaboration for additional rounds. Agents take turns responding. |
| nudge_collaborationA | Inject a message from the orchestrator into the collaboration. Use to redirect discussion, ask clarifying questions, or provide additional context. |
| pause_collaborationA | Pause a running collaboration. Can be resumed with continue_collaboration. |
| end_collaborationC | End a collaboration and optionally get a summary of the discussion. |
| get_collaboration_transcriptA | Get the full transcript of a collaboration without ending it. |
| list_collaborationsB | List all active collaborations. |
| debug_envA | Debug tool to check server environment and API key status. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 17 tools
The collaboration, meeting, and local-meeting families are separated by clear prefixes and distinct lifecycle verbs, so an agent can usually tell which session type a tool operates on. The four parallel meeting/local-meeting pairs are the only real source of confusion, but the 'local' naming and CLI-vs-API descriptions make the distinction recoverable.
Most tools follow an action_noun pattern such as start_collaboration, end_meeting, and list_local_meetings, with the collaboration family especially consistent. The exceptions are 'say', 'say_local', and 'chat_completion', which break the pattern but remain readable and contextually unambiguous.
Seventeen tools is slightly above the ideal 3-15 range, but the server genuinely covers three session modes, direct LLM completion, and environment debugging. The local-meeting variants inflate the count, yet each tool has a distinct operational role.
The collaboration lifecycle is well covered with start, pause, continue, nudge, end, list, and transcript tools, and meetings have start/say/end/list coverage. Minor gaps include no meeting transcript retrieval and no explicit agent-discovery tool, but summaries and orchestration context can work around these.