autogen-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| register_agent | Register a persistent sub-agent that owns the context of one task. The agent keeps its conversation memory for the whole server session and logs every exchange to .autogen-swarm/agents/.jsonl in the project the session runs in. Args: name: Unique identifier (must be a valid Python identifier, e.g. "auth_refactor"). model: ":" or alias "opus" / "heavy" / "cheap". role: The task this agent owns — becomes part of its system prompt and is what other agents will ask it about. system: Optional extra persona/instructions. tier: "heavy" (can initiate conversations via its converse tool) or "cheap" (must emit NEED_INFO lines for the manager to relay). Defaults to "cheap" for the cheap alias, "heavy" otherwise. |
| send_messageA | Send a message to a registered agent and return its reply (manager channel). Context persists across calls — the agent remembers previous exchanges.
Check |
| list_agents | List all registered persistent sub-agents. |
| agent_log | Return an agent's exchange history starting at entry |
| remove_agentC | Unregister an agent and release its model client. Its log file remains. |
| start_conversationA | Start an autonomous multi-agent conversation running in the background. Args: topic: The task or question the agents discuss. agents: Optional participants, each {"name", "model", "system"}. "model" is ":" — e.g. "anthropic:claude-opus-4-8", "deepinfra:zai-org/GLM-5.2" — or an alias: "opus", "heavy", "cheap". Defaults to an opus + GLM-5.2 pair (proponent vs critic). max_rounds: Full round-robin rounds before the conversation ends. Returns the conversation_id to use with get_transcript / inject_message / stop_conversation. Poll get_transcript to follow progress. |
| get_transcriptA | Return a conversation's status and its turns starting at since_turn. Pass the previous total_turns as since_turn to get only new turns. |
| inject_messageA | Queue a steering message for a running conversation. Delivered to the agents at the next round boundary (after the current round-robin round completes). |
| stop_conversationA | Cancel a running conversation. The transcript so far is preserved. |
| list_conversationsA | List all conversations known to this server session. |
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 7 tools
Each tool has a clearly distinct purpose: sending messages, removing agents, starting/stopping conversations, retrieving transcripts, injecting messages, and listing conversations. No overlapping functionality.
All tool names follow a consistent verb_noun pattern (e.g., send_message, start_conversation, get_transcript) using snake_case throughout.
With 7 tools, the server is well-scoped for multi-agent conversation management. Each tool serves a specific purpose without redundancy or being too thin.
Core conversation lifecycle (start, get transcript, inject message, stop) and agent management (remove) are covered. Minor gaps include lacking an explicit 'list agents' tool or ability to modify agent configurations.